This paper describes a robust method for recognizing vehicle classes. In our previous work, we have developed a vehicle recognition system based on local-feature configuration, which is a generalization of the eigen-window method. This system could recognize one vehicle class very accurately, but there have been limitations in recognizing several classes, when they are quite similar to each other. In this paper, we describe the improvements of our recognition system to distinguish four classes, namely sedan, wagon, mini-van and hatchback. The system requires training images of all target vehicle classes. These training images are easily created using a 3-dimentional computer graphic (3D-CG) tool. Using CG training images dispenses with much of the trouble of collecting real training images, and causes no effect on accuracy. Outdoor experimental results have shown that this recognition system can classify vehicles in real images with an accuracy of more than 80%.
[1]
Katsushi Ikeuchi,et al.
VEHICLE RECOGNITION WITH LOCAL-FEATURE BASED ALGORITHM USING PARALLEL VISION BOARD
,
2001
.
[2]
Hiroshi Murase,et al.
Visual learning and recognition of 3-d objects from appearance
,
2005,
International Journal of Computer Vision.
[3]
Katsushi Ikeuchi,et al.
Recognizing vehicles in infrared images using IMAP parallel vision board
,
2001,
IEEE Trans. Intell. Transp. Syst..
[4]
John Krumm.
Object detection with vector quantized binary features
,
1997,
Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
[5]
Katsushi Ikeuchi,et al.
VEHICLE RECOGNITION WITH LOCAL-FEATURE BASED ALGORITHM USING CG MODELS
,
2002
.