Multi‐receptive field graph convolutional neural networks for pedestrian detection. Issue 9 (20th May 2019)

• Record Type: Journal Article
• Authors: Shen, Chao; Zhao, Xiangmo; Fan, Xing; Lian, Xinyu; Zhang, Fan; Kreidieh, Abdul Rahman; Liu, Zhanwen
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 9(2019)
• Page Start: 1319
• Page End: 1328
• Publication Date: 2019-05-20
• Subjects: object detection -- image recognition -- pedestrians -- learning (artificial intelligence) -- convolutional neural nets -- graph theory; authors design -- multireceptive pooling pyramid module -- body parts graphs -- learned convolutional neural networks features -- graph CNN -- public pedestrian detection datasets -- multireceptive field graph convolutional neural networks -- general object detection -- deep learning -- pedestrian detection task -- pedestrian detection performance -- multireceptive field‐based framework -- single‐shot pedestrian detection; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5618
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Although great progress has been achieved for general object detection with the advent of deep learning, there are still several limitations when applied to pedestrian detection task. In this article, the authors mainly consider the following three problems. (i) most deep learning‐based methods are time‐consuming and require large storage space, making them unsuitable for real‐world applications; (ii) the scale of person varies greatly, which decreases the pedestrian detection performance; (iii) as pedestrians may be occluded by vehicles or other persons, it makes pedestrian detection more challenging. In response to these limitations, this article proposes a multi‐receptive field‐based framework for single‐shot pedestrian detection. Authors' contributions can be summarised as follows. First, to reduce the computational complexity of the detector, the authors design the multi‐receptive pooling pyramid module, which reduces the computation cost of the detector and improves its performance. Next, body parts graphs are built on the learned convolutional neural networks (CNN) features, and a graph CNN is used to mine the relationships of the graph nodes. Finally, experiments are conducted on two public pedestrian detection datasets to demonstrate the effectiveness of the proposed method.