Pedestrian re-identification method based on a skeleton posture

Abstract

A pedestrian re-identification method based on a skeleton posture comprises the following steps: acquiring a pedestrian image, and constructing a target pedestrian template; collecting image frames and sequentially segmenting all pedestrian images under various postures in the image through skeleton detection; performing size standardization on all segmented pedestrian images and skeleton information according to the target pedestrian skeleton template; according to the pedestrian skeleton information, sequentially carrying out local feature region segmentation on all the pedestrian images, and carrying out tilt correction on the local feature regions of all the pedestrians to obtain a local feature image set consistent with the target pedestrian template attitude; and establishing a target pedestrian local feature fusion recognition model, and comprehensively calculating the similarity between the target pedestrian template and all pedestrians detected in real time to realize accuraterecognition of the target pedestrian. According to the invention, effective pedestrian identification under the influence of abnormal postures such as bowing, limb inclination and the like in a multi-person scene in a complex environment can be realized, and the pedestrian identification accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of pedestrian recognition, in particular to a pedestrian re-identification method based on skeleton posture. Background technique [0002] Person re-identification (Person re-identification) is to identify the target pedestrian in the video images captured by different cameras. Different from pedestrian tracking, pedestrian re-identification can achieve long-term cross-border tracking goals in complex environments, so it can play a very important role in the field of monitoring. For example, pedestrians are re-tracked in the surveillance video. When the police are handling the case, the computer can automatically lock the suspect without manual time-consuming and laborious observation and identification. [0003] At present, pedestrian re-identification based on pedestrian feature matching usually uses a single feature matching, and its effect is often not ideal. Continuously track requirements. In additi...

AI Technical Summary

Problems solved by technology

[0003] At present, pedestrian re-identification based on pedestrian feature matching usually uses a single feature matching, and its effect is often not ideal. Continuous Tracking of Demand

In addition, the traditional recognition method that takes the whole body as a whole cannot highlight the local features of pedestrians. When encountering occlusion, important feature information of the target will be lost, resulting in a decrease in recognition rate, and ordinary local area extraction and similarity matching will cause local problems. The situation where the regions cannot be aligned leads to ambiguity in the matching, which greatly reduces the recognition rate

Images