Maintaining the identity of multiple vehicles as they travel through a video network

Large vision infrastructures have recently been installed, or are under construction in many major metropolitan areas. These networks of cameras offer enormous volumes of data from large areas. However, most work in ITS computer vision is constricted to the use of either single cameras, or small numbers of cameras. There is an enormous amount of information available from the fusion of data from multiple cameras that is not available from any single sensor. This paper presents an algorithm that provides an example of such data fusion: maintaining the identity of a vehicle, or groups of vehicles as they pass through multiple cameras sites. The algorithm uses a combination of color features and the spatial organization of vehicles within platoons to minimize false positives. The algorithm could be used in an application to track individual cars as they travel long distances through a traffic system, allowing the measurement of point-to-point traffic parameters such as travel time