Unsupervised pedestrian re-identification method based on pedestrian attribute adaptive learning

Abstract

The invention provides an unsupervised pedestrian re-identification method based on pedestrian attribute adaptive learning. The method comprises the following steps: firstly, pre-training an adjustedResNet50 network by utilizing a source video set with a label to obtain a pre-trained pedestrian attribute CNN model; secondly, space-time constraint information of the target video set is fully utilized on the target video set without any mark to generate a training sample on line; then, inputting the generated training sample into a Triplet network, and carrying out parameter fine tuning on a pre-trained pedestrian CNN model to obtain pedestrian features with higher discrimination; and finally, performing pedestrian feature extraction and similarity measurement by using the trained network to realize pedestrian re-identification. Characteristics learned by the method have higher robustness and discrimination, the accuracy of pedestrian re-identification can be remarkably improved, and the application range of pedestrian re-identification is expanded.

Description

technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, and in particular relates to an unsupervised pedestrian re-identification method based on adaptive learning of pedestrian attributes. Background technique [0002] In recent years, as the society pays more and more attention to security precautions such as the prevention of violent terrorist incidents and criminal investigation, the camera network is widely used in public places such as subways, airports, campuses, supermarkets, etc. Surveillance video data has exploded. Non-overlapping view camera monitoring technology can not only effectively expand the monitoring field of view, but also have a clearer grasp of the behavior of moving targets in multiple different monitoring areas, and has become a research hotspot in the field of monitoring analysis. For most monitoring scenarios, pedestrians are an important analysis object of intelligent monitoring. Vision-bas...

AI Technical Summary

Problems solved by technology

However, this method requires a lot of manpower and material resources to label the source video set, and it is obviously unrealistic to label the existing massive surveillance video data

In addition, since the distribution of pedestrian features in the target video set is usually very different from that in the source video set, using the CNN model learned on the source video set to identify pedestrian targets in the target video often does not achieve the best performance.

Images