Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World
This addresses the problem of tracking people in cluttered scenes for surveillance, though it is incremental as it builds on existing detection and tracking methods.
The paper tackles multi-people tracking with occlusions by proposing a deep network that jointly detects body parts and associates them over time, explicitly handling occluded joints through hallucination. It achieves good generalization on real benchmarks when trained on a large synthetic dataset of 500,000 frames and 10 million poses.
Multi-People Tracking in an open-world setting requires a special effort in precise detection. Moreover, temporal continuity in the detection phase gains more importance when scene cluttering introduces the challenging problems of occluded targets. For the purpose, we propose a deep network architecture that jointly extracts people body parts and associates them across short temporal spans. Our model explicitly deals with occluded body parts, by hallucinating plausible solutions of not visible joints. We propose a new end-to-end architecture composed by four branches (visible heatmaps, occluded heatmaps, part affinity fields and temporal affinity fields) fed by a time linker feature extractor. To overcome the lack of surveillance data with tracking, body part and occlusion annotations we created the vastest Computer Graphics dataset for people tracking in urban scenarios by exploiting a photorealistic videogame. It is up to now the vastest dataset (about 500.000 frames, almost 10 million body poses) of human body parts for people tracking in urban scenarios. Our architecture trained on virtual data exhibits good generalization capabilities also on public real tracking benchmarks, when image resolution and sharpness are high enough, producing reliable tracklets useful for further batch data association or re-id modules.