红外与毫米波学报2021，Vol.40Issue(1)：122-132,11.DOI:10.11972/j.issn.1001-9014.2021.01.017
基于深度时空卷积神经网络的点目标检测
Point target detection based on deep spatial-temporal convolution neural network
摘要
Abstract
Point target detection in Infrared Search and Track(IRST)is a challenging task. due to less informa-tion. 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 pro-posed method is realized based on fully convolution network. So input of arbitrary size can be put into the net-work 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 con-volution,and it leads to significantly 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.关键词
点目标检测/红外搜索与跟踪(IRST)/背景抑制/卷积神经网络(CNN)/时空检测Key words
point target detection/infrared search and track (IRST)/background suppression/convolutionneural network(CNN)/spatial-temporal detection分类
信息技术与安全科学引用本文复制引用
李淼,林再平,樊建鹏,盛卫东,李骏,安玮,李昕磊..基于深度时空卷积神经网络的点目标检测[J].红外与毫米波学报,2021,40(1):122-132,11.基金项目
Supported by the National Natural Science Foundation of China(61921001) （61921001）
