Learning Motion Constraint-Based Spatio-Temporal Networks for Infrared Dim Target Detections

doi:10.3390/app122211519

	Learning Motion Constraint-Based Spatio-Temporal Networks for Infrared Dim Target Detections
	Li, Jie 1,2; Liu, Pengxi 1; Huang, Xiayang 1; Cui, Wennan 1; Zhang, Tao1,2,3
	2022-11-01
发表期刊	APPLIED SCIENCES-BASEL (IF:2.5[JCR-2023],2.7[5-Year])
EISSN	2076-3417
卷号	12 期号:22
发表状态	已发表
DOI	10.3390/app122211519
摘要	Efficient infrared dim object detection has been challenged by low signal-to-noise ratios (SNRs). Traditional methods rely on the gradient difference and fixed-parameter model. These methods fail to adapt to sophisticated and variable situations in the real world. To tackle the issue, a deep learning method based on the spatio-temporal network is proposed in this paper. The model is established by the Convolutional Long Short-Term Memory cell (Conv-LSTM) and the 3D Convolution cell (3D-Conv). It is trained to learn the motion constraint of moving targets (spatio-temporal constraint module, called STM) and to fuse the multiscale local feature between the target and background (deep spatial features module, called DFM). In addition, a variable interval search module (state-aware module, called STAM) is added to the inference. The submodule decides to conduct a global search for images only if the target is lost due to fast motion, uncertain obstruction, and frame loss. Comprehensive experiments indicate that the proposed method achieves better performance over all baseline methods. On the mid-wave infrared datasets collected by the authors, the proposed method achieves a 95.87% detection rate. The SNR of the dataset is around 1-3 dB, and the background of the sequence includes sky, asphalt road, and buildings.
关键词	infrared image sequence dim target detection spatio-temporal constraint multiscale feature fusion deep learning
URL	查看原文
收录类别	SCI
语种	英语
资助项目	National Defense Key Laboratory of Science and Technology of Chinese Academy of Sciences[CXJJ-21S030]
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
WOS类目	Chemistry, Multidisciplinary ; Engineering, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号	WOS:000887134900001
出版者	MDPI
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/256384
专题	信息科学与技术学院_特聘教授组_张涛组
通讯作者	Cui, Wennan; Zhang, Tao
作者单位	1.Chinese Acad Sci, Shanghai Inst Tech Phys, Key Lab Intelligent Infrared Percept, Shanghai 200083, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Shanghai Tech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
通讯作者单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Li, Jie,Liu, Pengxi,Huang, Xiayang,et al. Learning Motion Constraint-Based Spatio-Temporal Networks for Infrared Dim Target Detections[J]. APPLIED SCIENCES-BASEL,2022,12(22).
APA	Li, Jie,Liu, Pengxi,Huang, Xiayang,Cui, Wennan,&Zhang, Tao.(2022).Learning Motion Constraint-Based Spatio-Temporal Networks for Infrared Dim Target Detections.APPLIED SCIENCES-BASEL,12(22).
MLA	Li, Jie,et al."Learning Motion Constraint-Based Spatio-Temporal Networks for Infrared Dim Target Detections".APPLIED SCIENCES-BASEL 12.22(2022).