Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors

doi:10.3390/s24196350

	Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors
	Tang, Shuyuan 1,2,3,4; Zhou, Yiqing 1,2,3,4; Li, Jintao 1,2,3,4; Liu, Chang 1,2,4; Shi, Jinglin 1,2,3,4
	2024-10-01
发表期刊	SENSORS
卷号	24 期号:19 页码:21
摘要	Occlusion presents a major obstacle in the development of pedestrian detection technologies utilizing computer vision. This challenge includes both inter-class occlusion caused by environmental objects obscuring pedestrians, and intra-class occlusion resulting from interactions between pedestrians. In complex and variable urban settings, these compounded occlusion patterns critically limit the efficacy of both one-stage and two-stage pedestrian detectors, leading to suboptimal detection performance. To address this, we introduce a novel architecture termed the Attention-Guided Feature Enhancement Network (AGFEN), designed within the deep convolutional neural network framework. AGFEN improves the semantic information of high-level features by mapping it onto low-level feature details through sampling, creating an effect comparable to mask modulation. This technique enhances both channel-level and spatial-level features concurrently without incurring additional annotation costs. Furthermore, we transition from a traditional one-to-one correspondence between proposals and predictions to a one-to-multiple paradigm, facilitating non-maximum suppression using the prediction set as the fundamental unit. Additionally, we integrate these methodologies by aggregating local features between regions of interest (RoI) through the reuse of classification weights, effectively mitigating false positives. Our experimental evaluations on three widely used datasets demonstrate that AGFEN achieves a 2.38% improvement over the baseline detector on the CrowdHuman dataset, underscoring its effectiveness and potential for advancing pedestrian detection technologies.
关键词	pedestrian detection computer vision attention-guided feature enhancement convolutional neural network
DOI	10.3390/s24196350
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan ; [2022YFC3320801-2]
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:001332816800001
出版者	MDPI
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39532
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tang, Shuyuan
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tang, Shuyuan,Zhou, Yiqing,Li, Jintao,et al. Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors[J]. SENSORS,2024,24(19):21.
APA	Tang, Shuyuan,Zhou, Yiqing,Li, Jintao,Liu, Chang,&Shi, Jinglin.(2024).Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors.SENSORS,24(19),21.
MLA	Tang, Shuyuan,et al."Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors".SENSORS 24.19(2024):21.