A pedestrian re-identification method, device, equipment and readable storage medium

Abstract

The invention discloses a pedestrian re-identification method, device, equipment and readable storage medium; in this scheme, the isomorphic training network of the initial pedestrian re-identification network is trained by objective functions such as dynamic classification probability loss functions, and the carrying The final person re-identification network with more accurate final weight parameters, and the person re-identification task is performed through the final person re-identification network. In this way, the accuracy and performance of the pedestrian re-identification network processing pedestrian re-identification task can be improved, and the equipment can be reduced. The occupancy of internal storage space is more conducive to the storage and deployment of portable devices, reduces the amount of calculation for performing pedestrian re-identification tasks, and improves the processing rate of pedestrian re-identification tasks.

Description

technical field [0001] The present invention relates to the technical field of image recognition, and more specifically, to a pedestrian re-identification method, device, equipment and readable storage medium. Background technique [0002] Pedestrian re-identification (Person re-identification, Re-ID) is an important image recognition technology, widely used in public security systems, traffic supervision and other fields. Pedestrian re-identification searches cameras distributed in different locations to determine whether the pedestrians in the field of view of different cameras are the same pedestrian. This technology can be used in scenarios such as criminal suspect search and missing child search. Pedestrian re-identification is mainly realized through deep learning technology, and with the continuous development of deep learning technology, network models emerge in an endless stream. In order to further improve the accuracy and performance of pedestrian re-identificatio...

AI Technical Summary

Problems solved by technology

[0004] 2. Deeper, wider or more complex pedestrian re-identification networks usually increase the amount of calculation, which is not conducive to the application of scenarios with high real-time requirements

For example: for the retrieval and tracking of criminal suspects, a large calculation delay will cause the entire system to miss the best opportunity, which will have a negative impact on system functions

Images