Pedestrian re-identification method and system of binarized triple twin network model

Abstract

The invention discloses a pedestrian re-identification and method for a binary triple twin network model, and the method comprises the steps: enabling three paths of convolutional neural networks to input positive and negative samples and detection sample images, extracting image features, and enabling each path of convolutional neural network to comprise a convolutional layer, a pooling layer, and a full connection layer; wherein the convolutional layer, the pooling layer and the full connection layer of each convolutional neural network are the same and share weight parameters, and binarizing the weight parameters and an activation function value between the convolutional layer and the pooling layer; connecting the Softmax layer with each full connection layer, and classifying and normalizying features output by the convolutional neural network and connecting the Triplet loss verification function module with the Softmax layer and using the module for receiving the sample characteristics output by the normalization classification layer and carrying out similarity calculation on the sample pairs. According to the invention, the deep learning model with stronger identification capability is obtained, and the problem of large content difference caused by illumination, scene change and human body posture diversification of similar and same pedestrian pictures on different pedestrian picture contents is better solved.

Description

technical field [0001] The invention relates to the field of computer vision image and video processing, in particular to a pedestrian re-identification method and system of a binary triplet twin network model. Background technique [0002] Pedestrian re-identification can generally be viewed as an image retrieval problem, i.e. matching pedestrians from different cameras. Given a queried pedestrian image, person re-identification aims to find images of the same pedestrian as the pedestrian from a library of pedestrian images from non-overlapping camera views. [0003] Because the images of pedestrians captured by the camera are affected by lighting, posture, viewing angle, image resolution, camera settings, occlusion, and background clutter, there will be great changes in the same pedestrian image, but it will be different when the pedestrian wears the same clothes or has a similar appearance. Phenomenon identified as the same person. [0004] Therefore, person re-identifi...

AI Technical Summary

Problems solved by technology

However, the current CNN-based pedestrian re-identification method still cannot solve the problem that different pedestrian pictures are similar in content but the same pedestrian pictures have large content differences due to lighting, scene changes, and diversification of human body postures.

Images