A method for person re-identification based on self-motivated discriminative feature learning

Abstract

The invention discloses a pedestrian re-identification method based on self-excited discriminative feature learning, comprising: (1) selecting a pedestrian re-identification network, and adding a negative branch to the original network; (2) in the training stage, the original network Generate a classification loss function, generate an adversarial loss function and a mutually exclusive response item between the original network and the negative branch, together form the objective function, and use the stochastic gradient descent method to optimize the entire network; (3) In the testing phase, remove the negative branch , only keep the part of the original network before the classifier as the trained network model, and input the pedestrian picture to extract the feature vector test; (4) in the pedestrian retrieval stage, use the trained network model to extract each picture in the picture library The eigenvector of the pedestrian image, select the identity of the image with the highest similarity with the eigenvector of the pedestrian image to be queried as the final recognition result. The invention can improve the effect of the existing pedestrian re-identification network.

Description

technical field

[0001] The invention relates to the field of computer vision and pattern classification, in particular to a pedestrian re-identification method based on self-excited discriminative feature learning. Background technique

[0002] In recent years, with the emergence of a large number of surveillance cameras in public places, pedestrian re-identification technology has received more and more attention. The goal of pedestrian re-identification technology is to perform cross-camera pedestrian search, that is, given a pedestrian picture captured by a certain camera, find pictures belonging to the same identity as this picture from other cameras. Pedestrian re-identification has a wide range of applications in missing person finding and suspect tracking. In recent years, pedestrian re-identification technology has developed rapidly, but there is still a long way to go before it can be applied to actual scenes. The difficulty is caused by many aspects: changes in il...

Images