This paper designs and implements a vehicle automatic classification system based on video images. Starting from the composition of the system, the implementation methods of each part are elaborated in detail. The system uses motion edge detection, image binarization, closure algorithm and other methods to preprocess the image, then extracts features by Fourier series expansion of the vehicle contour, and finally automatically classifies the vehicle by combining a direct classifier based on area features and a minimum distance classifier based on Fourier descriptors. Experiments show that the method in this paper is simple and effective, and can achieve a high classification accuracy.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore