OpenPose command line

OpenPose Output Deal With 关键参数

详情见：./build/examples/openpose/openpose.bin --help

• --face: Enable face key check.
• --hand: Enable manual key detection
• --video input.mp4: 读取视频
• --camera 3: 读取摄像头3
• --image_dir path_to_images/: Run on a folder with images
• --ip_camera [http://iris.not.iac.es/axis-cgi/mjpg/video.cgi?resolution=320x240?x.mjpeg](http://iris.not.iac.es/axis-cgi/mjpg/video.cgi?resolution=320x240?x.mjpeg): run in a streamIP摄像头.See example public IP 摄像机.
• --write_video path.avi: Save the processed image as a video
• --write_images folder_path: Save the processed images to a folder
• --write_keypoint path/: 输出JSON、XML或YML文件,and place the data in the folder
• --process_real_time: 对于视频,It can skip frames to display in real time
• --disable_blending: 如果启用,It will render the result(Keypoint skeleton or heatmap)on a black background,The original image is not displayed.
  • 相关的: part_to_show, alpha_pose, and alpha_pose.
• --part_to_show: Visualize prediction channels
• --display 0: The display window is not open.For the server and /or slightly acceleratedOpenPose很有
• --num_gpu 2 --num_gpu_start 1: through the required equipmentidat this numbergpu上并行化.默认情况下,It uses all availablegpu.
• --model_pose MPI: 模型的使用,Influence digital key points、速度和精度
• --logging_level 3: Log message threshold,范围[0,255]:0will output any messages,255No message will be output.The scope of the current message is [1-4],Low priority messages are1,Important news is4.

No visual presentation、直接输出 JSON

# Only body
./build/examples/openpose/openpose.bin --video  /media/video.avi --write_json output/ --display 0 --render_pose 0
# Body + face + hands
./build/examples/openpose/openpose.bin --video examples/media/video.avi --write_json output/ --display 0 --render_pose 0 --face --hand

JSON输出+The rendered image is saved

./build/examples/openpose/openpose.bin --video examples/media/video.avi --write_video output/result.avi --write_json output/

手部

# Fast method for speed
./build/examples/openpose/openpose.bin --hand
# Best results found with 6 scales
./build/examples/openpose/openpose.bin --hand --hand_scale_number 6 --hand_scale_range 0.4
# Adding tracking to Webcam (if FPS per GPU > 10 FPS) and Video
./build/examples/openpose/openpose.bin --video examples/media/video.avi --hand --hand_detector 3
# Multi-scale + tracking is also possible
./build/examples/openpose/openpose.bin --video examples/media/video.avi --hand --hand_scale_number 6 --hand_scale_range 0.4 --hand_detector 3

Faces and hands are rendered without poses

# CPU rendering (faster)
./build/examples/openpose/openpose.bin --render_pose 0 --face --face_render 1 --hand --hand_render 1
# GPU rendering
./build/examples/openpose/openpose.bin --render_pose 0 --face --face_render 2 --hand --hand_render 2

调试信息

# Basic information
./build/examples/openpose/openpose.bin --logging_level 3
# Showing all messages
./build/examples/openpose/openpose.bin --logging_level 0

选择一些GPU（The example below runs the demo video.avi,并行在 2 个GPU上, GPU 1和2(Note that it will skipGPU 0)）

./build/examples/openpose/openpose.bin --video examples/media/video.avi --num_gpu 2 --num_gpu_start 1

Heat Maps Storing

./build/examples/openpose/openpose.bin --video examples/media/video.avi --heatmaps_add_parts --heatmaps_add_bkg --heatmaps_add_PAFs --write_heatmaps output_heatmaps_folder/

对 OutPut 文件进行处理

poseModel = op.PoseModel.BODY_25
print(op.getPoseBodyPartMapping(poseModel))
print(op.getPoseNumberBodyParts(poseModel))
print(op.getPosePartPairs(poseModel))
print(op.getPoseMapIndex(poseModel))

./build/examples/openpose/openpose.bin --image_dir ./media/ --write_images ./out_put/ --num_gpu 0 --num_gpu_start 0 --display 0 --face --hand

./build/examples/openpose/openpose.bin --image_dir ./media/ --write_images ./out_put/  --face --hand --display 0