Pedestrian re-identification model training method and device and pedestrian re-identification method and device

Abstract

The invention discloses a pedestrian re-identification model training method and device and a pedestrian re-identification method and device, and the pedestrian re-identification model training methodcomprises the steps: carrying out the feature extraction of a pedestrian image through a convolution network of a pedestrian re-identification model, and obtaining the original features of the pedestrian image; processing the original features by using an attention module of the pedestrian re-identification model to obtain a plurality of pedestrian local features; determining a similarity matrixamong the pedestrian local features by using a graph neural network of the pedestrian re-identification model, and adjusting the pedestrian local features according to the similarity matrix; and determining a pedestrian recognition result and training loss of a pedestrian re-recognition model based on the adjusted pedestrian local features, and optimizing model parameters according to the trainingloss. According to the invention, the important pedestrian local features in the image can be automatically extracted without introducing extra annotation information, so that the final pedestrian local features have higher discrimination capability, and the model recognition performance is also improved.

Description

technical field [0001] The present application relates to the technical field of pedestrian re-identification, in particular to a pedestrian re-identification model training method and device, and a pedestrian re-identification method and device. Background technique [0002] Person Re-identification (Person Re-identification) technology is one of the core technologies in the field of security and new retail. In recent years, deep learning has made great breakthroughs in this field. In order to achieve better recognition performance, recent high-performance solutions use local features to capture finer-grained features to enhance model discrimination. [0003] The current local feature methods are mainly divided into two types: 1) Manual division, which directly divides the picture or feature map into several parts, and extracts features separately. The representative work is ECCV (European Conference on Computer Vision, European International Conference on Computer Vision) ...

AI Technical Summary

Problems solved by technology

[0005] (1) The local feature method based on manual division will lead to a decrease in model performance;

[0006] (2) The division method based on additional information will greatly affect the inference speed of the model

Images