Semi-supervised LDA pedestrian re-identification algorithm based on K-nearest neighbor resampling

Abstract

Person re-identification is a challenging task in the field of computer vision in recent years. The image samples of pedestrians undergo with drastic appearance variations across camera views. The training data of the existing dataset is unable to describe the complex appearance changes, which leads to over-fitting problem of the metric model. In order to solve this problem, based on the statistical and topological characteristics of multi-view paired pedestrian images, a resampled linear discriminant analysis (LDA) method was proposed. This method utilized sample normality and k-nearest neighbours to form potential positive pairs. The potential positive pairs are used to improve the metric model and generalize the metric model to the test data. By optimizing the inter-class divergence method, a semi-supervised re-sampling LDA person re-identification algorithm was established. It was then tested on the VIPeR, CUHK01 and Market 1501datasets. The results show that the proposed method achieves the best performance compared to some available methods. Especially, the proposed method outplays the best comparison method by 0.6% and 5.76% at rank-1 identification rate on the VIPeR and CUHK01 datasets respectively. At the same time, the improved LDA algorithm has improved the rank-1 identification accuracy of traditional LDA method by 9.36% and 32.11% on these two datasets respectively. Besides, the proposed method is limited to Market-1501 dataset when the test data is of large size.