基于检测与跟踪相互迭代的极暗弱目标搜索算法

doi:10.11772/j.issn.1001-9081.2020122000

计算机应用 ›› 2021, Vol. 41 ›› Issue (10): 3017-3024.DOI: 10.11772/j.issn.1001-9081.2020122000

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

基于检测与跟踪相互迭代的极暗弱目标搜索算法

効琦^1,2,3, 尹增山^1,2,3, 高爽¹

1. 中国科学院微小卫星创新研究院, 上海 201203;
2. 上海科技大学信息科学与技术学院, 上海 201210;
3. 中国科学院大学, 北京 100049

收稿日期:2020-12-18 修回日期:2021-04-21 出版日期:2021-10-10 发布日期:2021-10-27
通讯作者: 尹增山
作者简介:効琦(1995-),男,甘肃定西人,硕士研究生,主要研究方向:遥感图像处理、视频目标检测;尹增山(1971-),男,山东平度人,研究员,博士,主要研究方向:图像信息处理、遥感技术、卫星网络;高爽(1986-),女,山东青岛人,副研究员,博士,主要研究方向:遥感图像处理、微纳卫星系统。
基金资助:
中国科学院国防科技创新重点部署项目（KGFZD-135-20-03）。

Extremely dim target search algorithm based on detection and tracking mutual iteration

XIAO Qi^1,2,3, YIN Zengshan^1,2,3, GAO Shuang¹

1. Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201203, China;
2. School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China;
3. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-12-18 Revised:2021-04-21 Online:2021-10-10 Published:2021-10-27
Supported by:
This work is partially supported by the Key Deployment Project of National Defense Science and Technology Innovation of Chinese Academy of Sciences (KGFZD-135-20-03).

摘要/Abstract

摘要： 针对极低信噪比（LSNR）情况下暗弱运动目标和背景噪声的强度难以区分的问题，提出了一种基于检测与跟踪相互迭代的极暗弱目标搜索算法，总体上采用将时域检测与空域跟踪的过程联合、迭代进行的新型策略。首先，在检测过程中计算检测窗口内信号片段与已经提取的背景估计特征的差别；然后，在跟踪过程中运用动态规划算法保留使得轨迹能量累积最大的轨迹；最后，自适应地调整下一检测过程中被保留轨迹的检测器阈值参数，使该轨迹内的像素能以更宽容的策略被保留到下一检测跟踪阶段。实验测试结果表明，所提算法可以在1%~2%的虚警率和约70%的检测率下探测到低至0 dB的暗弱运动目标。可见该算法可有效改善对LSNR暗弱目标的检测能力。

关键词: 暗弱小目标, 小波包, 核函数, 时空域联合, 检测与跟踪迭代, 动态规划

Abstract: It is difficult to distinguish the intensity between dim moving targets and background noise in the case of extremely Low Signal-to-Noise Ratio (LSNR). In order to solve the problem, a new extremely dim target search algorithm based on detection and tracking mutual iteration was proposed with a new strategy for combining and iterating the process of temporal domain detection and spatial domain tracking. Firstly, the difference between the signal segment in the detection window and the extracted background estimated feature was calculated during the detection process. Then, the dynamic programming algorithm was adopted to remain the trajectories with the largest trajectory energy accumulation in the tracking process. Finally, the threshold parameters of the detector of the remained trajectory were adaptively adjusted in the next detection process, so that the pixels in this trajectory were able to be retained to the next detection and tracking stage with a more tolerant strategy. Experimental results show that, the dim moving targets with SNR as low as 0 dB can be detected by the proposed algorithm, false alarm rate of 1% - 2% and detection rate of about 70%. It can be seen that the detection ability for dim targets with extremely LSNR can be improved effectively by the proposed algorithm.

Key words: dim small target, wavelet packet, kernel function, spatio-temporal domain combination, detection and tracking iteration, dynamic programing

中图分类号:

TP391.9

効琦, 尹增山, 高爽. 基于检测与跟踪相互迭代的极暗弱目标搜索算法[J]. 计算机应用, 2021, 41(10): 3017-3024.

XIAO Qi, YIN Zengshan, GAO Shuang. Extremely dim target search algorithm based on detection and tracking mutual iteration[J]. Journal of Computer Applications, 2021, 41(10): 3017-3024.

参考文献

[1] 黄汉文. 海洋目标天基综合感知技术[J]. 航天电子对抗, 2011, 27(6):11-13, 48.(HUANG H W. Marine target spacebased comprehensive awareness technology[J]. Aerospace Electronic Warfare, 2011, 27(6):11-13, 48.)
[2] 孟庆宇, 张伟, 龙夫年. 天基空间目标可见光相机探测能力分析[J]. 红外与激光工程, 2012, 41(8):2079-2084.(MENG Q Y, ZHANG W, LONG F N. Analysis of detection capability of visible light camera for space-based targets[J]. Infrared and Laser Engineering, 2012, 41(8):2079-2084)
[3] MIRGHASEMI S, SADOGHI YAZDI H, LOTFIZAD M. A targetbased color space for sea target detection[J]. Applied Intelligence, 2012, 36(4):960-978.
[4] 王彩云. 目标检测的研究进展[C]//中国计算机用户协会网络应用分会2019年第23届网络新技术与应用年会论文集. 重庆:《计算机科学》编辑部, 2019:48-51.(WANG C Y. Research progress of target detection[C]//Proceedings of the 2019 23rd Annual Conference of New Network Technology and Application of China Computer Users Association Network Application Branch. Chongqing:Editorial Board of Computer Science, 2019:48-51.)
[5] MENG X Z, XING J P, WANG Y Z, et al. Pedestrian detection using frame differential method and improved HOG feature[J]. Advanced Materials Research, 2012, 461:7-12.
[6] THOTAPALLI P K, VIKRAM KUMAR C R, CHANDRA MOHANA REDDY B. Feature extraction of moving objects using background subtraction technique for robotic applications[J]. International Journal of Intelligent Robotics and Applications, 2021, 5(1):65-78.
[7] 顾晶, 何昇浍. 一种基于形态学滤波的雷达目标检测方法[J]. 计算机与数字工程, 2012, 40(2):112-114.(GU J, HE S H. A method of radar target detection based on morphological filtering[J]. Computer and Digital Engineering, 2012, 40(2):112-114.)
[8] 张寅, 蔡旭阳, 闫钧华, 等. 联合时空信息和轨迹关联的空中多目标检测[J]. 武汉大学学报(信息科学版), 2020, 45(10):1533-1540.(ZHANG Y, CAI X Y, YAN J H, et al. Aerial multitarget detection based on spatial-temporal information and trajectory association[J]. Geomatics and Information Science of Wuhan University, 2020, 45(10):1533-1540.)
[9] 何耀民, 何华锋, 徐永壮, 等. 基于改进小波变换的海上目标检测[J]. 系统工程与电子技术, 2020, 42(1):83-89.(HE Y M, HE H F, XU Y Z, et al. Marine target detection based on improved wavelet transform[J]. Systems Engineering and Electronic Technology, 2020, 42(1):83-89.)
[10] 李正周, 田蕾, 郑微, 等. 基于时频分析的成像小弱运动目标检测方法[J]. 强激光与粒子束, 2011, 23(9):2292-2296.(LI Z Z, TIAN L, ZHENG W, et al. Dim moving target detection method based on time frequency analysis[J]. High Power Laser and Particle Beams, 2011, 23(9):2292-2296.)
[11] REED I S, GAGLIARDI R M, SHAO H M. Applications of threedimensional filtering to moving target detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 1983, AES-19(6):898-905.
[12] 牛文龙. 基于高时相探测的运动点目标检测方法研究[D]. 北京:中国科学院大学, 2018:75-84.(NIU W L. Moving point target detecting based on high frame-rate image sequence in very low SNR[D]. Beijing:University of Chinese Academy of Sciences, 2018:75-84.)
[13] BAO Z C, JIANG Q X, LIU F Z. Multiple model efficient particle filter based track-before-detect for maneuvering weak targets[J]. Journal of Systems Engineering and Electronics, 2020, 31(4):647-656.
[14] 李振武. 基于动态规划的检测前跟踪算法研究[D]. 哈尔滨:哈尔滨工程大学, 2019:10-15.(LI Z W. Research on dynamic programming based track-before-detect algoritmh[D]. Harbin:Harbin Engineering University, 2019:10-15.)
[15] BARNIV Y. Dynamic programming solution for detecting dim moving targets[J]. IEEE Transactions on Aerospace and Electronic Systems, 1985, AES-21(1):144-156.
[16] 房垚鑫, 郭宝峰, 马超. 基于改进点扩散函数的遥感图像超分辨率重建[J]. 激光技术, 2019, 43(5):713-718.(FANF Y X, GUO B F, MA C. Super-resolution reconstruction of remote sensing images based on improved point spread function[J]. Laser Technology, 2019, 43(5):713-718.)
[17] NADARAJAH S. A modified bessel distribution of the second kind[J]. Statistica, 2007, 67(4):405-413.
[18] 唐向宏, 李齐良. 时频分析与小波变换[M]. 2版. 北京:科学出版社, 2016:119-128.(TANG X H, LI Q L. Time-Frequency Analysis and Wavelet Transform[M]. 2nd ed. Beijing:Science Press, 2016:119-128.)
[19] LIANG L M, WU J, ZHONG Z, et al. Sparse representation for kernel function selection of support vector machine[J]. International Journals of Autonomous and Adaptive Communications Systems, 2018, 11(1):83-97.
[20] WANG L P, ZHANG L P, ZHAO M, et al. An algorithm for moving target detection in IR image based on grayscale distribution and kernel function[J]. Journal of Central South University, 2014, 21(11):4270-4278.

基于检测与跟踪相互迭代的极暗弱目标搜索算法

Extremely dim target search algorithm based on detection and tracking mutual iteration

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	姜琨, 刘征, 朱磊, 李晓星. 基于有向无环图的倒排链等字长划分压缩算法[J]. 计算机应用, 2021, 41(3): 727-732.
[2]	曾志阳, 陈燕, 王珂. 圆片下料并行遗传算法的设计与实现[J]. 计算机应用, 2020, 40(2): 392-397.
[3]	李昆明, 王超迁, 倪巍伟, 鲍晓涵. 基于差分隐私的高精度直方图发布方法[J]. 计算机应用, 2020, 40(11): 3242-3248.
[4]	史文旭, 杨洋, 鲍胜利. 贪心核加速动态规划算法求解折扣{0-1}背包问题[J]. 计算机应用, 2019, 39(7): 1912-1917.
[5]	杨世强, 罗晓宇, 乔丹, 柳培蕾, 李德信. 基于滑动窗口和动态规划的连续动作分割与识别[J]. 计算机应用, 2019, 39(2): 348-353.
[6]	孙石磊, 王超, 赵元棣. 基于轮廓系数的参数无关空中交通轨迹聚类方法[J]. 计算机应用, 2019, 39(11): 3293-3297.
[7]	范君, 王新, 徐慧. 粒子群优化混合核极限学习机的构造煤厚度预测方法[J]. 计算机应用, 2018, 38(6): 1820-1825.
[8]	刘莉, 詹恩奇, 郑建彬, 汪阳. 基于曲线分段相似匹配的在线签名认证[J]. 计算机应用, 2018, 38(4): 1046-1050.
[9]	忽丽莎, 王素贞, 陈益强, 胡春雨, 蒋鑫龙, 陈振宇, 高兴宇. 基于目标均衡度量的核增量学习跌倒检测方法[J]. 计算机应用, 2018, 38(4): 928-934.
[10]	张乐园, 李佳烨, 李鹏清. 低秩约束的非线性属性选择算法[J]. 计算机应用, 2018, 38(12): 3444-3449.
[11]	南敬昌, 崔洪艳. 基于新型二维核函数动态X参数的功放建模[J]. 计算机应用, 2017, 37(8): 2421-2426.
[12]	刘院英, 郭景峰, 魏立东, 胡心专. 成本控制下的快速影响最大化算法[J]. 计算机应用, 2017, 37(2): 367-372.
[13]	汤海建, 鲍宇, 闵玄, 罗煜璇, 邹宇驰. 无线传感器网络中载体的自主移动策略[J]. 计算机应用, 2016, 36(2): 478-482.
[14]	李华, 李德玉, 王素格, 张晶. 多标记数据特征提取方法的核改进[J]. 计算机应用, 2015, 35(7): 1939-1944.
[15]	张垚, 潘峰, 申军伟. 基于小波包分解与矩阵编码的自适应音频隐写算法[J]. 计算机应用, 2015, 35(3): 722-725.