Vehicle Make and Model Recognition with Unfixed Views

Vision-based vehicle make and model recognition is a hot topic in the domain of intelligent transportation systems. But it is difficult to recognize the exact make and model of a vehicle due to the influence of some factors, for example, the view variations. In this paper, we present a new method for vehicle make and model recognition with variant views. We take Gabor wavelet coefficients as our initial ones considering their robustness to cope with the view variations. Then, ULLELDA algorithm is employed for feature extraction. An ensemble classifier is proposed at last based on ensemble learning. Experiments show that our method exhibits a higher recognition rate for vehicles with variant views.