Method for re-identifying vehicles in sequence images of monitoring video

Abstract

The invention discloses a method for re-identifying vehicles in sequence images of a mentoring video. The method comprises the following steps of performing image feature extraction: for all shot video data, firstly detecting out vehicle images appearing under a camera, dividing the vehicle images of the monitoring video into a plurality of equilong vehicle image sequences according to the vehicles and the camera, calculating grayscale histograms of two channels Cr and Cb in a YCrCb space, and finally obtaining vehicle contour images by using a Gabor filter and original image convolution; performing a set-to-set-based metric learning method: training a step of learning a metric function of relative distances between vehicle target image sequences, namely, performing metric learning based on a thought of maximization of a probability that inner-class distances are shorter than between-class distances; and performing between-set metric learning-based vehicle re-identification. According to the method, the complexity of an algorithm is lowered while feature dimensions are reduced; and after between-set distance measure is added based on a re-identification effect, the identification rate of the algorithm is increased and the identification effect is improved.

Description

technical field [0001] The invention relates to a method for re-identifying vehicles in monitoring video sequence images. Background technique [0002] The vehicle images captured by the monitoring system without overlapping fields of view are the main processing objects used in the vehicle re-identification problem. However, these vehicle images contain problems such as viewing angle changes, resolution, illumination changes, blur, camera settings, complex backgrounds, and occlusions. This makes the vehicle re-identification problem more difficult, and the solutions to these problems are still being studied by many scholars. In the field of vehicle re-identification under the non-overlapping view monitoring system, there are many methods proposed by domestic and foreign researchers. These methods can be roughly divided into two categories, one is the vehicle re-identification algorithm based on feature selection, and the other is the vehicle re-identification algorithm bas...

AI Technical Summary

Problems solved by technology

Using metric learning methods, such as PCCA[7], ([7]A.Mignon and F. Jurie. PCCA: A new approach for distance learning from sparsepairwise constraints. Computer Vision and Pattern Recognition, 2012, 157:2666-2672) LMNN[8], ([8]K. Q. Weinberger and L. K. Saul. Distance metriclearning for large margin nearest neighbor classification. Journal of Machine Learning Research, 2009, 10:207-244) RankSVM[9] and LDML[10] ([9] B. Prosser, W.-S. Zheng, S. Gong, and T. Xiang. Per...

Images