Point target detection based on deep spatial-temporal convolution neural network
Received:January 10, 2020  Revised:January 08, 2021  download
Citation:
Hits: 796
Download times: 250
Author NameAffiliationE-mail
LI Miao College of electronic science and technology, National University of Defense Technology, Changsha 410000, China lm8866@nudt.edu.cn 
Lin Zai-Ping College of electronic science and technology, National University of Defense Technology, Changsha 410000, China  
FAN Jian-Peng College of electronic science and technology, National University of Defense Technology, Changsha 410000, China  
SHENG Wei-Dong College of electronic science and technology, National University of Defense Technology, Changsha 410000, China  
LI Jun College of electronic science and technology, National University of Defense Technology, Changsha 410000, China  
AN Wei College of electronic science and technology, National University of Defense Technology, Changsha 410000, China  
LI Xin-Lei The Xian Chinese Space Tracking Control Center, Xian, Shanxi 710000, China  
Abstract:Point target detection in Infrared Search and Track (IRST) is a challenging task, due to less information. Traditional methods based on hand-crafted features are hard to finish detection intelligently. A novel deep spatial-temporal convolution neural network is proposed to suppress background and detect point targets. The proposed method is realized based on fully convolution network. So input of arbitrary size can be put into the network and correspondingly-sized output can be obtained. In order to meet the requirement of real time for practical application, the factorized technique is adopted. 3D convolution is decomposed into 2D convolution and 1D convolution, and it leads to signi?cantly less computation. Multi-weighted loss function is designed according to the relation between prediction error and detection performance for point target. Number-balance weight and intensity-balance weight are introduced to deal with the imbalanced sample distribution and imbalanced error distribution. The experimental results show that the proposed method can effectively suppress background clutters, and detect point targets with less runtime.
keywords:point target detection  infrared search and track (IRST)  background suppression  convolution neural network (CNN)  spatial-temporal detection
View Full Text  HTML  View/Add Comment  Download reader

Copyright:《Journal of Infrared And Millimeter Waves》