Pedestrian re-identification method based on multi-component self-attention mechanism

Abstract

The invention provides a pedestrian re-identification method based on a multi-component self-attention mechanism. The method comprises the following steps: firstly, pre-training a deep convolutional neural network backbone model; then, after the backbone model is branched, a multi-component self-attention network is constructed, and multi-component self-attention characteristics are obtained; inputting the multi-component self-attention features into a classifier, and performing joint training to minimize cross entropy loss and metric loss; and finally, inputting a test set picture into the trained model, fusing the output part features to obtain an overall feature, and realizing pedestrian re-identification through metric sorting. According to the method, various challenges existing in the pedestrian re-identification problem are fully considered, a multi-component self-attention mechanism is provided, the attention activation area is effectively expanded, and pedestrian features areenriched; the self-attention module enables the network to pay more sufficient and careful attention to an area with discrimination characteristics, and the spatial attention module and the channel attention module are integrated into the network in a residual form, so that the network is more robust and stable, and is easy to train.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and computer vision, and in particular relates to a pedestrian re-identification method based on a multi-component self-attention mechanism. Background technique [0002] With the acceleration of urbanization, public safety has become the focus and demand of people's increasing attention. Many important public health areas such as university campuses, theme parks, hospitals, and streets are widely covered with surveillance cameras, creating good objective conditions for automated surveillance using computer vision technology. [0003] In recent years, person re-identification, as an important research direction in the field of video surveillance, has attracted increasing attention. Specifically, pedestrian re-identification refers to the technology of using computer vision technology to judge whether a specific pedestrian exists in an image or video sequence under cross-camera and...

AI Technical Summary

Problems solved by technology

[0004] In an open environment, due to the complex and changeable monitoring scene, the collected pedestrian images often have interference factors such as background noise, illumination changes, posture changes, and severe occlusions. The area of ​​the degree of discrimination leads to the extraction of features that are not robust enough and the recognition performance is poor

Images