Sample Output Video

Usage

指定输入视频(input_video)   --viz-video
指定输入视频(the keypoints of input_video)  --input-npz
指定输出视频名称(the name of output video) --viz-output
指定输出的帧数(the frame number of output video)  --viz-limit

handle video by hrnet

python tools/hrnet_video.py --viz-output output.mp4 --viz-video /path/to/video.mp4

handle video by alphapose

python tools/alphapose_video.py --viz-output output.mp4 --viz-video /path/to/video.mp4

handle video with every frame keypoints

python tools/wild_video.py --viz-output output.mp4 --viz-video /path/to/video.mp4 --input-npz /path/to/input_name.npz

Model download

Alphapose

• Download yolov3-spp.weights from (Google Drive | Baidu pan), place to ./joints_detectors/Alphapose/models/yolo

• Download duc_se.pth from (Google Drive | Baidu pan), place to ./joints_detectors/Alphapose/models/sppe

HR-Net

• Download pose_hrnet* from Google Drive, place to ./joints_detectors/hrnet/models/pytorch/pose_coco/

• Download yolov3.weights from here, place to ./joints_detectors/hrnet/lib/detector/yolo

3D Joint Detector

• Download pretrained_h36m_detectron_coco.bin from here, place it into ./checkpoint folder

paper traslation 论文翻译

https://github.com/lxy5513/videopose/blob/master/doc/translate.md