Depth pedestrian re-identification method based on positive sample balance constraint

Abstract

The invention provides a depth pedestrian re-identification method based on positive sample balance constraint. A residual error network employed in the method is simple in structure and can be widely used, and the network structure which is deep sufficiently improves the feature representation capability. Moreover, there is no need to specially design the network structure. A residual error classifier is used for feature extraction of an image, so the accuracy of pedestrian re-identification can be greater than the accuracy of most of well-designed methods. Compared with two-tuple loss and three-tuple loss methods, the method does not need to intentionally generate an effective sample for improving the structural loss and can achieve the similar effect. Moreover, the method enables the learned gradient direction to be more robust and effective through the overall distribution information. On the basis of improving the structural loss, the method improves the positive sample balance constraint, can control the distance of a positive sample pair, also can balance the gradients of the distance of the positive sample pair and the distance of a positive sample pair, enables the algorithm to be easier to train, and improves the performances of an algorithm.

Description

technical field [0001] The present invention relates to the field of deep learning and pedestrian re-identification, and more specifically, to a deep pedestrian re-identification method based on positive sample balance constraints. Background technique [0002] Over the years, the fields of pattern recognition, machine learning, and computer vision research have made impressive progress. These advances have attracted the attention of the video surveillance, legal and security industries, and the demand for these intelligent algorithms and intelligent systems in this industry is also increasing. Under the influence of the continuous development of the security industry, smart monitoring tools for face detection, fingerprint detection, other biometric monitoring, and people and urban environments are widely used. These tools collect a large amount of data, usually in the form of images or videos, which brings new research topics to the field of machine learning, and the topic...

AI Technical Summary

Problems solved by technology

However, most of the current deep learning methods use the information of the local distribution of data, and still use fewer hidden layers, and the network is relatively not deep, so there is still room for improvement in algorithm performance

Images