方向显著性特征分布的加权散度红外弱小目标增强检测
doi: 10.11728/cjss2025.01.2024-0025 cstr: 32142.14.cjss.2024-0025
-
王怡雯 女, 出生于2002年, 河南工业大学电气工程学院在读本科生, 主要从事微弱信号处理等方面研究. E-mail: wangyiwen@stu.haut.edu.cn -
郑伟 男, 工学博士, 副研究员, 硕士生导师, 1996年于西北工业大学获得学士学位, 2001年于中国科学院西安光学精密机械研究所获得硕士学位, 2009年于中国科学院国家空间中心获得博士学位, 主要从事微弱信号处理、非线性信号处理与天基信息处理方面的研究. E-mail: zhengwei@nssc.ac.cn
-
邢成龙 男, 现任职于河南工业大学电气工程学院控制工程系, 主要研究方向为流动控制与优化、机器学习和智能检测技术等. E-mail: chenglong.xing@haut.edu.cn
作者简介:
通讯作者:
Weighted Divergence of Directionally Salient Features for Infrared Small Target Detection Enhancement
-
摘要: 红外弱小目标检测广泛应用于暗弱天体检测等领域, 是空间环境安全预警的重要手段. 基于熵的理论并结合目标扩散的方向性, 提出了一种方向显著性特征分布的加权散度红外弱小目标增强检测方法(DSWD). 在多层嵌套窗口中评估图像局部显著性, 基于点目标在红外图像中由中心向八个方向扩展的特征对图像进行多向空间滤波, 在复杂背景中增强目标. 鉴于显著性特征各向分布与平均背景分布之间的差异, 使用散度将目标区域与背景之间概率分布量化, 推断区域内感兴趣的部分. 为解决复杂背景中存在的高亮背景等混淆元素会对目标提取造成干扰的问题, 进一步采用改进的绝对均方差方法增强目标, 确保从复杂背景中准确分离出目标, 进而采用自适应阈值处理方法提取目标. 实验结果表明, 针对多变空间环境, 所提出的方法能够在空间环境中准确检测出弱小目标, 降低虚警率, 为未来空间环境安全预警系统提供参考.Abstract: Infrared small target detection is widely used in fields such as dark and weak object detection, which is an important means of early warning for space environment safety. Drawing on entropy theory and incorporating the directionality of target diffusion, this study introduces a method for Infrared Small Target Detection Enhancement named Weighted Divergence of Directionally Salient Features (DSWD). Initially, this method assesses the local saliency of an image using a multi-layer nested window approach, and applies multidirectional spatial filtering to highlight point targets that radiate outward from the center to eight directions within the infrared spectrum, thereby enhancing the target against a complex backdrop. To address the disparity between the anisotropic distribution of saliency features and the homogeneous background distribution, this study employs a scatter measure to quantify the probabilistic distribution between the target area and the background, thus identifying regions of interest. Nevertheless, the efficacy of target extraction can be compromised by obfuscating elements, such as prominently illuminated backgrounds. To mitigate this, the study leverages an enhanced absolute mean square deviation technique for further target refinement, ensuring precise separation and extraction from the intricate background. The process culminates with the application of an adaptive threshold segmentation method for final target extraction. The experimental results show that for the variable space environment, the method proposed in this paper can accurately detect the weak targets in the space environment and reduce the false alarm rate, which is expected to be applied in the future space environment safety warning system or for reference.
-
Key words:
- Infrared small target detection /
- Energy weighting /
- Local contrast /
- Dispersion
-
图 6 不同算法在不同序列下的红外弱小目标图像检测结果
Figure 6. Infrared small target image detection results under different sequences
图 7 利用不同算法在四组序列下的ROC曲线
Figure 7. ROC curves of different algorithms under four sets of sequences
表 1 四组序列详细信息
Table 1. Four sets of sequence details
序列 帧数 平均SCR SCR
方差场景说明 序列1 399 6.07 0.16 由远及近、单个目标、地面背景 序列2 1500 5.20 2.23 日标由远及近、单个目标、目标中途机动、地面背景 序列3 751 3.42 0.97 单个目标、目标机动、地面背景 序列4 500 2.20 0.15 目标由远及近、单个目标、地面背景 
下载: 导出CSV
表 2 利用不同算法在四组序列下计算的FSCRG值
Table 2. FSCRG values calculated by different algorithms under four sets of sequences
序列 DSWD WSLCM TLLCM PSTNN MPCM LGDC ADMD 序列1 26.95886 3.389853 2.41065 7.060763 2.132392 5.077733 0.289776 序列2 29.08403 3.114348 4.14042 7.535866 0.89089 1.659468 0.087604 序列3 4.342124 1.845483 3.6071 3.443729 0.549783 0.374816 0.038264 序列4 86.61648 1.818613 0.970138 22.27447 1.676713 4.845257 0.288661
下载: 导出CSV
表 3 利用不同算法在四组序列下计算的FBSF值
Table 3. FBSF values calculated by different algorithms under four sets of sequences
序列 DSWD WSLCM TLLCM PSTNN MPCM LGDC ADMD 序列1 14.25265 8.344599 6.071986 3.597427 3.578278 5.140639 3.99592 序列2 11.28658 5.699201 3.898466 2.658014 2.113583 3.541101 3.420808 序列3 14.26926 9.906523 7.195343 3.441276 4.485798 10.69522 7.449242 序列4 41.467 21.04057 13.6944 10.56703 7.350093 12.689 8.624328
下载: 导出CSV
表 4 单帧算法的平均运行效率
Table 4. Average operational efficiency of single-frame algorithms
算法 DSWD WSLCM TLLCM PSTNN MPCM LGDC ADMD 运行效率 0.075509 2.243401 0.555400 0.468005 0.112141 1.187946 0.066555
下载: 导出CSV
-
[1] 牛海鹏. 天基空间监视系统目标检测技术研究[D]. 长春: 中国科学院大学(中国科学院长春光学精密机械与物理研究所), 2023NIU Haipeng. Research on Target Detection Technology of Space-Based Space Surveillance System[D]. Changchun: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, 2023 [2] KONG X, YANG C P, CAO S Y, et al. Infrared small target detection via nonconvex tensor fibered rank approximation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5000321 [3] ZHANG K, LI X G. Infrared small dim target detection based on region proposal[J]. Optik, 2019, 182: 961-973 doi: 10.1016/j.ijleo.2019.02.008 [4] LU R T, YANG X G, JING X, et al. Infrared small target detection based on local hypergraph dissimilarity measure[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 7000405 [5] LU S, CHEN P F, WOŹNIAK M. Image enhancement-based detection with small infrared targets[J]. Remote Sensing, 2022, 14(13): 3232 doi: 10.3390/rs14133232 [6] LIU C, XIE F Y, ZHANG H P, et al. Infrared small target detection based on multi-perception of target features[J]. Infrared Physics & Technology, 2023, 135: 104927 [7] 凡遵林, 王浩, 管乃洋, 等. 单帧红外图像弱小目标检测研究综述[J]. 红外技术, 2023, 45(11): 1133-1140FAN Zunlin, WANG Hao, GUAN Naiyang, et al. Review of dim small target detection research in single infrared image[J]. Infrared Technology, 2023, 45(11): 1133-1140 [8] 孙熊伟. 复杂背景下海面红外小目标快速检测技术研究[D]. 合肥: 中国科学技术大学, 2019SUN Xiongwei. Research on the Rapid Detection of infrared Small Targets under Complex Marine Backgrounds[D]. Hefei: University of Science and Technology of China, 2019 [9] 杜鹏. 复杂背景条件下红外弱小目标检测关键技术研究[D]. 乌鲁木齐: 新疆大学, 2020DU Peng. Research on Key Technology of Infrared Detection of Dim and Small Target Under Complex Background Conditions[D]. Urumqi: Xinjiang University, 2020 [10] 刘征, 杨德振, 李江勇, 等. 红外单帧弱小目标检测算法研究综述[J]. 激光与红外, 2022, 52(2): 154-162 doi: 10.3969/j.issn.1001-5078.2022.02.002LIU Zheng, YANG Dezhen, LI Jiangyong, et al. A review of infrared single-frame dim small target detection algorithms[J]. Laser & Infrared, 2022, 52(2): 154-162 doi: 10.3969/j.issn.1001-5078.2022.02.002 [11] 马梁, 苟于涛, 雷涛, 等. 基于多尺度特征融合的遥感图像小目标检测[J]. 光电工程, 2022, 49(4): 47-63MA Liang, GUO Yutao, LEI Tao, et al. Small object detection based on multi-scale feature fusion using remote sensing images[J]. Opto-Electronic Engineering, 2022, 49(4): 47-63 [12] 杨本臣, 宋婉妮, 金海波, 等. 梯度差各向异性高斯滤波的红外小目标检测[J]. 激光与光电子学进展, 2023, 60(16): 1612003YANG Benchen, SONG Wanni, JIN Haibo, et al. Infrared small target detection using gradient differential anisotropic Gaussian filtering[J]. Laser & Optoelectronics Progress, 2023, 60(16): 1612003 [13] 穆靖, 李伟华, 饶俊民, 等. 采用三层模板局部差异度量的红外弱小目标检测[J]. 光学 精密工程, 2022, 30(7): 869-882 doi: 10.37188/OPE.20223007.0869MU Jing, LI Weihua, RAO Junmin, et al. Infrared small target detection using tri-layer template local difference measure[J]. Optics and Precision Engineering, 2022, 30(7): 869-882 doi: 10.37188/OPE.20223007.0869 [14] 饶俊民, 穆靖, 刘士建, 等. 基于聚类思想的红外弱小目标检测[J]. 红外与毫米波学报, 2023, 42(4): 527-537 doi: 10.11972/j.issn.1001-9014.2023.04.015RAO Junmin, MU Jing, LIU Shijian, et al. Infrared small target detection based on clustering idea[J]. Journal of Infrared and Millimeter Waves, 2023, 42(4): 527-537 doi: 10.11972/j.issn.1001-9014.2023.04.015 [15] HAN Jinhui , MA Yong, HUANG Jun, et al. An infrared small target detecting algorithm based on human visual system[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 13 (3): 452-456 [16] 薛锡瑞, 黄树彩, 马佳顺, 等. 基于局部熵参考预处理的RPCA红外小目标检测[J]. 红外技术, 2021, 43(7): 649-657XUE Xirui, HUANG Shucai, MA Jiashun, et al. RPCA infrared small target detection based on local entropy reference in preprocessing[J]. Infrared Technology, 2021, 43(7): 649-657 [17] 孙国栋, 吉书鹏, 周桢. 小波域自适应滤波的红外弱小目标检测[J]. 航空兵器, 2011(3): 20-23 doi: 10.3969/j.issn.1673-5048.2011.03.006SUN Guodong, JI Shupeng, ZHOU Zhen. Dim small IR target detection based on the wavelet domain adaptive filtering[J]. Aero Weaponry, 2011(3): 20-23 doi: 10.3969/j.issn.1673-5048.2011.03.006 [18] 赵骞, 韩金辉, 徐茂, 等. 基于局部对比度背景估计的红外小目标检测方法[J]. 智能系统学报, 2022, 17(2): 314-324 doi: 10.11992/tis.202101009ZHAO Qian, HAN Jinhui, XU Mao, et al. Infrared small-target detection utilizing background estimation combined with local contrast[J]. CAAI Transactions on Intelligent Systems, 2022, 17(2): 314-324 doi: 10.11992/tis.202101009 [19] HU J, YU Y, LIU F. Small and dim target detection by background estimation[J]. Infrared Physics & Technology, 2015, 73: 141-148 [20] CHEN C L P, LI H, WEI Y T, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 574-581 doi: 10.1109/TGRS.2013.2242477 [21] HAN J H, MORADI S, FARAMARZI I, et al. Infrared small target detection based on the weighted strengthened local contrast measure[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(9): 1670-1674 doi: 10.1109/LGRS.2020.3004978 [22] SUN Y, YANG J G, AN W. Infrared dim and small target detection via multiple subspace learning and spatial-temporal patch-tensor model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(5): 3737-3752 doi: 10.1109/TGRS.2020.3022069 [23] LI B Y, XIAO C, WANG L G, et al. Dense nested attention network for infrared small target detection[J]. IEEE Transactions on Image Processing, 2023, 32: 1745-1758 doi: 10.1109/TIP.2022.3199107 [24] 聂青凤, 刘应杰, 梁赟. 基于稀疏约束神经网络的红外弱小目标检测技术[J]. 电光与控制, 2022, 29(8): 40-44 doi: 10.3969/j.issn.1671-637X.2022.08.008NIE Qingfeng, LIU Yingjie, LIANG Yun. Infrared dim target detection based on neural network model with sparsity constraint[J]. Electronics Optics & Control, 2022, 29(8): 40-44 doi: 10.3969/j.issn.1671-637X.2022.08.008 [25] LIU F C, GAO C Q, CHEN F, et al. Infrared small-dim target detection with transformer under complex backgrounds[OL]. arXiv preprint arXiv: 2109.14379, 2021 [26] 韩金辉, 魏艳涛, 彭真明, 等. 红外弱小目标检测方法综述[J]. 红外与激光工程, 2022, 51(4): 20210393 doi: 10.3788/IRLA20210393HAN Jinhui, WEI Yantao, PENG Zhenming, et al. Infrared dim and small target detection: a review[J]. Infrared and Laser Engineering, 2022, 51(4): 20210393 doi: 10.3788/IRLA20210393 [27] MORADI S, MOALLEM P, SABAHI F M. Fast and robust small infrared target detection using absolute directional mean difference algorithm[J]. Signal Processing, 2020, 177: 107727 doi: 10.1016/j.sigpro.2020.107727 [28] HAN J H, MORADI S, FARAMARZI I, et al. A local contrast method for infrared small-target detection utilizing a tri-layer window[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(10): 1822-1826 doi: 10.1109/LGRS.2019.2954578 [29] ZHANG L D, PENG Z M. Infrared small target detection based on partial sum of the tensor nuclear norm[J]. Remote Sensing, 2019, 11(4): 382 doi: 10.3390/rs11040382 [30] WEI Y T, YOU X G, LI H. Multiscale patch-based contrast measure for small infrared target detection[J]. Pattern Recognition, 2016, 58: 216-226 doi: 10.1016/j.patcog.2016.04.002 [31] WAN M J, XU Y K, HUANG Q Y, et al. Single frame infrared small target detection based on local gradient and directional curvature[C]//Proceedings of SPIE 11897, Optoelectronic Imaging and Multimedia Technology VIII. Nantong: SPIE, 2021: 99-107 [32] 回丙伟, 宋志勇, 范红旗, 等. 地/空背景下红外图像弱小飞机目标检测跟踪数据集[J]. 中国科学数据, 2020, 5(3): 286-297HUI Bingwei, SONG Zhiyong, FAN Hongqi, et al. A dataset for infrared detection and tracking of dim-small aircraft targets under ground/air background[J]. China Scientific Data, 2020, 5(3): 286-297 -
-
下载:
图(7) / 表(4)
计量
- 文章访问数: 334
- HTML全文浏览量: 100
- PDF下载量: 35
-
被引次数:
0(来源:Crossref)
0(来源:其他)
