Weakly Aligned Feature Fusion for Multimodal Object Detection

doi:10.1109/TNNLS.2021.3105143

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Weakly Aligned Feature Fusion for Multimodal Object Detection
	Zhang, Lu1,2 ; Liu, Zhiyong1,2,3 ; Zhu, Xiangyu2,4,5 ; Song, Zhan 6; Yang, Xu1,2,3 ; Lei, Zhen2,4,5,7 ; Qiao, Hong1,2
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2021-08-25
页码	15
通讯作者	Liu, Zhiyong(zhiyong.liu@ia.ac.cn)
摘要	To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem. First, a region feature (RF) alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal RFs. Second, we propose a novel region of interest (RoI) jitter strategy to improve the robustness to unexpected shift patterns. Third, we present a new multimodal feature fusion method that selects the more reliable feature and suppresses the less useful one via feature reweighting. In addition, by locating bounding boxes in both modalities and building their relationships, we provide novel multimodal labeling named KAIST-Paired. Extensive experiments on 2-D and 3-D object detection, RGB-T, and RGB-D datasets demonstrate the effectiveness and robustness of our method.
关键词	Object detection Feature extraction Detectors Robustness Cameras Automation Training Deep learning feature fusion multimodal object detection pedestrian detection
DOI	10.1109/TNNLS.2021.3105143
关键词[WOS]	MULTISPECTRAL PEDESTRIAN DETECTION ; DEEP NEURAL-NETWORKS ; ACCURATE
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100] ; Beijing Science and Technology Plan Project[Z201100008320029] ; NSFC[61627808] ; NSFC[61876178] ; NSFC[61806196] ; Dongguan Core Technology Research Frontier Project, China[2019622101001]
项目资助者	National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Academy of Science ; Beijing Science and Technology Plan Project ; NSFC ; Dongguan Core Technology Research Frontier Project, China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000732172000001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	多模态智能
引用统计	被引频次：38[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46873
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Liu, Zhiyong
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100086, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 4.Chinese Acad Sci, Ctr Biometr & Secur Res, Inst Automat, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Guangdong, Peoples R China 7.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Lu,Liu, Zhiyong,Zhu, Xiangyu,et al. Weakly Aligned Feature Fusion for Multimodal Object Detection[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:15.
APA	Zhang, Lu.,Liu, Zhiyong.,Zhu, Xiangyu.,Song, Zhan.,Yang, Xu.,...&Qiao, Hong.(2021).Weakly Aligned Feature Fusion for Multimodal Object Detection.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15.
MLA	Zhang, Lu,et al."Weakly Aligned Feature Fusion for Multimodal Object Detection".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):15.