Pedestrian re-identification method and device based on Bayesian optimization technology and system

Abstract

The invention provides a pedestrian re-identification method and device based on a Bayesian optimization technology and a computer system, and the method comprises the steps: carrying out the detection of a pedestrian image data set in a video through employing a depth target detection algorithm, and obtaining all pedestrian image data of a to-be-extracted feature; performing depth feature extraction on all detected pedestrian image data to obtain all feature value data of pedestrians in the video, thereby establishing a retrieval feature database; and inputting a to-be-queried picture, carrying out depth feature extraction on the picture to obtain a to-be-retrieved image feature value, carrying out Euclidean distance calculation and sorting on the to-be-retrieved image feature value and all feature values in the retrieval feature database, and outputting a sorting result. According to the scheme, the precision of an existing model is improved by improving the prior art, so that the reasoning speed is guaranteed, and the retrieval precision is improved.

Description

technical field [0001] The invention relates to the technical field of video surveillance, in particular to a pedestrian re-identification method, device and computer system based on Bayesian optimization technology. Background technique [0002] Pedestrian re-identification is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence, and is widely considered to be a sub-problem of image retrieval. Cross-mirror tracking technology ReID, in short, is to capture scenes with multiple people (possibly thousands of people at most) under different camera equipment (such as surveillance cameras, mobile phone cameras, etc.) The same person is identified. The main difference between ReID and face recognition is that the face is used to authenticate a person's identity, while Pedestrian ReID is to match the same person under different camera equipment without knowing the real identity of that person. Given a mo...

AI Technical Summary

Problems solved by technology

The first method has small model parameters and fast inference speed, but the retrieval accuracy is average; the second method achieves the most advanced performance in the field of pedestrian re-identification, but the large number of model parameters makes the calculation of feature inference and retrieval complicated. Greatly improved speed and time

Since there is a large amount of video data in the security monitoring scene of the actual application, the second method is difficult to meet the real-time processing requirements due to the high computational complexity and the high cost of the corresponding hardware.

Images