Cross-mode pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism

A technology for pedestrian re-identification and attention mechanism, which is applied in the field of cross-modal pedestrian re-identification methods and systems, and can solve problems such as difficulty in identification and difficulty in measuring sample similarity across modalities.

Active Publication Date: 2019-05-31
中科人工智能创新技术研究院(青岛)有限公司
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventor found in the research that the difficulty of pedestrian re-identification technology is: the heterogeneity between samples of different modalities brings great difficulties to measure the similarity of samples across modalities; at the same time, because all pictures belong to the same Pedestrian categories, and the corresponding descriptions of different pedestrians are relatively similar, it is difficult to accurately identify

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cross-mode pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism
  • Cross-mode pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism
  • Cross-mode pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0069] It should be noted that the terminology used herein is only for describing specific embodiments, and is not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and / or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and / or combinations thereof.

[0070] In a typical implementation of the present disclosure, such as figure 1 As shown, a cross-modal pedestrian re-identific...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a cross-modal pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism, and the method comprises the steps: extracting pedestrianimage features and text description features, and enabling the pedestrian image features and the text description features to serve as initial global features of a pedestrian image channel and a textdescription channel; Establishing a heterogeneous hierarchical attention model, and enhancing pedestrian picture features and text description features by using a bidirectional cross-mode fine-grained matching attention mechanism and a context-guided local feature aggregation attention mechanism by the model; A heterogeneous hierarchical attention model is trained in a two-stage training mode, preliminary training is carried out in the first stage by utilizing pedestrian category supervision information, training in the second stage is carried out by utilizing cross-modal samples to match thepedestrian category supervision information on the basis, and pedestrian re-identification is carried out by utilizing the trained model. The pedestrian re-identification method and device can improve the accuracy of pedestrian re-identification.

Description

technical field [0001] The present disclosure relates to the technical fields of computer vision, pattern recognition and multimodal computing, in particular to a cross-modal pedestrian re-identification method and system based on a heterogeneous hierarchical attention mechanism. Background technique [0002] Pedestrian re-identification is an important and challenging classic computer vision task, which has a wide range of applications in security monitoring, intelligent video analysis, personnel search and rescue retrieval and other fields. [0003] The cross-modal person re-identification method based on text description has the characteristics of easy generation of description and the ability to provide relatively rich information for retrieval. [0004] The inventor found in the research that the difficulty of pedestrian re-identification technology is: the heterogeneity between samples of different modalities brings great difficulties to measure the similarity of sampl...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06F17/27G06N3/04G06N3/08
Inventor 王亮黄岩牛凯王海滨李凯
Owner 中科人工智能创新技术研究院(青岛)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap