A vision based monitoring system for street video image

This paper describes a vision based monitoring system which classifies targets (vehicles and humans) based on shape appearance and estimates their colors from images of color video cameras set up toward a street. The categories of targets were classified into {human, sedan, van, truck, mule (golf cart for workers), and others}, and their colors were classified into the groups of {red-orange-yellow, green, blue-light blue, white-silver-gray, dark blue-dark gray-black, and dark red-dark orange}. The system tracks the target, independently conducts category classification and color estimation, extracts the result with the largest probability throughout the tracking sequence from each result, and provides the data as the final decision. For classification, we cooperatively used a stochastic linear discrimination method (linear discriminant analysis: LDA) and nonlinear decision rule (K-Nearest Neighbor rule: K-NN).