1 / 19

Real-Time Human Pose Recognition in Parts from Single Depth Images

Real-Time Human Pose Recognition in Parts from Single Depth Images . Speaker DengLei At I-VisionGroup. Outline. Introduction Data Algorithm Experiments. Introduction —Human Body Tracking. Apps Game, HCI, Security, telepresence , health-care etc. Depth Camera Kinect

kory
Télécharger la présentation

Real-Time Human Pose Recognition in Parts from Single Depth Images

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Real-Time Human Pose Recognition in Parts from Single Depth Images Speaker DengLei At I-VisionGroup

  2. Outline • Introduction • Data • Algorithm • Experiments

  3. Introduction—Human Body Tracking • Apps • Game, HCI, Security, telepresence, health-care etc. • Depth Camera • Kinect • full range shapes, sizes and motions • Existing Sys • Fast tracking but slow re-initialize • Our Sys • Per-frame initialization • For temporal, kinematic coherence tracking • For initialization and recovering from failure

  4. Show • Final Video Show

  5. General Description • Goals • Fast • Robust • Steps: • Single depth image =>dense probabilistic body part labeling near joint • Reprojecting, Generating confidence-weighted 3D joint • Strategy • Per-pixel classification, Independent Evaluation • Synthetic depth images • Deep randomized decision forest classifier with 10^5 samples • Simple 3D invariance feature distance, GPU • Mean shift for 3D joint proposals

  6. Testing Environment • Xbox 360 GPU • 5ms per frame • One order faster than existing • Evaluate on real and synthetic samples

  7. Contributions • Main Contrib. • Treat pose estimation as object recognition with BODY PARTS REPRESENTATION near joint • Low computational cost and high accuracy • Insights • Synthetic data is good proxy for real • Scaling up with synthetic data is important

  8. Outline • Introduction • Data • Algorithm • Experiments

  9. Data Description • Lack of training data • Computer graphics hampered by color, texture variability caused by clothing, hair, skin. • Limitation of mocap • Depth imaging • Kinect depth camera: 640x480_30, err: 10^-2m • Low light • color texture invariant • resolving silhouette ambiguities in pose • Simplify background substraction • Synthesize realistic depth images of people and build large dataset cheaply

  10. Motion Capture data • Capture real data • 500 k • Not record • Rotation about vertical axis • Mirroring left-right • Scene position and camera pose • Shapes and size • Furthest neighbor • Reduce redundant • Finally • 100k subset, distance < 5cm

  11. Generating synthetic data • Randomize rendering pipeline • Goal: realism and variety • Cg + random parameters • 15 base body meshes spanning shapes and sizes • Camera pose& noise, clothing & hair style etc • Compare

  12. Outline • Introduction • Data • Algorithm • Experiments

  13. Body Part Inference • Labeling • Key contribution: body part representation • Color-coded with joints and gaps • 31 body parts, small: accurate numerous: waste classifier • Adjust to application • Features • Simple • 5 arithmetic • 3 image reading

  14. Random Forest • Classification • Training • On different set of synthesized images, 2000 pixels on each. • Random set of • Left and Right • Largest Gain • Terminal Cond • Large gain, Small depth • Recursing for left and right • 3 trees, depth 20, 10^6 images, 1 day on 1000 core cluster

  15. Joint proposals • Mean shift with Gaussian kernel • Discard outlying • Smooth • Threshold • Mean shift start from c • Parameter desicion • Grid search on 5000 images

  16. Outline • Introduction • Data • Algorithm • Experiments

  17. Experiments • Paras • 3 trees, 20 deep, 300k images per tree, 2000 pixels per image • 2000 candidate 50 candidateper feature

  18. Thanks

More Related