A Dynamic Part-Attention Model for Person Re-Identification

Autor: Xinkai Wu, Yao Ziying, Ma Yalong, Zhongxia Xiong
Rok vydání: 2019
Předmět:
Computer science
media_common.quotation_subject
Video Recording
convolutional neural network
02 engineering and technology
lcsh:Chemical technology
Machine learning
computer.software_genre
Biochemistry
Convolutional neural network
Article
Analytical Chemistry
Image (mathematics)
Discriminative model
Image Processing
Computer-Assisted
0202 electrical engineering
electronic engineering
information engineering
Humans
lcsh:TP1-1185
Electrical and Electronic Engineering
Function (engineering)
attention parts
Instrumentation
Pedestrians
media_common
person re-identification
business.industry
cross cameras
Atomic and Molecular Physics
and Optics
Variable (computer science)
Feature (computer vision)
Biometric Identification
020201 artificial intelligence & image processing
Neural Networks
Computer
Artificial intelligence
Focus (optics)
business
dynamic combination
computer
Algorithms
Zdroj: Sensors, Vol 19, Iss 9, p 2080 (2019)
Sensors (Basel, Switzerland)
Sensors
Volume 19
Issue 9
ISSN: 1424-8220
Popis: Person re-identification (ReID) is gaining more attention due to its important applications in pedestrian tracking and security prevention. Recently developed part-based methods have proven beneficial for stronger and explicit feature descriptions, but how to find real significant parts and reduce miscorrelation between images to improve accuracy of ReID still leaves much room to improve. In this paper, we propose a dynamic part-attention (DPA) method based on masks, which aims to improve the use of variable attention parts. Particularly, a two-branch network with a dynamic loss function is designed to extract features of the global image and the parts of the body separately. With the comprehensive but targeting learning strategy, the proposed method can capture discriminative features based, but not depending on, masks, which guides the whole network to focus on body features more consciously and achieves more robust performance. Our method achieves rank-1 accuracy of 91.68% on public dataset Market1501, and experimental results on three public datasets indicate that the proposed method is effective and achieves favorable accuracy when compared with the state-of-the-art methods.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje