Covered pedestrian re-identification method based on adaptive deep metric learning

Abstract

The invention provides a covered pedestrian re-identification method based on adaptive deep metric learning and relates to the computer vision technique. The method is characterized by, to begin with,designing convolutional neural network structure, which is robust to coverage, and extracting middle-and-low-level semantic features of a pedestrian image in the network; then, extracting local features robust to coverage, and combining global features, then, studying high-level semantics features, learning features sufficiently discriminating for pedestrian identity change through adaptive neighbor deep metric loss, and combined with classification loss, finishing update learning of the whole network quickly and stably; and finally, according to a trained network model, extracting output ofa first full connection layer as feature representation from a test image and finishing subsequent feature similarity comparison and sorting to obtain a final pedestrian re-identification result. Themethod effectively improves robustness of features to coverage.

Description

technical field [0001] The invention relates to computer vision technology, in particular to an occluded pedestrian re-identification method based on adaptive depth metric learning. Background technique [0002] Pedestrian re-identification refers to identifying a single pedestrian from different camera perspectives, that is, judging whether the pedestrians appearing in different perspectives are the same person. Pedestrian re-identification technology is a challenging technology in the field of computer vision, which is widely used in camera monitoring, intelligent security, etc. The main challenge of the pedestrian re-identification task is the dramatic change in the appearance of pedestrians captured by different cameras. [0003] The pedestrian re-identification method mainly includes two steps: 1) Effective feature description, which is used to describe the appearance changes of pedestrians, such as Yang et al. (Y.Yang, J.Yang, J.Yan, S.Liao, D.Yi, and S.Z.Li, “Salien...

AI Technical Summary

Problems solved by technology

However, this method does not consider the spatial structure relationship in pedestrian images, which can effectively deal with pedestrian recognition under occlusion.

Images