Pedestrian re-identification method based on multi-attribute and multi-strategy fusion learning

Abstract

The invention discloses a pedestrian re-identification method based on multi-attribute and multi-strategy fusion learning. The method of the invention includes the steps of in an offline training phase, firstly selecting pedestrian attributes which are easy to be judged and have a sufficient distinguishing degree, training a pedestrian attribute identifier on an attribute data set, then labeling attribute tags for a pedestrian re-identification data set by using the attribute identifier, and next, by combining the attributes and pedestrian identity tags, training a pedestrian re-identification model by using a strategy fused with pedestrian classification and novel constraint comparison verification; and in an online query phase, extracting features of a query image and images in a database by using the pedestrian re-identification model, and calculating the Euclidean distance between the feature of the query image and the feature of each image in the database to obtain the image with the shortest distance, which is considered as the result of pedestrian re-identification. In terms of performance, the features in the invention are distinguishable and high accuracy is obtained; and in terms of efficiency, the method of the invention can quickly search for the pedestrian indicated by the query image from the pedestrian image database.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and more specifically relates to a pedestrian re-identification method based on multi-attribute and multi-strategy fusion learning. Background technique [0002] In recent years, frequent terrorist attacks at home and abroad have posed a great threat to the lives and property of people all over the world. As the anti-terrorism situation in the world becomes increasingly severe, governments of various countries invest more and more in maintaining public safety. In 2005, the State Council approved the "Safe City" plan proposed by the Ministry of Public Security. Now more than 600 cities in my country are vigorously building "Safe City". The video surveillance system is an indispensable part of the construction of a "Safe City". At present, more than 20 million surveillance cameras are installed in public places across the country. Each camera in the video surveillance system is continu...

AI Technical Summary

Problems solved by technology

In the current large-scale data set, there are mainly three-step methods for combining attributes, combining semantic attributes and latent attributes to learn together, focusing more on attribute prediction and optimization in the process, and using the correlation joint modeling of multiple attributes, and simultaneously Attribute prediction and pedestrian re-identification, but they use manual labeling of pedestrian re-identification datasets, the workload is too large, which affects the overall efficiency of the algorithm

[0006] To sum up, a lot of research work has been done in the field of pedestrian re-identification, but the existing methods have problems such as poor expressiveness, poor robustness to pedestrian appearance changes, complex construction and application, and cannot be directly applied to surveillance video intelligence. analysis system

Images