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

林两魁; 王少游; 唐忠兴

doi:doi:10.11972/j.issn.1001-9014.2018.02.015

红外与毫米波学报, 2018, 37 (2): 219, 网络出版: 2018-05-29

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

论文大纲

林两魁王少游唐忠兴

作者单位

上海卫星工程研究所, 上海 201109

摘要

针对红外过采样扫描成像特点,提出一种基于深度卷积神经网络的红外点目标检测方法.首先,设计回归型深度卷积神经网络以抑制扫描图像杂波背景,该网络不含池化层,输出的背景抑制图像尺寸与输入图像一致；其次,对抑制后的图像进行门限检测,提取候选目标小区域原始数据；最后,将候选目标区域数据依次输入分类型深度卷积神经网络以进一步判别目标、剔除虚警.生成大量过采样训练数据有效训练两个深度网络.结果表明,在不同杂波背景下,该方法在目标信杂比增益、检测概率、虚警概率和运算时间等方面,均优于典型红外小目标检测方法,适用于红外过采样扫描系统的点目标检测.

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 network 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-suppression image is tested and the original data of candidate target region is extracted. Finally, the candidate target area raw data is input into the classification-type DCNN to further identify the target and remove 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 clutter 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 system.

参考文献

[1] Latry C, Rouge B. In-flight commissioning of SPOT5 the quincunx sampling mode[C]. Proceedings of SPIE, 2003, 4881:189-199.

[2] Larsen M F, Tansock Jr J J., Sorenson G, et al. Impact of the SPIRIT III sensor design on algorithm for background removal, object detection, and point source extraction[J]. Proceedings of SPIE, 1996, 2759:194-204.

[3] Lomheim T S, Milne E L, Kwok Lt J D, et al. Performance/sizing relationships for a short-wave/mid-wave infrared scanning point-source detection space sensor[C]. Proceedings of IEEE Aerospace Conference, 1999:113-138.

[4] Lawrie D G, Lomheim T S. Advanced electro-optical space-based systems for missile surveillance[R]. Aerospace Report, TR-2001(8556)-1,2011.

[5] WANG Shi-Tao, ZHANG Wei, JIN Li-Hua,et al.. Point target detection based on temporal-spatial over-sampling system[J]. J. Infrared Millim. Waves(王世涛,张伟,金丽花,等.基于时－空过采样系统的点目标检测性能分析.红外与毫米波学报),2013,32(1):68-72.

[6] LIN Liang-Kui, WANG Shao-You, WANG Tie-Bing. Simulation and analysis of point target detection performance for infrared scanning over-sampling system[J]. Acta Optica Sinica(林两魁,王少游,王铁兵. 红外扫描过采样系统点目标检测性能分析与仿真. 光学学报), 2016,36(5):0528001.

[7] WANG Tie-Bing, LI Miao, LIN Zai-Ping,et al. Compara-tive performance analysis of over-sampling scanning[J]. J. Infrared Millim. Waves(王铁兵,李淼,林再平,等.过采样扫描探测性能对比分析. 红外与毫米波学报), 2015,34(1):87-91.

[8] Tartakovsky A G, Brown J. Adaptive spatial-temporal filtering methods for clutter removal and target tracking[J]. IEEE Transactions on aerospace and electronic systems, 2008, 44(4):1522-1537.

[9] Gao C Q, Meng D Y, Yang Y, et al. Infrared patch-image model for small target detection in a single image[J]. IEEE Transactions on Image Processing, 2013, 22(12):4996-5009.

[10] Deshpande. Max-mean and max-median filters for detection of small targets[J]. Proc. SPIE, 1999, 3809:74-83.

[11] Tom V T, Peli T, Leung M, et al. Morphology-based algorithm for point target detection in infrared backgrounds[J]. Proc. SPIE, 1993, 1954:25-32.

[12] Gao Y, Liu R M, Yang J. Small target detection using two-dimensional least mean square (TDLMS) filter based on neighborhood analysis[J]. International Journal of Infrared and Millimeter Waves, 2008, 29(2):188-200.

[13] WANG Da-Bao,LIU Shang-Qian,KOU Xiao-Ming,et al.Infrared background clutter suppression algor ithm of adaptive regular ization based on MRF[J]. J. Infrared Millim. Waves(汪大宝,刘上乾,寇小明,等.基于MRF的自适应正则化红外背景杂波抑制算法.红外与毫米波学报), 2009,28(6):440-444.

[14] Zheng C Y, Li H. Small infrared target detection based on low-rank and sparse matrix decomposition[J]. Applied Mechanics and Materials, 2013, 239-240: 214-218.

[15] Li L, Li H, Li T,et al. Infrared small target detection in compressive domain[J]. Electronics Letters, 2014, 50(7):510-512.

[16] ZHAO Jia-Jia,TANG Zheng-Yuan,YANG Jie,et al, Infrared small target detection based on image sparse representation [J]. J. Infrared Millim. Waves,(赵佳佳,唐峥远,杨杰,等. 基于图像稀疏表示的红外小目标检测算法. 红外与毫米波学报), 2011,30(2):156-166.

[17] Girshick R, Donahue J, Darrell T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016,38(1):142-158.

[18] Girshick R. Fast R-CNN[C]. Computer vision and pattern recognition, 2015.

[19] Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.

[20] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]. CVPR,2016.

[21] Goodfellow I, Bengio Y, Courville A. Deep Learning [M]. The MIT Press,2016.

[22] Vedaldi A, Lenc K, Gupta A. MatConvNet convolutional neural networks[EB/OL].http://www.vlfeat.org/matconvnet/matconvnet-manual.pdf,2017.

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. LIN Liang-Kui, WANG Shao-You, TANG Zhong-Xing. Point target detection in infrared over-sampling scanning images using deep convolutional neural networks[J]. Journal of Infrared and Millimeter Waves, 2018, 37(2): 219.

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

关于本站 Cookie 的使用提示

全站搜索

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

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索