Multi-scale pedestrian re-identification method based on multi-granularity depth feature fusion

Abstract

The invention discloses a multi-scale pedestrian re-identification method based on multi-granularity depth feature fusion, and the method comprises the steps: selecting a pedestrian re-identification data set, and carrying out the preprocessing of a training set in the data set; selecting a residual network as a basic skeleton, including a global coarse-grained fusion learning branch, a local coarse-grained fusion learning branch and a local attention fine-grained fusion learning branch; adopting softmax loss and triple loss as re-identification network supervisors, and training a pedestrian re-identification network model; and fusing the network features of different branches as a final descriptor of the pedestrian, and taking the to-be-queried pedestrian image as the input of the pedestrian re-identification network model to obtain a pedestrian re-identification result. According to the method, the pressure of a complex background or posture change on a re-identification task is effectively relieved, and the identification precision is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a pedestrian re-identification method. Background technique [0002] Pedestrian re-identification is a technology that uses computer vision algorithms to retrieve pedestrians across cameras based on their clothing, posture, hairstyle and other information. When a specific pedestrian in a monitoring device is determined, the pedestrian can be retrieved from other non-overlapping camera devices by this method, and tracked and identified. In recent years, combined with video pedestrian tracking and detection technology, it has been widely used in public place security monitoring. [0003] Traditional research methods are mostly based on manually designed features, however, with the rapid development of deep learning, these traditional research methods are gradually being replaced. As one of the typical feature extraction methods in deep learning, convolutional ...

AI Technical Summary

Problems solved by technology

However, in real scenarios, the deployment of pedestrian re-identification systems is still troubled by many factors, such as blurred images obtained from monitoring equipment, changes in pedestrian postures, different camera angles, occlusion interference, etc., resulting in low recognition rates

Images