Pedestrian re-identification method based on pedestrian identity and attributive character combined identification verification

Abstract

The invention provides a pedestrian re-identification method based on pedestrian identity and attributive character combined identification verification, which makes full use of complementary information of pedestrian identity and attributive character, and performs multi-task learning on a deep convolutional neural network in two modes of combined identification and verification to obtain more discriminative pedestrian characters. According to the method, pedestrian identity characters and pedestrian attributive characters are learned at the same time, so that a character layer of the neuralnetwork can learn overall identity characters of a pedestrian high layer and can also grab semantic characters of a middle layer, the two characters are effectively fused in the same neural network, and therefore, the method has higher robustness and discrimination. Besides, the deep convolutional neural network is trained in a supervised manner by combining two modes of pedestrian recognition andpedestrian verification so that different types of pedestrian pictures can be distinguished by the learned pedestrian characters, the character distance of the same pedestrian can be enabled to be quite short, and the character distance of different pedestrians can be enabled to be quite long.

Description

technical field [0001] The invention relates to the technical field of computer vision and pattern recognition, in particular to a pedestrian re-identification method for joint identification and verification. Background technique [0002] In recent years, surveillance cameras with non-overlapping fields of view are often used to conduct large-scale video surveillance of crowded public places such as schools and stations, and play an important role in security prevention, case investigation, and suspect tracking. For most monitoring scenarios, pedestrians are an important analysis object of intelligent monitoring. Vision-based pedestrian re-identification technology is an important research content of intelligent monitoring and the basis for cross-camera retrieval and tracking. Although the existing person re-identification methods have achieved some results, it is still a challenging task due to the complex and changing lighting and imaging conditions. The problems of perso...

AI Technical Summary

Problems solved by technology

However, the existing methods do not jointly recognize and verify patterns to train the network to learn pedestrian identity features and attribute features at the same time.

Images