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...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | Chinese English |
Published |
13.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |