A pedestrian re-recognition method based on depth learning

Abstract

The invention discloses a pedestrian re-identification method based on depth learning, includes Step 1: pre-training the CNN model: including pedestrian feature extraction and feature measurement, wherein pedestrian feature extraction adopts the method of combining global feature and local feature, Euclidean distance is used as similarity measure, and loss function based on measure matrix is established under the constraint condition of distance of eigenvector. The loss function is optimized by adding constraint function on the basis of traditional Triplet Loss. 2, testing the data set: inputting the image of the teste data set into the CNN model trained in the step 1, obtaining the image features, calculate the similarity between the target pedestrian image and the reference pedestrian image by the Euclidean distance, and finally arranging the reference pedestrian image according to the similarity magnitude to obtain the pedestrian re-recognition result. The method is suitable for there-recognition of people in complex scenes, and has strong transplantability for scene changes, stable algorithm, fast speed and strong practicability.

Description

technical field [0001] The invention belongs to the fields of digital image processing and computer vision, and in particular relates to a pedestrian re-identification method based on deep learning. Background technique [0002] With the extensive application of surveillance cameras in various fields, traditional manual surveillance methods cannot cope with the resulting massive surveillance videos. Pedestrian re-identification refers to pedestrian matching under the monitoring of multiple cameras, that is, given a pedestrian target, the target is found in the videos captured by multiple cameras in different positions at different times. Pedestrian re-identification technology is the core technology in many fields such as intelligent video analysis, video surveillance, human-computer interaction, etc., and has become a research hotspot in the field of computer vision. However, due to the influence of factors such as illumination, viewing angle, posture, occlusion and resolu...

AI Technical Summary

Problems solved by technology

This has several major drawbacks: 1) inaccurate pedestrian detection boxes may affect feature learning; 2) occluded body parts may introduce irrelevant context into the learned features; 3) local differences in global features are Very important, especially when we have to distinguish between two people with very similar appearance; 4) deformed and blurred body postures, making metric learning difficult

[0005] Due to the camera's angle of view, scale, illumination, clothing and posture changes, different resolutions, and occlusions, continuous position and motion information may be lost between different cameras. Standard distance metrics such as Euclidean distance and Barrett's distance are used to measure pedestrians. The similarity of apparent features cannot obtain a good re-identification effect

Images