Multi-granularity cross modal feature fusion pedestrian re-identification method and re-identification system

Abstract

The invention discloses a multi-granularity cross modal feature fusion pedestrian re-identification method and a re-identification system. The pedestrian re-identification method comprises the steps:1, constructing a training sample set; 2, constructing a fine-grained feature extraction network and a coarse-grained feature extraction network; 3, training the fine-grained feature extraction network and the coarse-grained feature extraction network by adopting the training sample set to obtain a trained network; 4, respectively inputting a to-be-identified IR image into the fine-grained featureextraction network and the coarse-grained feature extraction network; and extracting fine-grained features and coarse-grained features of the to-be-identified image, fusing the extracted features toobtain a fused feature Ftest, obtaining the probability that pedestrians in the to-be-identified image belong to each category, and selecting the pedestrian category with the maximum probability valueas an identification result. According to the method, fine-grained features of small regions of an image and global coarse-grained features are combined to obtain more discriminative fusion featuresfor pedestrian classification and recognition.

Description

technical field [0001] The invention belongs to the technical field of pedestrian re-identification, and in particular relates to a method and system for re-identifying pedestrians in an image under an infrared light mode. Background technique [0002] Pedestrian re-identification aims to use computer vision technology to determine whether there is a specified detection pedestrian in the images or video sequences captured by different cameras in the non-overlapping field of view. Due to the increasing demand for public safety and the popularity of video networks, the research on person re-identification has received extensive attention in recent years. In the research in recent years, most researchers focus on the recognition problem in the field of visible light (RGB), that is, in the visible light range image, given a picture or video sequence, to find whether there is an image in the image library or video library Images or videos of the same object as in a given image o...

AI Technical Summary

Problems solved by technology

The above methods have improved the accuracy of pedestrian re-identification to a certain extent, but there are still deficiencies. The reason for these deficiencies mainly comes from "cross-modality", that is, there are inter-modal differences between RGB and IR modalities. Intra-modal difference

Images