working
This commit is contained in:
Tulis
1
.gitattributes
vendored
Normal file
1
.gitattributes
vendored
Normal file
@ -0,0 +1 @@
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
4
.gitignore
vendored
4
.gitignore
vendored
@ -1,6 +1,8 @@
|
||||
/mmdetection/
|
||||
/mmpose/
|
||||
/.ipynb_checkpoints/
|
||||
/.gpu/
|
||||
/.gpu-3d/
|
||||
/.venv/
|
||||
/venv/
|
||||
|
||||
yolo11*
|
||||
7
.idea/JustTwerk.iml
generated
7
.idea/JustTwerk.iml
generated
@ -8,7 +8,10 @@
|
||||
<orderEntry type="sourceFolder" forTests="false" />
|
||||
</component>
|
||||
<component name="PyDocumentationSettings">
|
||||
<option name="format" value="GOOGLE" />
|
||||
<option name="myDocStringFormat" value="Google" />
|
||||
<option name="format" value="PLAIN" />
|
||||
<option name="myDocStringFormat" value="Plain" />
|
||||
</component>
|
||||
<component name="TestRunnerService">
|
||||
<option name="PROJECT_TEST_RUNNER" value="py.test" />
|
||||
</component>
|
||||
</module>
|
||||
101
.idea/workspace.xml
generated
101
.idea/workspace.xml
generated
@ -5,22 +5,28 @@
|
||||
</component>
|
||||
<component name="ChangeListManager">
|
||||
<list default="true" id="441a4e7b-d6ce-44cb-92c5-2f22f1b1874f" name="Changes" comment="initial commit">
|
||||
<change afterPath="$PROJECT_DIR$/.gitignore" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.idea/JustTwerk.iml" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.idea/inspectionProfiles/profiles_settings.xml" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.idea/misc.xml" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.idea/vcs.xml" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/02_whole_body_from_image.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/body3d.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/humanPoseDetection.ipynb" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/is_torch.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/test.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/mmpose/demo/body3d_pose_lifter_demo.py" beforeDir="false" afterPath="$PROJECT_DIR$/mmpose/demo/body3d_pose_lifter_demo.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/.gitattributes" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/calculate.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/draw.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/filter.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/main.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/ploting.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/receive_images.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/receiver.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/sender.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/utils.py" afterDir="false" />
|
||||
<change afterPath="$PROJECT_DIR$/video_methods.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/.gitignore" beforeDir="false" afterPath="$PROJECT_DIR$/.gitignore" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/.idea/JustTwerk.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/JustTwerk.iml" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/02_whole_body_from_image.py" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/body3d.py" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/humanPoseDetection.ipynb" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/test.py" beforeDir="false" afterPath="$PROJECT_DIR$/test.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth" beforeDir="false" />
|
||||
</list>
|
||||
<option name="SHOW_DIALOG" value="false" />
|
||||
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
||||
@ -36,6 +42,7 @@
|
||||
</component>
|
||||
<component name="Git.Settings">
|
||||
<option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
|
||||
<option name="ROOT_SYNC" value="SYNC" />
|
||||
</component>
|
||||
<component name="ProjectColorInfo">{
|
||||
"associatedIndex": 6
|
||||
@ -49,13 +56,21 @@
|
||||
"keyToString": {
|
||||
"ModuleVcsDetector.initialDetectionPerformed": "true",
|
||||
"Python.02_whole_body_from_image.executor": "Run",
|
||||
"Python.3d.executor": "Run",
|
||||
"Python.body3d.executor": "Run",
|
||||
"Python.body3d_pose_lifter_demo.executor": "Run",
|
||||
"Python.calculate.executor": "Run",
|
||||
"Python.checkpoint.executor": "Run",
|
||||
"Python.draw.executor": "Run",
|
||||
"Python.filter.executor": "Run",
|
||||
"Python.is_torch.executor": "Run",
|
||||
"Python.local_visualizer_3d.executor": "Run",
|
||||
"Python.openpose.executor": "Run",
|
||||
"Python.receive_images.executor": "Run",
|
||||
"Python.receiver.executor": "Run",
|
||||
"Python.sender.executor": "Run",
|
||||
"Python.test.executor": "Run",
|
||||
"Python.ultralytics-test.executor": "Run",
|
||||
"RunOnceActivity.ShowReadmeOnStart": "true",
|
||||
"RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager.252": "true",
|
||||
"RunOnceActivity.git.unshallow": "true",
|
||||
@ -66,7 +81,7 @@
|
||||
"node.js.selected.package.eslint": "(autodetect)",
|
||||
"node.js.selected.package.tslint": "(autodetect)",
|
||||
"nodejs_package_manager_path": "npm",
|
||||
"settings.editor.selected.configurable": "editor.preferences.fonts.default",
|
||||
"settings.editor.selected.configurable": "configurable.group.editor",
|
||||
"vue.rearranger.settings.migration": "true"
|
||||
}
|
||||
}]]></component>
|
||||
@ -76,6 +91,29 @@
|
||||
</key>
|
||||
</component>
|
||||
<component name="RunManager">
|
||||
<configuration name="draw" type="PythonConfigurationType" factoryName="Python" temporary="true" nameIsGenerated="true">
|
||||
<module name="JustTwerk" />
|
||||
<option name="ENV_FILES" value="" />
|
||||
<option name="INTERPRETER_OPTIONS" value="" />
|
||||
<option name="PARENT_ENVS" value="true" />
|
||||
<envs>
|
||||
<env name="PYTHONUNBUFFERED" value="1" />
|
||||
</envs>
|
||||
<option name="SDK_HOME" value="" />
|
||||
<option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
|
||||
<option name="IS_MODULE_SDK" value="true" />
|
||||
<option name="ADD_CONTENT_ROOTS" value="true" />
|
||||
<option name="ADD_SOURCE_ROOTS" value="true" />
|
||||
<EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
|
||||
<option name="SCRIPT_NAME" value="$PROJECT_DIR$/draw.py" />
|
||||
<option name="PARAMETERS" value="" />
|
||||
<option name="SHOW_COMMAND_LINE" value="false" />
|
||||
<option name="EMULATE_TERMINAL" value="false" />
|
||||
<option name="MODULE_MODE" value="false" />
|
||||
<option name="REDIRECT_INPUT" value="false" />
|
||||
<option name="INPUT_FILE" value="" />
|
||||
<method v="2" />
|
||||
</configuration>
|
||||
<configuration name="test" type="PythonConfigurationType" factoryName="Python" temporary="true" nameIsGenerated="true">
|
||||
<module name="JustTwerk" />
|
||||
<option name="ENV_FILES" value="" />
|
||||
@ -101,6 +139,7 @@
|
||||
</configuration>
|
||||
<recent_temporary>
|
||||
<list>
|
||||
<item itemvalue="Python.draw" />
|
||||
<item itemvalue="Python.test" />
|
||||
</list>
|
||||
</recent_temporary>
|
||||
@ -124,8 +163,20 @@
|
||||
<workItem from="1755884695519" duration="705000" />
|
||||
<workItem from="1755885461444" duration="2686000" />
|
||||
<workItem from="1755888180570" duration="3107000" />
|
||||
<workItem from="1755891319108" duration="23374000" />
|
||||
<workItem from="1755891319108" duration="33842000" />
|
||||
<workItem from="1755974689137" duration="258000" />
|
||||
<workItem from="1755974961407" duration="19035000" />
|
||||
<workItem from="1756053672258" duration="10010000" />
|
||||
</task>
|
||||
<task id="LOCAL-00001" summary="initial commit">
|
||||
<option name="closed" value="true" />
|
||||
<created>1755963464017</created>
|
||||
<option name="number" value="00001" />
|
||||
<option name="presentableId" value="LOCAL-00001" />
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1755963464017</updated>
|
||||
</task>
|
||||
<option name="localTasksCounter" value="2" />
|
||||
<servers />
|
||||
</component>
|
||||
<component name="TypeScriptGeneratedFilesManager">
|
||||
@ -136,13 +187,21 @@
|
||||
<option name="LAST_COMMIT_MESSAGE" value="initial commit" />
|
||||
</component>
|
||||
<component name="com.intellij.coverage.CoverageDataManagerImpl">
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$openpose.coverage" NAME="openpose Coverage Results" MODIFIED="1755886110615" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/human-pose-estimation-opencv" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$receiver.coverage" NAME="receiver Coverage Results" MODIFIED="1756142451233" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$filter.coverage" NAME="filter Coverage Results" MODIFIED="1755972211046" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$body3d_pose_lifter_demo.coverage" NAME="body3d_pose_lifter_demo Coverage Results" MODIFIED="1755937235510" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/mmpose/demo" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$body3d.coverage" NAME="body3d Coverage Results" MODIFIED="1755944498141" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$02_whole_body_from_image.coverage" NAME="02_whole_body_from_image Coverage Results" MODIFIED="1755885569302" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$local_visualizer_3d.coverage" NAME="local_visualizer_3d Coverage Results" MODIFIED="1755937454029" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/.gpu/Lib/site-packages/mmpose/visualization" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$checkpoint.coverage" NAME="checkpoint Coverage Results" MODIFIED="1755936916130" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/.gpu/Lib/site-packages/mmengine/runner" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$calculate.coverage" NAME="calculate Coverage Results" MODIFIED="1756054778057" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$receive_images.coverage" NAME="receive_images Coverage Results" MODIFIED="1755966230858" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$sender.coverage" NAME="sender Coverage Results" MODIFIED="1756142463914" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$openpose.coverage" NAME="openpose Coverage Results" MODIFIED="1755886110615" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/human-pose-estimation-opencv" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$draw.coverage" NAME="draw Coverage Results" MODIFIED="1756053706980" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$ultralytics_test.coverage" NAME="ultralytics-test Coverage Results" MODIFIED="1756116377896" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$3d.coverage" NAME="3d Coverage Results" MODIFIED="1756027604884" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$local_visualizer_3d.coverage" NAME="local_visualizer_3d Coverage Results" MODIFIED="1755937454029" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/.gpu/Lib/site-packages/mmpose/visualization" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$is_torch.coverage" NAME="is_torch Coverage Results" MODIFIED="1755943611769" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$test.coverage" NAME="test Coverage Results" MODIFIED="1755962675907" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
<SUITE FILE_PATH="coverage/JustTwerk$test.coverage" NAME="test Coverage Results" MODIFIED="1756025632346" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
||||
</component>
|
||||
</project>
|
||||
@ -1,70 +0,0 @@
|
||||
# From Python
|
||||
# It requires OpenCV installed for Python
|
||||
import sys
|
||||
import cv2
|
||||
import os
|
||||
from sys import platform
|
||||
import argparse
|
||||
|
||||
try:
|
||||
# Import Openpose (Windows/Ubuntu/OSX)
|
||||
dir_path = r"C:\Users\Kajetan\Documents\openpose/python"
|
||||
try:
|
||||
# Change these variables to point to the correct folder (Release/x64 etc.)
|
||||
sys.path.append(dir_path + '/../bin/python/openpose/Release');
|
||||
os.environ['PATH'] = os.environ['PATH'] + ';' + dir_path + '/../x64/Release;' + dir_path + '/../bin;'
|
||||
|
||||
print(os.environ["PATH"])
|
||||
import pyopenpose as op
|
||||
except ImportError as e:
|
||||
print('Error: OpenPose library could not be found. Did you enable `BUILD_PYTHON` in CMake and have this Python script in the right folder?')
|
||||
raise e
|
||||
|
||||
# Flags
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--image_path", default="../examples/media/COCO_val2014_000000000241.jpg", help="Process an image. Read all standard formats (jpg, png, bmp, etc.).")
|
||||
args = parser.parse_known_args()
|
||||
|
||||
# Custom Params (refer to include/openpose/flags.hpp for more parameters)
|
||||
params = dict()
|
||||
params["model_folder"] = "../models/"
|
||||
params["face"] = True
|
||||
params["hand"] = True
|
||||
|
||||
# Add others in path?
|
||||
for i in range(0, len(args[1])):
|
||||
curr_item = args[1][i]
|
||||
if i != len(args[1])-1: next_item = args[1][i+1]
|
||||
else: next_item = "1"
|
||||
if "--" in curr_item and "--" in next_item:
|
||||
key = curr_item.replace('-','')
|
||||
if key not in params: params[key] = "1"
|
||||
elif "--" in curr_item and "--" not in next_item:
|
||||
key = curr_item.replace('-','')
|
||||
if key not in params: params[key] = next_item
|
||||
|
||||
# Construct it from system arguments
|
||||
# op.init_argv(args[1])
|
||||
# oppython = op.OpenposePython()
|
||||
|
||||
# Starting OpenPose
|
||||
opWrapper = op.WrapperPython()
|
||||
opWrapper.configure(params)
|
||||
opWrapper.start()
|
||||
|
||||
# Process Image
|
||||
datum = op.Datum()
|
||||
imageToProcess = cv2.imread(args[0].image_path)
|
||||
datum.cvInputData = imageToProcess
|
||||
opWrapper.emplaceAndPop(op.VectorDatum([datum]))
|
||||
|
||||
# Display Image
|
||||
print("Body keypoints: \n" + str(datum.poseKeypoints))
|
||||
print("Face keypoints: \n" + str(datum.faceKeypoints))
|
||||
print("Left hand keypoints: \n" + str(datum.handKeypoints[0]))
|
||||
print("Right hand keypoints: \n" + str(datum.handKeypoints[1]))
|
||||
cv2.imshow("OpenPose 1.7.0 - Tutorial Python API", datum.cvOutputData)
|
||||
cv2.waitKey(0)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
sys.exit(-1)
|
||||
555
body3d.py
555
body3d.py
@ -1,555 +0,0 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import logging
|
||||
import mimetypes
|
||||
import os
|
||||
import time
|
||||
from argparse import ArgumentParser
|
||||
from functools import partial
|
||||
|
||||
import cv2
|
||||
import json_tricks as json
|
||||
import mmcv
|
||||
import mmengine
|
||||
import numpy as np
|
||||
from mmengine.logging import print_log
|
||||
|
||||
from mmpose.apis import (_track_by_iou, _track_by_oks,
|
||||
convert_keypoint_definition, extract_pose_sequence,
|
||||
inference_pose_lifter_model, inference_topdown,
|
||||
init_model)
|
||||
from mmpose.models.pose_estimators import PoseLifter
|
||||
from mmpose.models.pose_estimators.topdown import TopdownPoseEstimator
|
||||
from mmpose.registry import VISUALIZERS
|
||||
from mmpose.structures import (PoseDataSample, merge_data_samples,
|
||||
split_instances)
|
||||
from mmpose.utils import adapt_mmdet_pipeline
|
||||
|
||||
try:
|
||||
from mmdet.apis import inference_detector, init_detector
|
||||
has_mmdet = True
|
||||
except (ImportError, ModuleNotFoundError):
|
||||
has_mmdet = False
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = ArgumentParser()
|
||||
parser.add_argument('--det_config', default="mmpose/demo/mmdetection_cfg/rtmdet_m_640-8xb32_coco-person.py", help='Config file for detection')
|
||||
parser.add_argument('--det_checkpoint', default="rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth", help='Checkpoint file for detection')
|
||||
parser.add_argument(
|
||||
'--pose_estimator_config',
|
||||
type=str,
|
||||
default="mmpose/configs/body_2d_keypoint/rtmpose/body8/rtmpose-m_8xb256-420e_body8-256x192.py",
|
||||
help='Config file for the 1st stage 2D pose estimator')
|
||||
parser.add_argument(
|
||||
'--pose_estimator_checkpoint',
|
||||
type=str,
|
||||
default="rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth",
|
||||
help='Checkpoint file for the 1st stage 2D pose estimator')
|
||||
parser.add_argument(
|
||||
'--pose_lifter_config',
|
||||
default="mmpose/configs/body_3d_keypoint/video_pose_lift/h36m/video-pose-lift_tcn-243frm-supv-cpn-ft_8xb128-200e_h36m.py",
|
||||
help='Config file for the 2nd stage pose lifter model')
|
||||
parser.add_argument(
|
||||
'--pose_lifter_checkpoint',
|
||||
default="videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth",
|
||||
help='Checkpoint file for the 2nd stage pose lifter model')
|
||||
parser.add_argument('--input', type=str, default='webcam', help='Video path')
|
||||
parser.add_argument(
|
||||
'--show',
|
||||
action='store_true',
|
||||
default=True,
|
||||
help='Whether to show visualizations')
|
||||
parser.add_argument(
|
||||
'--disable-rebase-keypoint',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='Whether to disable rebasing the predicted 3D pose so its '
|
||||
'lowest keypoint has a height of 0 (landing on the ground). Rebase '
|
||||
'is useful for visualization when the model do not predict the '
|
||||
'global position of the 3D pose.')
|
||||
parser.add_argument(
|
||||
'--disable-norm-pose-2d',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='Whether to scale the bbox (along with the 2D pose) to the '
|
||||
'average bbox scale of the dataset, and move the bbox (along with the '
|
||||
'2D pose) to the average bbox center of the dataset. This is useful '
|
||||
'when bbox is small, especially in multi-person scenarios.')
|
||||
parser.add_argument(
|
||||
'--num-instances',
|
||||
type=int,
|
||||
default=1,
|
||||
help='The number of 3D poses to be visualized in every frame. If '
|
||||
'less than 0, it will be set to the number of pose results in the '
|
||||
'first frame.')
|
||||
parser.add_argument(
|
||||
'--output-root',
|
||||
type=str,
|
||||
default='',
|
||||
help='Root of the output video file. '
|
||||
'Default not saving the visualization video.')
|
||||
parser.add_argument(
|
||||
'--save-predictions',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='Whether to save predicted results')
|
||||
parser.add_argument(
|
||||
'--device', default='cuda:0', help='Device used for inference')
|
||||
parser.add_argument(
|
||||
'--det-cat-id',
|
||||
type=int,
|
||||
default=0,
|
||||
help='Category id for bounding box detection model')
|
||||
parser.add_argument(
|
||||
'--bbox-thr',
|
||||
type=float,
|
||||
default=0.3,
|
||||
help='Bounding box score threshold')
|
||||
parser.add_argument('--kpt-thr', type=float, default=0.3)
|
||||
parser.add_argument(
|
||||
'--use-oks-tracking', action='store_true', help='Using OKS tracking')
|
||||
parser.add_argument(
|
||||
'--tracking-thr', type=float, default=0.3, help='Tracking threshold')
|
||||
parser.add_argument(
|
||||
'--show-interval', type=int, default=0, help='Sleep seconds per frame')
|
||||
parser.add_argument(
|
||||
'--thickness',
|
||||
type=int,
|
||||
default=1,
|
||||
help='Link thickness for visualization')
|
||||
parser.add_argument(
|
||||
'--radius',
|
||||
type=int,
|
||||
default=3,
|
||||
help='Keypoint radius for visualization')
|
||||
parser.add_argument(
|
||||
'--online',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='Inference mode. If set to True, can not use future frame'
|
||||
'information when using multi frames for inference in the 2D pose'
|
||||
'detection stage. Default: False.')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def process_one_image(args, detector, frame, frame_idx, pose_estimator,
|
||||
pose_est_results_last, pose_est_results_list, next_id,
|
||||
pose_lifter, visualize_frame, visualizer):
|
||||
"""Visualize detected and predicted keypoints of one image.
|
||||
|
||||
Pipeline of this function:
|
||||
|
||||
frame
|
||||
|
|
||||
V
|
||||
+-----------------+
|
||||
| detector |
|
||||
+-----------------+
|
||||
| det_result
|
||||
V
|
||||
+-----------------+
|
||||
| pose_estimator |
|
||||
+-----------------+
|
||||
| pose_est_results
|
||||
V
|
||||
+--------------------------------------------+
|
||||
| convert 2d kpts into pose-lifting format |
|
||||
+--------------------------------------------+
|
||||
| pose_est_results_list
|
||||
V
|
||||
+-----------------------+
|
||||
| extract_pose_sequence |
|
||||
+-----------------------+
|
||||
| pose_seq_2d
|
||||
V
|
||||
+-------------+
|
||||
| pose_lifter |
|
||||
+-------------+
|
||||
| pose_lift_results
|
||||
V
|
||||
+-----------------+
|
||||
| post-processing |
|
||||
+-----------------+
|
||||
| pred_3d_data_samples
|
||||
V
|
||||
+------------+
|
||||
| visualizer |
|
||||
+------------+
|
||||
|
||||
Args:
|
||||
args (Argument): Custom command-line arguments.
|
||||
detector (mmdet.BaseDetector): The mmdet detector.
|
||||
frame (np.ndarray): The image frame read from input image or video.
|
||||
frame_idx (int): The index of current frame.
|
||||
pose_estimator (TopdownPoseEstimator): The pose estimator for 2d pose.
|
||||
pose_est_results_last (list(PoseDataSample)): The results of pose
|
||||
estimation from the last frame for tracking instances.
|
||||
pose_est_results_list (list(list(PoseDataSample))): The list of all
|
||||
pose estimation results converted by
|
||||
``convert_keypoint_definition`` from previous frames. In
|
||||
pose-lifting stage it is used to obtain the 2d estimation sequence.
|
||||
next_id (int): The next track id to be used.
|
||||
pose_lifter (PoseLifter): The pose-lifter for estimating 3d pose.
|
||||
visualize_frame (np.ndarray): The image for drawing the results on.
|
||||
visualizer (Visualizer): The visualizer for visualizing the 2d and 3d
|
||||
pose estimation results.
|
||||
|
||||
Returns:
|
||||
pose_est_results (list(PoseDataSample)): The pose estimation result of
|
||||
the current frame.
|
||||
pose_est_results_list (list(list(PoseDataSample))): The list of all
|
||||
converted pose estimation results until the current frame.
|
||||
pred_3d_instances (InstanceData): The result of pose-lifting.
|
||||
Specifically, the predicted keypoints and scores are saved at
|
||||
``pred_3d_instances.keypoints`` and
|
||||
``pred_3d_instances.keypoint_scores``.
|
||||
next_id (int): The next track id to be used.
|
||||
"""
|
||||
pose_lift_dataset = pose_lifter.cfg.test_dataloader.dataset
|
||||
pose_lift_dataset_name = pose_lifter.dataset_meta['dataset_name']
|
||||
|
||||
# First stage: conduct 2D pose detection in a Topdown manner
|
||||
# use detector to obtain person bounding boxes
|
||||
det_result = inference_detector(detector, frame)
|
||||
pred_instance = det_result.pred_instances.cpu().numpy()
|
||||
|
||||
# filter out the person instances with category and bbox threshold
|
||||
# e.g. 0 for person in COCO
|
||||
bboxes = pred_instance.bboxes
|
||||
bboxes = bboxes[np.logical_and(pred_instance.labels == args.det_cat_id,
|
||||
pred_instance.scores > args.bbox_thr)]
|
||||
|
||||
# estimate pose results for current image
|
||||
pose_est_results = inference_topdown(pose_estimator, frame, bboxes)
|
||||
|
||||
if args.use_oks_tracking:
|
||||
_track = partial(_track_by_oks)
|
||||
else:
|
||||
_track = _track_by_iou
|
||||
|
||||
pose_det_dataset_name = pose_estimator.dataset_meta['dataset_name']
|
||||
pose_est_results_converted = []
|
||||
|
||||
# convert 2d pose estimation results into the format for pose-lifting
|
||||
# such as changing the keypoint order, flipping the keypoint, etc.
|
||||
for i, data_sample in enumerate(pose_est_results):
|
||||
pred_instances = data_sample.pred_instances.cpu().numpy()
|
||||
keypoints = pred_instances.keypoints
|
||||
# calculate area and bbox
|
||||
if 'bboxes' in pred_instances:
|
||||
areas = np.array([(bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
|
||||
for bbox in pred_instances.bboxes])
|
||||
pose_est_results[i].pred_instances.set_field(areas, 'areas')
|
||||
else:
|
||||
areas, bboxes = [], []
|
||||
for keypoint in keypoints:
|
||||
xmin = np.min(keypoint[:, 0][keypoint[:, 0] > 0], initial=1e10)
|
||||
xmax = np.max(keypoint[:, 0])
|
||||
ymin = np.min(keypoint[:, 1][keypoint[:, 1] > 0], initial=1e10)
|
||||
ymax = np.max(keypoint[:, 1])
|
||||
areas.append((xmax - xmin) * (ymax - ymin))
|
||||
bboxes.append([xmin, ymin, xmax, ymax])
|
||||
pose_est_results[i].pred_instances.areas = np.array(areas)
|
||||
pose_est_results[i].pred_instances.bboxes = np.array(bboxes)
|
||||
|
||||
# track id
|
||||
track_id, pose_est_results_last, _ = _track(data_sample,
|
||||
pose_est_results_last,
|
||||
args.tracking_thr)
|
||||
if track_id == -1:
|
||||
if np.count_nonzero(keypoints[:, :, 1]) >= 3:
|
||||
track_id = next_id
|
||||
next_id += 1
|
||||
else:
|
||||
# If the number of keypoints detected is small,
|
||||
# delete that person instance.
|
||||
keypoints[:, :, 1] = -10
|
||||
pose_est_results[i].pred_instances.set_field(
|
||||
keypoints, 'keypoints')
|
||||
pose_est_results[i].pred_instances.set_field(
|
||||
pred_instances.bboxes * 0, 'bboxes')
|
||||
pose_est_results[i].set_field(pred_instances, 'pred_instances')
|
||||
track_id = -1
|
||||
pose_est_results[i].set_field(track_id, 'track_id')
|
||||
|
||||
# convert keypoints for pose-lifting
|
||||
pose_est_result_converted = PoseDataSample()
|
||||
pose_est_result_converted.set_field(
|
||||
pose_est_results[i].pred_instances.clone(), 'pred_instances')
|
||||
pose_est_result_converted.set_field(
|
||||
pose_est_results[i].gt_instances.clone(), 'gt_instances')
|
||||
keypoints = convert_keypoint_definition(keypoints,
|
||||
pose_det_dataset_name,
|
||||
pose_lift_dataset_name)
|
||||
pose_est_result_converted.pred_instances.set_field(
|
||||
keypoints, 'keypoints')
|
||||
pose_est_result_converted.set_field(pose_est_results[i].track_id,
|
||||
'track_id')
|
||||
pose_est_results_converted.append(pose_est_result_converted)
|
||||
|
||||
pose_est_results_list.append(pose_est_results_converted.copy())
|
||||
|
||||
# Second stage: Pose lifting
|
||||
# extract and pad input pose2d sequence
|
||||
pose_seq_2d = extract_pose_sequence(
|
||||
pose_est_results_list,
|
||||
frame_idx=frame_idx,
|
||||
causal=pose_lift_dataset.get('causal', False),
|
||||
seq_len=pose_lift_dataset.get('seq_len', 1),
|
||||
step=pose_lift_dataset.get('seq_step', 1))
|
||||
|
||||
# conduct 2D-to-3D pose lifting
|
||||
norm_pose_2d = not args.disable_norm_pose_2d
|
||||
pose_lift_results = inference_pose_lifter_model(
|
||||
pose_lifter,
|
||||
pose_seq_2d,
|
||||
image_size=visualize_frame.shape[:2],
|
||||
norm_pose_2d=norm_pose_2d)
|
||||
|
||||
# post-processing
|
||||
for idx, pose_lift_result in enumerate(pose_lift_results):
|
||||
pose_lift_result.track_id = pose_est_results[idx].get('track_id', 1e4)
|
||||
|
||||
pred_instances = pose_lift_result.pred_instances
|
||||
keypoints = pred_instances.keypoints
|
||||
keypoint_scores = pred_instances.keypoint_scores
|
||||
if keypoint_scores.ndim == 3:
|
||||
keypoint_scores = np.squeeze(keypoint_scores, axis=1)
|
||||
pose_lift_results[
|
||||
idx].pred_instances.keypoint_scores = keypoint_scores
|
||||
if keypoints.ndim == 4:
|
||||
keypoints = np.squeeze(keypoints, axis=1)
|
||||
|
||||
keypoints = keypoints[..., [0, 2, 1]]
|
||||
keypoints[..., 0] = -keypoints[..., 0]
|
||||
keypoints[..., 2] = -keypoints[..., 2]
|
||||
|
||||
# rebase height (z-axis)
|
||||
if not args.disable_rebase_keypoint:
|
||||
keypoints[..., 2] -= np.min(
|
||||
keypoints[..., 2], axis=-1, keepdims=True)
|
||||
|
||||
pose_lift_results[idx].pred_instances.keypoints = keypoints
|
||||
|
||||
pose_lift_results = sorted(
|
||||
pose_lift_results, key=lambda x: x.get('track_id', 1e4))
|
||||
|
||||
pred_3d_data_samples = merge_data_samples(pose_lift_results)
|
||||
det_data_sample = merge_data_samples(pose_est_results)
|
||||
pred_3d_instances = pred_3d_data_samples.get('pred_instances', None)
|
||||
|
||||
if args.num_instances < 0:
|
||||
args.num_instances = len(pose_lift_results)
|
||||
|
||||
# Visualization
|
||||
if visualizer is not None:
|
||||
visualizer.add_datasample(
|
||||
'result',
|
||||
visualize_frame,
|
||||
data_sample=pred_3d_data_samples,
|
||||
det_data_sample=det_data_sample,
|
||||
draw_gt=False,
|
||||
dataset_2d=pose_det_dataset_name,
|
||||
dataset_3d=pose_lift_dataset_name,
|
||||
show=args.show,
|
||||
draw_bbox=True,
|
||||
kpt_thr=args.kpt_thr,
|
||||
num_instances=args.num_instances,
|
||||
wait_time=args.show_interval)
|
||||
|
||||
return pose_est_results, pose_est_results_list, pred_3d_instances, next_id
|
||||
|
||||
|
||||
def main():
|
||||
assert has_mmdet, 'Please install mmdet to run the demo.'
|
||||
|
||||
args = parse_args()
|
||||
|
||||
assert args.show or (args.output_root != '')
|
||||
assert args.input != ''
|
||||
assert args.det_config is not None
|
||||
assert args.det_checkpoint is not None
|
||||
|
||||
detector = init_detector(
|
||||
args.det_config, args.det_checkpoint, device=args.device.lower())
|
||||
detector.cfg = adapt_mmdet_pipeline(detector.cfg)
|
||||
|
||||
pose_estimator = init_model(
|
||||
args.pose_estimator_config,
|
||||
args.pose_estimator_checkpoint,
|
||||
device=args.device.lower())
|
||||
|
||||
assert isinstance(pose_estimator, TopdownPoseEstimator), 'Only "TopDown"' \
|
||||
'model is supported for the 1st stage (2D pose detection)'
|
||||
|
||||
det_kpt_color = pose_estimator.dataset_meta.get('keypoint_colors', None)
|
||||
det_dataset_skeleton = pose_estimator.dataset_meta.get(
|
||||
'skeleton_links', None)
|
||||
det_dataset_link_color = pose_estimator.dataset_meta.get(
|
||||
'skeleton_link_colors', None)
|
||||
|
||||
pose_lifter = init_model(
|
||||
args.pose_lifter_config,
|
||||
args.pose_lifter_checkpoint,
|
||||
device=args.device.lower())
|
||||
|
||||
assert isinstance(pose_lifter, PoseLifter), \
|
||||
'Only "PoseLifter" model is supported for the 2nd stage ' \
|
||||
'(2D-to-3D lifting)'
|
||||
|
||||
pose_lifter.cfg.visualizer.radius = args.radius
|
||||
pose_lifter.cfg.visualizer.line_width = args.thickness
|
||||
pose_lifter.cfg.visualizer.det_kpt_color = det_kpt_color
|
||||
pose_lifter.cfg.visualizer.det_dataset_skeleton = det_dataset_skeleton
|
||||
pose_lifter.cfg.visualizer.det_dataset_link_color = det_dataset_link_color
|
||||
visualizer = VISUALIZERS.build(pose_lifter.cfg.visualizer)
|
||||
|
||||
# the dataset_meta is loaded from the checkpoint
|
||||
visualizer.set_dataset_meta(pose_lifter.dataset_meta)
|
||||
|
||||
if args.input == 'webcam':
|
||||
input_type = 'webcam'
|
||||
else:
|
||||
input_type = mimetypes.guess_type(args.input)[0].split('/')[0]
|
||||
|
||||
if args.output_root == '':
|
||||
save_output = False
|
||||
else:
|
||||
mmengine.mkdir_or_exist(args.output_root)
|
||||
output_file = os.path.join(args.output_root,
|
||||
os.path.basename(args.input))
|
||||
if args.input == 'webcam':
|
||||
output_file += '.mp4'
|
||||
save_output = True
|
||||
|
||||
if args.save_predictions:
|
||||
assert args.output_root != ''
|
||||
args.pred_save_path = f'{args.output_root}/results_' \
|
||||
f'{os.path.splitext(os.path.basename(args.input))[0]}.json'
|
||||
|
||||
if save_output:
|
||||
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
|
||||
|
||||
pose_est_results_list = []
|
||||
pred_instances_list = []
|
||||
if input_type == 'image':
|
||||
frame = mmcv.imread(args.input, channel_order='rgb')
|
||||
_, _, pred_3d_instances, _ = process_one_image(
|
||||
args=args,
|
||||
detector=detector,
|
||||
frame=frame,
|
||||
frame_idx=0,
|
||||
pose_estimator=pose_estimator,
|
||||
pose_est_results_last=[],
|
||||
pose_est_results_list=pose_est_results_list,
|
||||
next_id=0,
|
||||
pose_lifter=pose_lifter,
|
||||
visualize_frame=frame,
|
||||
visualizer=visualizer)
|
||||
|
||||
if args.save_predictions:
|
||||
# save prediction results
|
||||
pred_instances_list = split_instances(pred_3d_instances)
|
||||
|
||||
if save_output:
|
||||
frame_vis = visualizer.get_image()
|
||||
mmcv.imwrite(mmcv.rgb2bgr(frame_vis), output_file)
|
||||
|
||||
elif input_type in ['webcam', 'video']:
|
||||
next_id = 0
|
||||
pose_est_results = []
|
||||
|
||||
if args.input == 'webcam':
|
||||
video = cv2.VideoCapture(0)
|
||||
else:
|
||||
video = cv2.VideoCapture(args.input)
|
||||
|
||||
(major_ver, minor_ver, subminor_ver) = (cv2.__version__).split('.')
|
||||
if int(major_ver) < 3:
|
||||
fps = video.get(cv2.cv.CV_CAP_PROP_FPS)
|
||||
else:
|
||||
fps = video.get(cv2.CAP_PROP_FPS)
|
||||
|
||||
video_writer = None
|
||||
frame_idx = 0
|
||||
|
||||
while video.isOpened():
|
||||
success, frame = video.read()
|
||||
frame_idx += 1
|
||||
|
||||
if not success:
|
||||
break
|
||||
|
||||
pose_est_results_last = pose_est_results
|
||||
|
||||
# First stage: 2D pose detection
|
||||
# make person results for current image
|
||||
(pose_est_results, pose_est_results_list, pred_3d_instances,
|
||||
next_id) = process_one_image(
|
||||
args=args,
|
||||
detector=detector,
|
||||
frame=frame,
|
||||
frame_idx=frame_idx,
|
||||
pose_estimator=pose_estimator,
|
||||
pose_est_results_last=pose_est_results_last,
|
||||
pose_est_results_list=pose_est_results_list,
|
||||
next_id=next_id,
|
||||
pose_lifter=pose_lifter,
|
||||
visualize_frame=mmcv.bgr2rgb(frame),
|
||||
visualizer=visualizer)
|
||||
|
||||
if args.save_predictions:
|
||||
# save prediction results
|
||||
pred_instances_list.append(
|
||||
dict(
|
||||
frame_id=frame_idx,
|
||||
instances=split_instances(pred_3d_instances)))
|
||||
|
||||
if save_output:
|
||||
frame_vis = visualizer.get_image()
|
||||
if video_writer is None:
|
||||
# the size of the image with visualization may vary
|
||||
# depending on the presence of heatmaps
|
||||
video_writer = cv2.VideoWriter(output_file, fourcc, fps,
|
||||
(frame_vis.shape[1],
|
||||
frame_vis.shape[0]))
|
||||
|
||||
video_writer.write(mmcv.rgb2bgr(frame_vis))
|
||||
|
||||
if args.show:
|
||||
# press ESC to exit
|
||||
if cv2.waitKey(5) & 0xFF == 27:
|
||||
break
|
||||
time.sleep(args.show_interval)
|
||||
|
||||
video.release()
|
||||
|
||||
if video_writer:
|
||||
video_writer.release()
|
||||
else:
|
||||
args.save_predictions = False
|
||||
raise ValueError(
|
||||
f'file {os.path.basename(args.input)} has invalid format.')
|
||||
|
||||
if args.save_predictions:
|
||||
with open(args.pred_save_path, 'w') as f:
|
||||
json.dump(
|
||||
dict(
|
||||
meta_info=pose_lifter.dataset_meta,
|
||||
instance_info=pred_instances_list),
|
||||
f,
|
||||
indent='\t')
|
||||
print(f'predictions have been saved at {args.pred_save_path}')
|
||||
|
||||
if save_output:
|
||||
input_type = input_type.replace('webcam', 'video')
|
||||
print_log(
|
||||
f'the output {input_type} has been saved at {output_file}',
|
||||
logger='current',
|
||||
level=logging.INFO)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
135
calculate.py
Normal file
135
calculate.py
Normal file
@ -0,0 +1,135 @@
|
||||
import numpy as np
|
||||
|
||||
|
||||
import numpy as np
|
||||
|
||||
def angle_between(pkt1, pkt2, pkt3):
|
||||
"""
|
||||
Oblicza kąt między trzema punktami w stopniach z zachowaniem znaku.
|
||||
pkt2 jest wierzchołkiem kąta.
|
||||
|
||||
Parameters:
|
||||
pkt1, pkt2, pkt3 : array-like (x, y) lub (x, y, z)
|
||||
|
||||
Returns:
|
||||
Kąt w stopniach (ujemny lub dodatni)
|
||||
"""
|
||||
|
||||
pkt1 = np.array(pkt1[:2].cpu().numpy())
|
||||
pkt2 = np.array(pkt2[:2].cpu().numpy())
|
||||
pkt3 = np.array(pkt3[:2].cpu().numpy())
|
||||
|
||||
# wektory względem pkt2
|
||||
a = pkt1 - pkt2
|
||||
b = pkt3 - pkt2
|
||||
|
||||
# iloczyn skalarny i cosinus kąta
|
||||
dot = np.dot(a, b)
|
||||
norm = np.linalg.norm(a) * np.linalg.norm(b)
|
||||
cos_theta = dot / norm
|
||||
cos_theta = np.clip(cos_theta, -1.0, 1.0)
|
||||
|
||||
# kąt bez znaku
|
||||
angle = np.degrees(np.arccos(cos_theta))
|
||||
|
||||
# znak z iloczynu wektorowego (w 2D to skalar = z-component)
|
||||
cross = a[0]*b[1] - a[1]*b[0]
|
||||
|
||||
if cross < 0:
|
||||
angle = -angle
|
||||
|
||||
return angle
|
||||
|
||||
def compare_poses(f1, f2):
|
||||
# Odległość euklidesowa
|
||||
l2_dist = np.linalg.norm(f1 - f2)
|
||||
|
||||
# Cosine similarity
|
||||
cos_sim = np.dot(f1, f2) / (np.linalg.norm(f1) * np.linalg.norm(f2) + 1e-6)
|
||||
|
||||
return l2_dist, cos_sim
|
||||
|
||||
def compare_poses_boolean(f1, f2):
|
||||
l2, cos_sim = compare_poses(f1, f2)
|
||||
|
||||
return l2 < 0.7 and cos_sim > 0.90
|
||||
|
||||
def center(keypoints):
|
||||
mid_hip = (keypoints[11] + keypoints[12]) / 2 # left_hip=11, right_hip=12
|
||||
keypoints = keypoints - mid_hip
|
||||
|
||||
return keypoints
|
||||
|
||||
def normalize_pose(keypoints):
|
||||
"""
|
||||
keypoints: np.array shape (17, 2) [x,y] dla COCO
|
||||
Zwraca wektor cech odporny na skalę i przesunięcie
|
||||
"""
|
||||
|
||||
# 1. translacja -> środek bioder jako początek układu
|
||||
mid_hip = (keypoints[11] + keypoints[12]) / 2 # left_hip=11, right_hip=12
|
||||
keypoints = keypoints - mid_hip
|
||||
|
||||
# 2. normalizacja skali -> odległość między barkami
|
||||
shoulder_dist = np.linalg.norm(keypoints[5] - keypoints[6]) # left_shoulder=5, right_shoulder=6
|
||||
if shoulder_dist > 0:
|
||||
keypoints = keypoints / shoulder_dist
|
||||
|
||||
# 3. definicja segmentów (przykład: łokieć-ramię, nadgarstek-łokieć)
|
||||
limbs = [
|
||||
(5, 7), # ramię L
|
||||
(7, 9), # przedramię L
|
||||
(6, 8), # ramię P
|
||||
(8, 10), # przedramię P
|
||||
(11, 13), # udo L
|
||||
(13, 15), # goleń L
|
||||
(12, 14), # udo P
|
||||
(14, 16), # goleń P
|
||||
]
|
||||
|
||||
# 4. oblicz kąty
|
||||
angles = []
|
||||
for (a, b), (c, d) in zip(limbs[::2], limbs[1::2]): # np. (ramię, przedramię)
|
||||
v1 = keypoints[b] - keypoints[a]
|
||||
v2 = keypoints[d] - keypoints[c]
|
||||
cos_angle = np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2) + 1e-6)
|
||||
angle = np.arccos(np.clip(cos_angle, -1, 1))
|
||||
angles.append(angle)
|
||||
|
||||
# 5. opcjonalnie: dodać wektory kończyn (znormalizowane)
|
||||
vectors = []
|
||||
for (a, b) in limbs:
|
||||
v = keypoints[b] - keypoints[a]
|
||||
v_norm = v / (np.linalg.norm(v) + 1e-6)
|
||||
vectors.extend(v_norm)
|
||||
|
||||
# finalny wektor cech = kąty + wektory
|
||||
feature_vector = np.concatenate([angles, vectors])
|
||||
|
||||
return feature_vector
|
||||
|
||||
|
||||
def denormalize_pose(feature_vector):
|
||||
"""
|
||||
feature_vector: wynik normalize_pose
|
||||
Zwraca przybliżone współrzędne keypoints (w układzie znormalizowanym)
|
||||
"""
|
||||
# 1. oddziel kąty i wektory
|
||||
angles = feature_vector[:4]
|
||||
vectors_flat = feature_vector[4:]
|
||||
vectors = vectors_flat.reshape(-1, 2)
|
||||
|
||||
# 2. inicjalizacja keypoints
|
||||
keypoints = np.zeros((17, 2))
|
||||
|
||||
# 3. przybliżona rekonstrukcja kończyn
|
||||
limbs = [
|
||||
(5, 7), (7, 9), (6, 8), (8, 10),
|
||||
(11, 13), (13, 15), (12, 14), (14, 16)
|
||||
]
|
||||
|
||||
for (a, b), v in zip(limbs, vectors):
|
||||
keypoints[b] = keypoints[a] + v # przybliżona rekonstrukcja
|
||||
|
||||
# 4. punkt startowy (biodra) = (0,0), skalowanie w oryginale trzeba by przywrócić osobno
|
||||
return keypoints
|
||||
93
filter.py
Normal file
93
filter.py
Normal file
@ -0,0 +1,93 @@
|
||||
from collections import deque
|
||||
|
||||
import numpy as np
|
||||
|
||||
def filter_moves(moves):
|
||||
newMoves = []
|
||||
lastTime = 0
|
||||
|
||||
ema = EMAFilter(0.2)
|
||||
|
||||
for i, move in enumerate(moves):
|
||||
s = move[0] / 1000
|
||||
|
||||
if i != len(moves) - 1:
|
||||
origS = s
|
||||
s = s - lastTime
|
||||
lastTime = origS
|
||||
|
||||
newMoves.append((s, ema.update(move[1])))
|
||||
|
||||
return newMoves
|
||||
|
||||
class MedianFilter:
|
||||
def __init__(self, n_channels=8, window_size=3):
|
||||
self.n = n_channels
|
||||
self.buffers = [deque(maxlen=window_size) for _ in range(n_channels)]
|
||||
|
||||
def update(self, angles_deg):
|
||||
smoothed = []
|
||||
for i, ang in enumerate(angles_deg):
|
||||
self.buffers[i].append(ang)
|
||||
smoothed_ang = np.median(self.buffers[i])
|
||||
smoothed.append(smoothed_ang)
|
||||
return smoothed
|
||||
|
||||
class HybridFilter:
|
||||
def __init__(self, alpha=0.7, n_channels=8, median_window=3):
|
||||
self.alpha = alpha
|
||||
self.n = n_channels
|
||||
self.median_window = median_window
|
||||
|
||||
# Bufory do mediany dla każdego kanału
|
||||
self.buffers = [deque(maxlen=median_window) for _ in range(n_channels)]
|
||||
|
||||
# Stan EMA (cos/sin)
|
||||
self.cos_state = [None] * n_channels
|
||||
self.sin_state = [None] * n_channels
|
||||
|
||||
def update(self, angles_deg):
|
||||
smoothed = []
|
||||
for i, ang in enumerate(angles_deg):
|
||||
# wrzucamy do bufora mediany
|
||||
self.buffers[i].append(ang)
|
||||
med = np.median(self.buffers[i]) # filtr medianowy
|
||||
|
||||
ang_rad = np.deg2rad(med)
|
||||
c, s = np.cos(ang_rad), np.sin(ang_rad)
|
||||
|
||||
if self.cos_state[i] is None:
|
||||
self.cos_state[i] = c
|
||||
self.sin_state[i] = s
|
||||
else:
|
||||
self.cos_state[i] = self.alpha * c + (1 - self.alpha) * self.cos_state[i]
|
||||
self.sin_state[i] = self.alpha * s + (1 - self.alpha) * self.sin_state[i]
|
||||
|
||||
smoothed_ang = np.rad2deg(np.arctan2(self.sin_state[i], self.cos_state[i]))
|
||||
smoothed.append(smoothed_ang)
|
||||
return smoothed
|
||||
|
||||
class EMAFilter:
|
||||
def __init__(self, alpha=0.2, n_channels=8):
|
||||
self.alpha = alpha
|
||||
self.cos_state = [None] * n_channels
|
||||
self.sin_state = [None] * n_channels
|
||||
self.n = n_channels
|
||||
|
||||
def update(self, angles_deg):
|
||||
smoothed = []
|
||||
for i, ang in enumerate(angles_deg):
|
||||
ang_rad = np.deg2rad(ang)
|
||||
|
||||
c, s = np.cos(ang_rad), np.sin(ang_rad)
|
||||
|
||||
if self.cos_state[i] is None:
|
||||
self.cos_state[i] = c
|
||||
self.sin_state[i] = s
|
||||
else:
|
||||
self.cos_state[i] = self.alpha * c + (1 - self.alpha) * self.cos_state[i]
|
||||
self.sin_state[i] = self.alpha * s + (1 - self.alpha) * self.sin_state[i]
|
||||
|
||||
smoothed_ang = np.rad2deg(np.arctan2(self.sin_state[i], self.cos_state[i]))
|
||||
smoothed.append(smoothed_ang)
|
||||
return smoothed
|
||||
BIN
hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth
(Stored with Git LFS)
BIN
hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth
(Stored with Git LFS)
Binary file not shown.
File diff suppressed because one or more lines are too long
204
main.py
Normal file
204
main.py
Normal file
@ -0,0 +1,204 @@
|
||||
import pickle
|
||||
import sys
|
||||
|
||||
import regex as re
|
||||
import numpy as np
|
||||
from ultralytics import YOLO
|
||||
import cv2
|
||||
import time
|
||||
|
||||
from calculate import normalize_pose, compare_poses_boolean
|
||||
from draw import draw_new
|
||||
|
||||
model = YOLO("yolo11x-pose.pt")
|
||||
|
||||
if len(sys.argv) == 1:
|
||||
method = sys.argv[1]
|
||||
else:
|
||||
print("Podaj argument 'cam', albo 'network'.")
|
||||
exit(1)
|
||||
|
||||
cap = cv2.VideoCapture(0)
|
||||
|
||||
if not cap.isOpened():
|
||||
print("Nie można otworzyć kamerki")
|
||||
exit(1)
|
||||
|
||||
last_time = time.time()
|
||||
|
||||
|
||||
startTime = time.time()
|
||||
stage = 0
|
||||
|
||||
pose = normalize_pose(np.array([[ 353.17, 107.28],
|
||||
[ 363.3, 96.435],
|
||||
[ 347.1, 98.647],
|
||||
[ 390.12, 99.096],
|
||||
[ 346.09, 103.63],
|
||||
[ 425.77, 149.95],
|
||||
[ 327.92, 153.12],
|
||||
[ 495.16, 169.82],
|
||||
[ 260.86, 166.3],
|
||||
[ 565.53, 182.68],
|
||||
[ 192.34, 170.58],
|
||||
[ 393.83, 316.99],
|
||||
[ 337.05, 316.41],
|
||||
[ 388.36, 433.37],
|
||||
[ 333.88, 431.89],
|
||||
[ 383.58, 479.16],
|
||||
[ 330.89, 480]]))
|
||||
|
||||
do_pose_shot = False
|
||||
|
||||
def click_event(event, x, y, flags, param):
|
||||
global do_pose_shot
|
||||
|
||||
if event == cv2.EVENT_LBUTTONDOWN: # lewy przycisk myszy
|
||||
do_pose_shot = not do_pose_shot
|
||||
|
||||
currTimeIndex = 0
|
||||
currIndex = None
|
||||
currMove = None
|
||||
currStatus = "Zacznij tanczyc"
|
||||
|
||||
mehCount = 0
|
||||
goodCount = 0
|
||||
failCount = 0
|
||||
failRate = 2
|
||||
|
||||
def wczytaj_dane_z_txt(sciezka):
|
||||
wynik = []
|
||||
with open(sciezka, "r") as f:
|
||||
zawartosc = f.read()
|
||||
|
||||
# Znajdź wszystkie krotki w formacie (float, array([...]))
|
||||
pattern = re.compile(r"\(([^,]+),\s*array\((\[.*?\]),\s*dtype=float32\)\)")
|
||||
matches = pattern.findall(zawartosc)
|
||||
|
||||
for m in matches:
|
||||
liczba = float(m[0])
|
||||
tablica = np.array(eval(m[1]), dtype=np.float32)
|
||||
wynik.append((liczba, tablica))
|
||||
|
||||
return wynik
|
||||
|
||||
moves = []
|
||||
|
||||
with open('moves.pkl', 'rb') as f: # 'rb' = read binary
|
||||
moves = pickle.load(f)
|
||||
|
||||
startValue = moves[0][0]
|
||||
totalCount = len(moves)
|
||||
|
||||
for i, move in enumerate(moves):
|
||||
moves[i] = (move[0] - startValue, move[1], move[2])
|
||||
|
||||
def find_closest(target):
|
||||
global moves
|
||||
return min(moves, key=lambda t: abs(t[0] - target))
|
||||
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
frame = cv2.flip(frame, 1)
|
||||
|
||||
results = model(frame, verbose=False)
|
||||
|
||||
current_time = time.time()
|
||||
delta = current_time - last_time
|
||||
last_time = current_time
|
||||
|
||||
fps = 1 / delta if delta > 0 else float('inf')
|
||||
# print(f"\rDelta: {delta:.4f}s, FPS: {fps:.2f}", end="")
|
||||
|
||||
for result in results:
|
||||
kpts = result.keypoints.data[0] if len(result.keypoints.data) else None
|
||||
|
||||
if kpts is None:
|
||||
continue
|
||||
|
||||
img = frame
|
||||
|
||||
normalized = normalize_pose(result.keypoints.xy.cpu().numpy()[0])
|
||||
cv2.imshow('you', draw_new(result.keypoints.xy.cpu()[0]))
|
||||
|
||||
if currTimeIndex != 0 and moves.index(find_closest(time.time() - currTimeIndex)) == len(moves) - 1:
|
||||
mehCount = totalCount - failCount - goodCount
|
||||
|
||||
print(f"PODSUMOWANIE: FAIL {failCount} MEH: {mehCount} PERFECT: {goodCount} PERCENTAGE: {(goodCount + (0.95 * mehCount)) / totalCount * 100}%")
|
||||
exit(1)
|
||||
|
||||
if currMove is None:
|
||||
if compare_poses_boolean(moves[0][1], normalized):
|
||||
currIndex = 1
|
||||
currTimeIndex = time.time()
|
||||
deltaTime = time.time()
|
||||
currStatus = f"Zaczoles tanczyc {currIndex}"
|
||||
currMove = moves[0]
|
||||
|
||||
# thread = Thread(target=print_animation, args=(moves, False))
|
||||
# thread.start()
|
||||
else:
|
||||
changed = False
|
||||
|
||||
closest = find_closest(time.time() - currTimeIndex)
|
||||
cv2.imshow('Dots', draw_new(closest[2]))
|
||||
|
||||
if abs((time.time() - currTimeIndex) - moves[currIndex][0]) > failRate:
|
||||
currStatus = f"FAIL!"
|
||||
failCount += 1
|
||||
|
||||
if compare_poses_boolean(closest[1], normalized):
|
||||
# delays += (time.time() - deltaTime - moves[0][0]) * 1000
|
||||
# delaysCount += 1
|
||||
|
||||
currStatus = f"SUPER! {currIndex} Zostalo {len(moves)} Delay {(time.time() - currTimeIndex - closest[0]) / 1000}ms"
|
||||
deltaTime = time.time()
|
||||
|
||||
currIndex = moves.index(closest) + 1
|
||||
goodCount += 1
|
||||
changed = True
|
||||
|
||||
if not changed and compare_poses_boolean(moves[currIndex][1], normalized):
|
||||
# delays += (time.time() - deltaTime - moves[0][0]) * 1000
|
||||
# delaysCount += 1
|
||||
|
||||
currStatus = f"SUPER! {currIndex} Zostalo {len(moves)} Delay {(time.time() - currTimeIndex - closest[0]) / 1000}ms"
|
||||
deltaTime = time.time()
|
||||
|
||||
changed = True
|
||||
|
||||
currIndex += 1
|
||||
goodCount += 1
|
||||
|
||||
# if do_pose_shot:
|
||||
# moves.append((time.time() - startTime, normalize_pose(result.keypoints.xy.cpu().numpy()[0]), result.keypoints.xy.cpu()[0]))
|
||||
# elif len(moves) != 0:
|
||||
# with open('moves.pkl', 'wb') as f: # 'wb' = write binary
|
||||
# pickle.dump(moves, f)
|
||||
#
|
||||
# exit(1)
|
||||
|
||||
cv2.putText(
|
||||
img, # obraz
|
||||
currStatus, # tekst
|
||||
(50, 100), # pozycja (x, y) lewego dolnego rogu tekstu
|
||||
cv2.FONT_HERSHEY_SIMPLEX, # czcionka
|
||||
1, # rozmiar (skalowanie)
|
||||
(0, 0, 255), # kolor (BGR) - tutaj czerwony
|
||||
2, # grubość linii
|
||||
cv2.LINE_AA # typ antyaliasingu
|
||||
)
|
||||
|
||||
cv2.imshow('Klatka z kamerki', img)
|
||||
cv2.setMouseCallback('Klatka z kamerki', click_event)
|
||||
cv2.waitKey(1) # Czekaj na naciśnięcie klawisza
|
||||
|
||||
|
||||
# Access the results
|
||||
for result in results:
|
||||
annotated_frame = result.plot() # zwraca obraz z naniesionymi keypoints
|
||||
|
||||
# Wyświetlenie obrazu przy użyciu OpenCV
|
||||
cv2.imshow("Pose", annotated_frame)
|
||||
cv2.waitKey(0)
|
||||
cv2.destroyAllWindows()
|
||||
26
ploting.py
Normal file
26
ploting.py
Normal file
@ -0,0 +1,26 @@
|
||||
import matplotlib.pyplot as plt
|
||||
import queue
|
||||
|
||||
data_queue = queue.Queue()
|
||||
|
||||
x_data, y_data = [], []
|
||||
|
||||
fig, ax = plt.subplots()
|
||||
line, = ax.plot([], [], 'r-')
|
||||
|
||||
def init():
|
||||
ax.set_xlim(0, 100)
|
||||
ax.set_ylim(0, 10)
|
||||
return line,
|
||||
|
||||
def update(frame):
|
||||
# sprawdzamy, czy są nowe dane w kolejce
|
||||
while not data_queue.empty():
|
||||
value = data_queue.get()
|
||||
x_data.append(len(x_data))
|
||||
y_data.append(value)
|
||||
if len(x_data) > 100:
|
||||
x_data.pop(0)
|
||||
y_data.pop(0)
|
||||
line.set_data(x_data, y_data)
|
||||
return line,
|
||||
48
receive_images.py
Normal file
48
receive_images.py
Normal file
@ -0,0 +1,48 @@
|
||||
import socket
|
||||
import cv2
|
||||
import numpy as np
|
||||
import struct
|
||||
|
||||
HOST = "0.0.0.0" # nasłuchuj na wszystkich interfejsach
|
||||
PORT = 9999
|
||||
|
||||
server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
server_socket.bind((HOST, PORT))
|
||||
server_socket.listen(1)
|
||||
|
||||
print("Serwer nasłuchuje na port", PORT)
|
||||
conn, addr = server_socket.accept()
|
||||
print("Połączono z:", addr)
|
||||
|
||||
data = b""
|
||||
payload_size = struct.calcsize("Q") # 8 bajtów na długość ramki
|
||||
|
||||
while True:
|
||||
while len(data) < payload_size:
|
||||
packet = conn.recv(4096)
|
||||
if not packet:
|
||||
break
|
||||
data += packet
|
||||
if not data:
|
||||
break
|
||||
|
||||
packed_msg_size = data[:payload_size]
|
||||
data = data[payload_size:]
|
||||
msg_size = struct.unpack("Q", packed_msg_size)[0]
|
||||
|
||||
while len(data) < msg_size:
|
||||
data += conn.recv(4096)
|
||||
|
||||
frame_data = data[:msg_size]
|
||||
data = data[msg_size:]
|
||||
|
||||
frame = np.frombuffer(frame_data, dtype=np.uint8)
|
||||
frame = cv2.imdecode(frame, cv2.IMREAD_COLOR)
|
||||
|
||||
cv2.imshow("Odebrany obraz", frame)
|
||||
if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
break
|
||||
|
||||
conn.close()
|
||||
server_socket.close()
|
||||
cv2.destroyAllWindows()
|
||||
62
receiver.py
Normal file
62
receiver.py
Normal file
@ -0,0 +1,62 @@
|
||||
import socket
|
||||
import struct
|
||||
import numpy as np
|
||||
import cv2
|
||||
import time
|
||||
|
||||
HOST = '0.0.0.0'
|
||||
PORT = 9999
|
||||
|
||||
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
sock.bind((HOST, PORT))
|
||||
sock.listen(1)
|
||||
conn, addr = sock.accept()
|
||||
print(f"Connected by {addr}")
|
||||
|
||||
total_bytes_received = 0
|
||||
start_time = time.time()
|
||||
|
||||
|
||||
def recvall(sock, n):
|
||||
data = b''
|
||||
while len(data) < n:
|
||||
packet = sock.recv(n - len(data))
|
||||
if not packet:
|
||||
return None
|
||||
data += packet
|
||||
return data
|
||||
|
||||
|
||||
try:
|
||||
while True:
|
||||
# Odbiór długości
|
||||
packed_len = recvall(conn, 4)
|
||||
if not packed_len:
|
||||
break
|
||||
length = struct.unpack('!I', packed_len)[0]
|
||||
|
||||
# Odbiór danych
|
||||
data = recvall(conn, length)
|
||||
if not data:
|
||||
break
|
||||
|
||||
total_bytes_received += length
|
||||
|
||||
# Dekodowanie JPEG
|
||||
img_array = np.frombuffer(data, dtype=np.uint8)
|
||||
frame = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
|
||||
|
||||
cv2.imshow("Stream", frame)
|
||||
if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
break
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
if elapsed >= 1.0:
|
||||
print(f"Download speed: {total_bytes_received * 8 / 1e6:.2f} Mbps")
|
||||
total_bytes_received = 0
|
||||
start_time = time.time()
|
||||
|
||||
finally:
|
||||
conn.close()
|
||||
sock.close()
|
||||
cv2.destroyAllWindows()
|
||||
BIN
rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth
(Stored with Git LFS)
BIN
rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth
(Stored with Git LFS)
Binary file not shown.
BIN
rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth
(Stored with Git LFS)
BIN
rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth
(Stored with Git LFS)
Binary file not shown.
51
sender.py
Normal file
51
sender.py
Normal file
@ -0,0 +1,51 @@
|
||||
import cv2
|
||||
import socket
|
||||
import zstandard as zstd
|
||||
import struct
|
||||
import time
|
||||
|
||||
from utils import resize_with_padding
|
||||
|
||||
SERVER_IP = '127.0.0.1'
|
||||
SERVER_PORT = 9999
|
||||
|
||||
# Socket
|
||||
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
sock.connect((SERVER_IP, SERVER_PORT))
|
||||
|
||||
# Kompresor Zstd
|
||||
compressor = zstd.ZstdCompressor(level=10)
|
||||
|
||||
cap = cv2.VideoCapture(0) # kamerka
|
||||
|
||||
total_bytes_sent = 0
|
||||
start_time = time.time()
|
||||
|
||||
JPEG_QUALITY = 25 # 0-100, im mniejsza, tym większa kompresja
|
||||
|
||||
try:
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
break
|
||||
|
||||
frame = resize_with_padding(frame)
|
||||
|
||||
# Konwersja do JPEG
|
||||
_, buffer = cv2.imencode('.jpg', frame, [cv2.IMWRITE_JPEG_QUALITY, JPEG_QUALITY])
|
||||
data = buffer.tobytes()
|
||||
|
||||
# Wysyłanie długości + danych
|
||||
sock.sendall(struct.pack('!I', len(data)))
|
||||
sock.sendall(data)
|
||||
|
||||
total_bytes_sent += len(data)
|
||||
elapsed = time.time() - start_time
|
||||
if elapsed >= 1.0:
|
||||
print(f"Upload speed: {total_bytes_sent * 8 / 1e6:.2f} Mbps") # w megabitach
|
||||
total_bytes_sent = 0
|
||||
start_time = time.time()
|
||||
|
||||
finally:
|
||||
cap.release()
|
||||
sock.close()
|
||||
34
utils.py
Normal file
34
utils.py
Normal file
@ -0,0 +1,34 @@
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
def recvall(sock, n):
|
||||
data = b''
|
||||
while len(data) < n:
|
||||
packet = sock.recv(n - len(data))
|
||||
if not packet:
|
||||
return None
|
||||
data += packet
|
||||
return data
|
||||
|
||||
def resize_with_padding(image, target_size=(640, 640)):
|
||||
h, w = image.shape[:2]
|
||||
target_w, target_h = target_size
|
||||
|
||||
# Oblicz współczynnik skalowania, zachowując proporcje
|
||||
scale = min(target_w / w, target_h / h)
|
||||
new_w, new_h = int(w * scale), int(h * scale)
|
||||
|
||||
# Resize obrazu
|
||||
resized_image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_AREA)
|
||||
|
||||
# Stwórz tło (czarne) o wymiarach docelowych
|
||||
output_image = np.zeros((target_h, target_w, 3), dtype=np.uint8)
|
||||
|
||||
# Oblicz offsety do wyśrodkowania obrazu
|
||||
x_offset = (target_w - new_w) // 2
|
||||
y_offset = (target_h - new_h) // 2
|
||||
|
||||
# Wklej resized image na tło
|
||||
output_image[y_offset:y_offset+new_h, x_offset:x_offset+new_w] = resized_image
|
||||
|
||||
return output_image
|
||||
65
video_methods.py
Normal file
65
video_methods.py
Normal file
@ -0,0 +1,65 @@
|
||||
import socket
|
||||
import struct
|
||||
import time
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from utils import recvall
|
||||
|
||||
methods = ["cam", "net"]
|
||||
|
||||
HOST = '0.0.0.0'
|
||||
PORT = 9999
|
||||
|
||||
class Method:
|
||||
def __init__(self, method_type):
|
||||
self.method_type = method_type
|
||||
|
||||
if method_type is "cam":
|
||||
self.cap = cv2.VideoCapture(0)
|
||||
|
||||
if not self.cap.isOpened():
|
||||
print("Nie można otworzyć kamerki")
|
||||
exit(1)
|
||||
else:
|
||||
self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
self.sock.bind((HOST, PORT))
|
||||
self.sock.listen(1)
|
||||
print(f"Oczekuje podłączenia na: {HOST}:{PORT}")
|
||||
self.conn, addr = self.sock.accept()
|
||||
print(f"Podłączono przez {addr}")
|
||||
|
||||
self.total_bytes_received = 0
|
||||
self.start_time = time.time()
|
||||
|
||||
def receive_frame(self):
|
||||
if self.method_type is "cam":
|
||||
_, frame = self.cap.read()
|
||||
|
||||
if not _:
|
||||
exit(1)
|
||||
else:
|
||||
packed_len = recvall(self.conn, 4)
|
||||
if not packed_len:
|
||||
exit(1)
|
||||
|
||||
length = struct.unpack('!I', packed_len)[0]
|
||||
|
||||
data = recvall(self.conn, length)
|
||||
if not data:
|
||||
exit(1)
|
||||
|
||||
self.total_bytes_received += length
|
||||
|
||||
img_array = np.frombuffer(data, dtype=np.uint8)
|
||||
frame = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
|
||||
|
||||
return frame
|
||||
|
||||
|
||||
def initialize_method(method_type):
|
||||
if not method_type in methods:
|
||||
return None
|
||||
|
||||
return Method(method_type)
|
||||
BIN
videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth
(Stored with Git LFS)
BIN
videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth
(Stored with Git LFS)
Binary file not shown.
Reference in New Issue
Block a user