A method and system for image person re-identification based on multi-attention joint learning

Abstract

The invention discloses an image pedestrian re-identification method and system based on multi-attention joint learning, belonging to the technical field of image processing. The present invention introduces Soft attention and high-order attention into the ResNet50 feature extraction network, uses the complementary effects of two different types of attention on feature extraction, improves the feature extraction network's ability to learn pedestrian features, and makes the feature extraction network Focus on more discriminative features in pedestrian images. In order to obtain more accurate attention features, a multi-level attention loss function is proposed. This loss function is used to guide the training and learning of the feature extraction network, and further improve the learning ability of the feature extraction network for pedestrian features. While learning the global features of pedestrians, the intermediate features in the feature extraction network are fused and the learning of local features of pedestrians is strengthened, which improves the ability of the network to learn the subtle differences between pedestrian features, and improves the performance of the network in image pedestrian re-identification.

Description

technical field [0001] The invention belongs to the research field of pedestrian re-identification in image processing and machine vision, and in particular relates to an image pedestrian re-identification method and system based on multi-attention joint learning. Background technique [0002] Pedestrian re-identification is a fundamental task in automatic video surveillance, and it is also a research hotspot in recent years. The purpose of person re-identification is to establish corresponding links between observations of the same person under different cameras. Typically, this is done by taking an image (or set of images) of a person seen in one camera view and forming a descriptive model for comparison with images of pedestrians observed in another camera view or point in time . Its purpose is to determine the past (or present) position of a person in a set of cameras by finding the correct matching image. [0003] Person re-identification is a very difficult research...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defect of low pedestrian re-identification accuracy caused by the use of single attention in the prior art and the need for improvement, the present invention provides a method and system for image pedestrian re-identification based on multi-attention joint learning, the purpose of which is to use the Soft attention module And high-order attention module, extract more robust and more discriminative features, and obtain the similarity between images, improve the accuracy of recognition

Images