Pedestrian re-recognition method and device based on deep learning

Abstract

The invention provides a pedestrian re-recognition method and device based on deep learning. The pedestrian re-recognition method comprises the steps of acquiring a target pedestrian image and a reference pedestrian image from a first video stream and a second video stream respectively, wherein the first video stream and the second video stream are videos shot by cameras with different angles in a preset region; by using a pre-trained deep learning network model, extracting an image feature of the target pedestrian image to act as a first image feature, and extracting an image feature of the reference pedestrian image to act as a second image feature; calculating the feature similarity of the first image feature and the second image feature; if the feature similarity conforms to a preset requirement, determining a target pedestrian in the target pedestrian image and a reference pedestrian in the reference pedestrian image are the same pedestrian. Implicit features of the target pedestrian image and the reference pedestrian image are learnt respectively by adopting a deep learning technology, a coupling problem existing in paired pedestrian images adopted by a traditional pedestrian re-recognition method is overcome, and the flexibility is good.

Description

technical field [0001] The present invention relates to the technical field of pattern recognition, in particular to a method and device for pedestrian re-identification based on deep learning. Background technique [0002] Pedestrian re-identification refers to the technology of automatically matching the same pedestrian object under the non-overlapping multi-camera images in the illuminated area, so as to quickly and accurately discover the moving images and trajectories of the pedestrian object under the multi-camera. Although pedestrian re-identification technology has broad application prospects in video control, intelligent transportation, multimedia retrieval and other fields, because the pictures in pedestrian re-identification come from different cameras, and the angles and lighting of different cameras are affected by the environment. In different pictures of the same pedestrian, the appearance features will change to a certain extent; on the contrary, due to chang...

AI Technical Summary

Problems solved by technology

[0004] In the research, the inventor found that the pedestrian re-identification method in the prior art can only extract features and pedestrian recognition through the depth model based on the paired pedestrian images. Since the above-mentioned paired pedestrian images cannot be decoupled, the method is flexible. Poor degree

Images