Multiple Vehicle Segmentation and Tracking in Complex Environments

Xuefeng Song


Our goal is to detect and to track multiple moving vehicles observed from static surveillance cameras, which are usually placed on poles or buildings. Methods of background subtraction are widely used in this kind of conditions. But to extract vehicle information from motion foreground, common difficulties (like noise foreground, shadow, scene occlusion, blob merge and blob split) have to be solved. By using vehicle shape models, in addition to camera calibration and ground plane knowledge, the proposed methods can detect, track and classify moving vehicles in presence of all these difficulties. Two methods are proposed in this thesis to deal with related problems. The first method uses dynamic background model to extract the motion foreground. The models of camera and vehicle are used to reduce the foreground noise. Spatial and temporal constraints are applied to handle blob split, and object color appearance is used to track each vehicle when multiple vehicles are merged together. The evaluation on a large dataset by a third party shows that the method works robustly under many conditions. The second method focuses on the challenging tracking situation when vehicle inter-occlusion is prevalent. In this case, each foreground blob could contain multiple vehicles. Simple one-to-one correspondence between the foreground blobs and vehicles doesn't hold any more. How to segment the merged vehicles is a difficult problem. The proposed method works in the framework of Markov chain Monte Carlo (MCMC). By sampling in the multi-vehicle configuration space, the method searches for the set of vehicle parameters, which best explains the foreground. Several bottom-up detections are utilized with top-down analysis to guide the sampling working in an effective way.

Maintained by Qian Yu