Multiple Vehicle Segmentation and Tracking in Complex Environments
Xuefeng Song
Abstract
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.