Few-sample pedestrian re-identification method based on deep multi-example learning

Abstract

The invention relates to a few-sample pedestrian re-identification method based on deep multi-example learning. The method comprises three stages: a network pre-training stage, a data set expansion stage and a network fine tuning stage. The method includes: after the pedestrian re-identification feature extraction sub-network is pre-trained, performing data expansion by utilizing a pedestrian keypoint feature region exchange algorithm; finely adjusting the pedestrian re-identification feature extraction sub-network and the feature aggregation sub-network by using the expanded data set; iteratively repeating data set expansion and network fine tuning until the feature extraction sub-network and the feature aggregation sub-network converge. Once the training is completed, the pedestrian re-identification model on the original domain is migrated and extended to the target domain by using few samples. On the premise of giving a small number of learning samples in the target domain, the pedestrian re-identification model can be effectively migrated and expanded to the target domain monitoring network, and the few-sample pedestrian re-identification method has the advantages of high accuracy, good robustness, good expansibility and mobility.

Description

technical field [0001] The invention belongs to the technical field of computer image analysis, and in particular relates to a method for re-identifying pedestrians with few samples based on deep multi-instance learning. Background technique [0002] Pedestrian re-identification algorithms are designed to identify and match pedestrian pictures captured by multiple disjoint cameras. In the past few years, the task of person re-identification has received more and more attention, and plays an important role in a large number of applications in natural scenarios, such as suspect tracking, crowd counting, security surveillance, etc. With the upsurge of deep learning, a large number of deep model-based methods have been proposed to solve the problem of pedestrian re-identification under supervised learning. These methods are either used to mine to learn more discriminative feature representations, or to learn better similarity measures, or to combine the above two. At the same ...

AI Technical Summary

Problems solved by technology

However, it is very difficult and tedious to manually label pedestrian images across multiple cameras

Images