红外与毫米波学报2018，Vol.37Issue(2)：219-226,8.DOI:10.11972/j.issn.1001-9014.2018.02.015
基于深度卷积神经网络的红外过采样扫描图像点目标检测方法
Point target detection in infrared over-sampling scanning images using deep convolutional neural networks
摘要
Abstract
Aiming at the characteristics of infrared over-sampling scanning imaging, an infrared point target detection method based on DCNN(Deep Convolution Neural Network)is proposed.Firstly, a regressive-type DCNN is designed to suppress the background clutter of the scanning image.The net-work does not contain any pooling layer,so can input the original image of any size,with the size of output image after clutter suppression in accordance with the input image.Subsequently,the post-sup-pression image is tested and the original data of candidate target region is extracted.Finally,the candi-date target area raw data is input into the classification-type DCNN to further identify the target and re-move the false alarm.Meanwhile,a large number of training data of infrared over-sampling scanning images are designed,and two networks are trained effectively.The experimental results show that the proposed method is superior to multiple typical infrared small target detection methods in the target clut-ter ratio gain, detection probability, false alarm probability and running time under different clutter backgrounds,and is applicable to the point target detection of the infrared oversampling scanning sys-tem.关键词
模式识别与智能系统/点目标检测/卷积神经网络/红外过采样扫描/深度学习Key words
pattern recognition and intelligent systems/point target detection/convolution neural net-work/infrared over-sampling scanning/deep learning分类
信息技术与安全科学引用本文复制引用
林两魁,王少游,唐忠兴..基于深度卷积神经网络的红外过采样扫描图像点目标检测方法[J].红外与毫米波学报,2018,37(2):219-226,8.基金项目
国家重点研发计划(2016YFB0500801)Supported by National Key Research and Development Program of China （2016YFB0500801）
