Person Re-identification Method and Device Based on Residual Attention Mechanism Spatio-temporal Joint Model

Abstract

The present invention provides a pedestrian re-identification method and system based on the spatio-temporal joint model of the residual attention mechanism, including extracting features of the input pedestrian through the pre-trained ResNet-50 model; constructing a residual attention mechanism network, including the residual attention mechanism module, feature sampling layer, global pooling layer and local feature connection layer; according to the trained residual attention mechanism network, the cosine distance is used to calculate the feature distance and recorded as the visual probability; according to the camera ID and frame in the pedestrian label of the training sample Spatio-temporal probability modeling of number information, and Laplace smoothing for the probability model. Using visual probability and spatiotemporal probability, the final joint spatiotemporal probability is used to obtain pedestrian re-identification results. The invention overcomes the problem that the existing method ignores the time and space prior information in the camera network, optimizes the network iteration with the attention residual mechanism network, accelerates the convergence, and solves the problem through the optimized Bayesian joint probability, so that pedestrians The recognition accuracy is higher.

Description

technical field [0001] The invention belongs to the technical field of pedestrian re-identification, and relates to a pedestrian re-identification method and device based on a residual attention mechanism spatio-temporal joint model. Background technique [0002] Surveillance video is usually unable to obtain very high-quality face pictures due to the camera resolution and shooting angle, and pedestrians often show multi-scale characteristics, making detection and recognition difficult. At this time, pedestrian re-identification has become a very important alternative technology . Pedestrian re-identification is to achieve cross-device retrieval through a given monitored pedestrian image, which can effectively compensate for the visual limitations of fixed-view cameras, and has important application value in the fields of video surveillance, intelligent security, and smart cities. [0003] In recent years, with the development of machine learning theory, methods based on de...

AI Technical Summary

Problems solved by technology

However, most of the existing methods to solve the pedestrian re-identification problem only use the pedestrian identity information in the tag, and ignore the spatio-temporal information such as the camera ID information, the time sequence of the image, and the frame number of the image in the video, which are easier to collect.

Images