Correlation-and-Correction Fusion Attention Network for Occluded Pedestrian Detection

As a significant issue in computer vision, pedestrian detection has achieved certain achievements with the support of deep learning. However, pedestrian detection in congested scenes still encounters the challenging problem of feature loss and obfuscation. To address the issue, we propose a pedestri...

Full description

Saved in:
Bibliographic Details
Published inIEEE sensors journal Vol. 23; no. 6; p. 1
Main Authors Zou, Fengmin, Li, Xu, Xu, Qimin, Sun, Zhengliang, Zhu, Jianxiao
Format Journal Article
LanguageEnglish
Published New York IEEE 15.03.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Attention mechanism
Computer vision
Correlation
crowded scenes
Datasets
Detectors
feature enhancement
Feature extraction
Fuses
fusion
Head
Masks
Modules
Occlusion
pedestrian detection
Pedestrians
Proposals
Sensors
Online AccessGet full text

Cover

More Information
Summary:As a significant issue in computer vision, pedestrian detection has achieved certain achievements with the support of deep learning. However, pedestrian detection in congested scenes still encounters the challenging problem of feature loss and obfuscation. To address the issue, we propose a pedestrian detection network based on a correlation-and-correction fusion attention mechanism. First, a multi-mask correction attention module is proposed, which generates visible part masks of pedestrians, enhancing the visible region's features and correcting the false one. Besides, the module preserves the features of multi-class pedestrians by generating multiple masks. Then, we fuse a correlation channel attention module to enhance the correlation of various pedestrians' body features. Next, we studied three fusion methods of correlation and correction attention mechanisms and found that the serial connection of "correlation first and correction behind" works best. Finally, we extend our method to multi-class pedestrian detection in congested scenes. Experimental results on the CityPersons, Caltech and CrowdHuman datasets demonstrate the effectiveness of our method. On the CityPersons dataset where more than 70% of pedestrians are occluded, our method outperforms the baseline method by 1.12% on the heavy occlusion subset and surpasses many outstanding methods.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2023.3242082