Title :
Dynamic Bayesian Networks for Vehicle Classification in Video
Author :
Kafai, Mehran ; Bhanu, Bir
Author_Institution :
Comput. Sci. Dept., Univ. of California at Riverside, Riverside, CA, USA
Abstract :
Vehicle classification has evolved into a significant subject of study due to its importance in autonomous navigation, traffic analysis, surveillance and security systems, and transportation management. While numerous approaches have been introduced for this purpose, no specific study has been conducted to provide a robust and complete video-based vehicle classification system based on the rear-side view where the camera´s field of view is directly behind the vehicle. In this paper, we present a stochastic multiclass vehicle classification system which classifies a vehicle (given its direct rear-side view) into one of four classes: sedan, pickup truck, SUV/minivan, and unknown. A feature set of tail light and vehicle dimensions is extracted which feeds a feature selection algorithm to define a low-dimensional feature vector. The feature vector is then processed by a hybrid dynamic Bayesian network to classify each vehicle. Results are shown on a database of 169 videos for four classes.
Keywords :
belief networks; traffic engineering computing; video signal processing; autonomous navigation; dynamic Bayesian networks; feature vector; hybrid dynamic Bayesian network; security systems; stochastic multiclass vehicle classification system; surveillance; traffic analysis; transportation management; video-based vehicle classification system; Bayesian methods; Feature extraction; Image color analysis; Image edge detection; Licenses; Shape; Vehicles; Classification; hybrid dynamic Bayesian network (HDBN);
Journal_Title :
Industrial Informatics, IEEE Transactions on
DOI :
10.1109/TII.2011.2173203