Target detection and tracking represent two fundamental steps in automatic video-based surveillance systems where the goal is to provide intelligent recognition capabilities by analyzing target behavior. Junxian Wang and colleagues at the University of Nevada (Reno, NV, USA) and Ford Motor Company (Dearborn, MI, USA) have developed a framework for video-based surveillance where target detection is integrated with tracking to improve detection results.
In contrast to methods that apply target detection and tracking sequentially and independently from each other, they feed the results of tracking back to the detection stage to adaptively optimize the detection threshold and improve system robustness. First, the initial target locations are extracted using background subtraction. To model the background, they employ support vector regression (SVR), which is updated over time using an on-line learning scheme. Target detection is performed by thresholding the outputs of the SVR model. Tracking uses shape projection histograms to iteratively localize the targets and improve the confidence level of detection.
The researchers have validated their approach in two different scenarios, one detecting vehicles at a traffic intersection using visible video and the other detecting pedestrians at a university campus walkway using thermal video.
SOURCE: IngentaConnect
Posted by Vision Systems Design