3D Tree-Structured Object Tracking for Autonomous Ground Vehicles

Safe and effective vision analysis is a key capability for autonomous ground vehicle (AGV) guidance systems. The complexity of natural settings requires the use of a robust image understanding technique. The proposed novel 3D tree-structured object tracking approach is implemented by tracking 2D objects in successive video frames using a wavelet-domain tree structure. It is robust and reliable due to its powerful data structure and also adaptable for moving and stationary object tracking as well as the tracking problem when the vehicle itself is in motion. This approach consists of wavelet decomposition, spatial object detection and temporal object tracking. The results show this approach can produce precise detection and tracking results.