Pedestrian re-identification method, device and equipment and storage medium

Abstract

The invention discloses a pedestrian re-identification method, device and equipment and a storage medium. The pedestrian re-identification method comprises the following steps: inputting each frame ofpedestrian picture into a residual error network to extract features; inputting features extracted from two adjacent frames into an optical flow graph prediction network to obtain a frame of opticalflow graph; inputting the features of the previous frame and the optical flow graph into a feature fusion device for fusion; inputting the fusion features and the optical flow graph of each frame intoa long-short-term memory network with an optical flow graph processing mechanism, inputting the obtained multi-frame data output features into a uniform volume integral block model for horizontal block processing, performing classification loss training on each block, and taking a classification score as a weight; multiplying the feature vector of each block by the weight to obtain a contrast loss function, training the whole pedestrian re-identification asymmetric twin network model, and carrying out pedestrian re-identification. According to the method, complementation information of multiple frames of pictures can be fused to generate complete pedestrian characteristics, noise information is removed, cost is saved, and recognition accuracy is improved.

Description

technical field [0001] The present invention relates to the field of computer vision, in particular to a pedestrian re-identification method, device, equipment and storage medium. Background technique [0002] Person Reidentification (Person Re-ID) is an important technology in public security. In ordinary life, it is mainly used to find children lost in the park, and in public security cases, it is mainly used to track suspects. Deep learning has developed rapidly in recent years, especially the emergence of convolutional neural network (CNN), which has brought great impetus to the field of image processing. Slowly, deep learning algorithms for target detection have emerged, developed by R -CNN-type image detection algorithm as a representative, target detection technology is the basic work of pedestrian re-identification, it can train pedestrian detection model, applied to the work of pedestrian re-identification. Due to the advancement of technology, pedestrian re-ident...

AI Technical Summary

Problems solved by technology

There are two shortcomings in this algorithm model: one is that there are still certain errors in the pose estimation data set and the pedestrian re-identification data set, which will lead to inaccurate accuracy; if the pose estimation model is trained on the pedestrian re-identification data set Additional labeling is required and the cost is huge; the other is that the algorithm of the pose estimation model has a large amount of calculation, and embedding the pedestrian re-identification model will further increase the amount of calculation of the model, which will make the detection speed very slow and may not be able to achieve The requirement of real-time recognition leads to the phenomenon of underfitting; and this algorithm only uses a single frame of pedestrian images to train the model, most of the work is only performed on a single frame of images, and the information of a single frame of pedestrian images is always scarce , cannot provide a good solution to the problem of removing pedestrian occlusion

Images