SLIDE 1
LightTrack: Online Multi-Person Pose Tracking
6/1/20 1:54 PM 2
LightTrack: A Generic Framework for Online Top-Down Human Pose - - PowerPoint PPT Presentation
LightTrack: A Generic Framework for Online Top-Down Human Pose - - PowerPoint PPT Presentation
LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking Authors: Guanghan Ning, Heng Huang LightTrack: Online Multi-Person Pose Tracking q Overview of Proposed Framework 2 6/1/20 1:54 PM Proposed Framework q Single-Person Pose
SLIDE 2
SLIDE 3
Proposed Framework
6/1/20 2:09 PM 3
q Single-Person Pose Tracking
Incorporate object tracking with single-person pose tracking. A recursive approach:
- Use human keypoints as explicit visual cues for bounding box tracking.
- Estimate keypoints for future frames with tracked bounding boxes.
- Detections only performed at Key-frames.
SLIDE 4
Proposed Framework
6/1/20 2:17 PM 4
q Re-ID with Pose Matching
Pose Matching Network: Siamese Graph Convolutional Network (SGCN)
SLIDE 5
Proposed Framework
6/1/20 2:22 PM 5
q Re-ID with Pose Matching
- Spatial Consistency is helpful as well.
- In some situations, poses are indeed similar.
SLIDE 6
Performance
6/1/20 1:54 PM 6
q Qualitative Results
SLIDE 7
Performance
6/1/20 2:32 PM 7
q Qualitative Results
Unseen Test Video from PoseTrack Dataset Unseen Surveillance Video
SLIDE 8
Performance
6/1/20 2:32 PM 8
q Quantitative Results
SLIDE 9
Performance
6/1/20 2:32 PM 9