Pedestrian re-identification method and device based on multi-fine-grained features, and storage medium

The invention provides a pedestrian re-identification method and device based on multi-fine-grained features and a storage medium, and the method comprises the following steps: obtaining pedestrian images which at least comprise a target pedestrian image and a to-be-identified image; inputting image...

Full description

Saved in:
Bibliographic Details
Main Author XIE XILIN
Format Patent
LanguageChinese
English
Published 13.12.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention provides a pedestrian re-identification method and device based on multi-fine-grained features and a storage medium, and the method comprises the following steps: obtaining pedestrian images which at least comprise a target pedestrian image and a to-be-identified image; inputting images to be recognized into the trained pedestrian trunk part detection network model for feature extraction to obtain global features of the images to be recognized and fine-grained features of pedestrian trunk part partitions of multiple layers of the images to be recognized; performing weighted fusion on the global features of the image to be recognized and the fine-grained features of the multiple layers of pedestrian trunk part partitions to obtain pedestrian re-recognition features of the image to be recognized; and performing similarity calculation on the pedestrian re-identification features of the to-be-identified image and the pedestrian re-identification features of the target pedestrian image to determine a
Bibliography:Application Number: CN202211043447