基于奇异值分解和叠加法的慢速小目标检测算法

摘要/Abstract

摘要：

摘要：在图像集同一像素位置噪声满足遍历性的条件下，分析了利用叠加法进行目标检测的可行性，在此基础上提出了一种基于叠加法的慢速小目标检测算法.首先，分析了目标不重叠、完全重叠和部分重叠时，目标合成图像和噪声合成图像的能量变化情况，分析表明随着叠加次数的增加，噪声合成图像的能量衰减快于目标合成图像，从而保证了合成图像中目标与噪声能量比的增加，为利用叠加法进行目标检测提供了可行性.其次，根据合成图像的奇异值特性，利用标准化奇异值的不均匀变化完成了目标检测.同时，仿真验证了目标合成图像和噪声合成图像的能量衰减情况，分析了叠加次数、目标尺寸与强度对目标可检测性的影响.

关键词: 奇异值分解, 叠加法, 目标检测

Abstract:

Abstract： In the case of the measurement noises obtained from the same pixel position in a set of images which are ergodic, the feasibility of superposition method for target detection was analyzed, based on which, a superposition-based lowspeed small target detection algorithm was proposed. First, the energy variation of the target synthesis images and the noise synthesis images were analysized, when the targets were non-overlapped, completely overlapped and partially overlapped. The analysis shows that with the increase in the superimposed number, the energy of the noise synthesis images is attenuated faster than that of the target synthesis images, thus ensuring an increase in the ratio of target to noise in synthesis images. Second, depending on the characteristics of singular values of the synthesis images, the uneven variations of the standardized singular values were used for target detection. The simulation verifies the attenuation of the target energy and noise energy of the synthesis images, and analyzes the impact of superimposed number， target size and strength on target detectability.

Key words: singular value decomposition (SVD), superposition, object detection

中图分类号:

TP 391

高敬礼1，文成林2，刘妹琴1. 基于奇异值分解和叠加法的慢速小目标检测算法[J]. 上海交通大学学报（自然版）, 2015, 49(06): 876-883.

GAO Jingli1，WEN Chenglin2，LIU Meiqin1. Low-Speed Small Target Detection Based on SVD and Superposition[J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 876-883.

参考文献

［1］张建伟, 郭会明. 低空慢速小目标拦截系统研究［J］. 计算机工程与设计, 2012, 33(7): 28742878.

Jianwei Z, Huiming G. Net cast interception system research aimed at low small slow target［J］. Computer Engineering and Design, 2012, 33(7):28742878.

［2］王忠, 马妍, 王莲荣. 防空作战中低慢小目标威胁度评估［J］. 舰船电子对抗, 2013, 36(6): 103105.

WANG Zhong, MA Yan, WANG Lianrong. Assessment of threat degree for LSS target in air defense operation［J］. Shipboard Electronic Countermeasure, 2013.

［3］Li Z Z, Chen J, Hou Q, et al. Sparse representation for infrared dim target detection via a discriminative overcomplete dictionary learned online［J］. Sensors, 2014, 14(6): 94519470.

［4］Zhao J, Liu F, Mo B. An algorithm of dim and small target detection based on wavelet transform and image fusion［C］∥2012 Fifth International Symposium on Computational Intelligence and Design (ISCID). USA: IEEE, 2012, 2: 4345.

［5］臧传吉, 李桂祥, 王宇翔. 基于形态学方法的红外小目标检测［J］. 空军预警学院学报, 2012(2):9497.

ZANG Chuanji,LI Guixiang,WANG Yuxiang. Infrared dim target detection using morphology based method［J］. Journal of Air Force Radar Academy, 2012,26(2):9497.

［6］Gao J L, Wen C L, Liu M Q. steel surface defect detection and localization based on SVD and twoside compressive measurements［C］∥26th Chinese Control and Decision Conference. USA: IEEE, 2014: 14011406.

［7］Lu C J, Tsai D M. Automatic defect inspection for LCDs using singular value decomposition［J］. The International Journal of Advanced Manufacturing Technology, 2005, 25(12): 5361.

［8］Reed I S, Gagliardi R M, Stotts L B. Optical moving target detection with 3D matched filtering［J］. IEEE Transactions on Aerospace and Electronic Systems, 1988, 24(4): 327336.

［9］Blostein S D, Huang T S. Detecting small, moving objects in image sequences using sequential hypothesis testing［J］. IEEE Transactions on Signal Processing, 1991, 39(7): 16111629.

［10］Arnold J, Shaw S W, Pasternack H. Efficient target tracking using dynamic programming［J］. IEEE Transactions on Aerospace and Electronic Systems, 1993, 29(1): 4456.

［11］Falconer D G. Target tracking with the Hough transform［C］∥1977 11th Asilomar Conference on Circuits, Systems and Computers. USA: IEEE, 1977: 249252.

［12］Gao J L, Wen C L, Liu M Q. SVDbased scattered small targets detection［C］∥2014 International Conference on Multisensor Fusion and Information Integration for Intelligent Systems (MFI). USA: IEEE, 2014: 16.

［13］Petrou M, Petrou C. Image processing: The fundamentals［M］. Second Edition. United Kingdom: John Wiley and Sons, 2010.

[1]	. 用于内窥镜图像息肉检测的实时轻量级卷积神经网络[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 521-534.
[2]	薛昂, 姜恩宇, 张文涛, 林顺富, 米阳. 基于窗口自注意力网络与YOLOv5融合的输电线路通道异物检测[J]. 上海交通大学学报, 2025, 59(3): 413-423.
[3]	王一力, 李强, 沈俊逸, 杨翊东, 王琦. 多模态舰船图像生成及其关键部位检测[J]. 空天防御, 2025, 8(1): 77-85.
[4]	李楚晨, 唐善军, 赵冰青. 一种基于无人机探测图像区块信息的弱小目标检测算法[J]. 空天防御, 2025, 8(1): 41-47.
[5]	刘婧, 郭晓雷, 张欣海, 毛靖军, 吕瑞恒. 空面导弹轻量化空中斜框目标检测算法[J]. 空天防御, 2024, 7(4): 106-113.
[6]	张彦军1,4,5,6,7, 王碧云2,3 , 蔡云泽1,4,5,6,7. 基于注意力的多通道网络红外弱小目标检测[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 414-427.
[7]	章涛, 张雪瑞, 陈勇, 钟科林, 罗其俊. 面向民机可视导航的场面多尺度目标检测[J]. 上海交通大学学报, 2024, 58(11): 1816-1825.
[8]	牛国臣, 孙翔宇, 苑峥岩. 基于双流特征提取的车路协同感知方法[J]. 上海交通大学学报, 2024, 58(11): 1826-1834.
[9]	王建园, 陈小彤, 张越, 孙俊格, 石东浩, 陈金宝. 无人机多模态融合的城市目标检测算法[J]. 空天防御, 2024, 7(1): 32-39.
[10]	张晓宇, 杜祥润, 张佳梁, 檀盼龙, 杨诗博. 基于Deformable DETR的红外图像目标检测方法研究[J]. 空天防御, 2024, 7(1): 16-23.
[11]	武星, 张庆丰, 王健嘉, 姚骏峰, 郭毅可, . 基于多重检测模型融合框架的印刷电路板缺陷检测[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(6): 717-727.
[12]	蒋瑞民, 王宣灵, 张明恩, 赵斌. 基于量子遗传算法的反舰导弹航路规划方法[J]. 空天防御, 2023, 6(4): 31-34.
[13]	. 基于多视角道路相机的时空关联三维车辆检测与跟踪系统[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(1): 52-60.
[14]	魏志飞, 宋泉宏, 李芳, 杨擎宇, 王爱华. 基于神经网络模型压缩技术的目标检测算法研究[J]. 空天防御, 2021, 4(4): 107-112.
[15]	邱忠宇, 赵文龙, 高文, 潘洪涛, 史冉东. 动态视觉传感器的目标检测算法对比分析[J]. 空天防御, 2021, 4(4): 101-106.