由于红外小目标检测技术在国防领域的精确制导、防空反导、目标预警和民用领域的交通监测、医学成像分析、森林火灾预警等方面发挥着重要作用，因此，受到了学者的广泛关注。在实际应用中，目标与红外探测器之间的距离较大，其对应的像素点在整幅图像中的占比较低，缺乏清晰的纹理特性与物理结构；同时，在图像采集中也会不可避免地引入噪声以及复杂背景，如强杂波、高亮边缘等，都会对目标的检测造成严重干扰。针对此问题，本文结合人类视觉对比度方法，旨在提高目标检测率，解决现有对比度算法的不足。主要研究内容概括如下：

 （1）针对局部对比度算法利用多尺度滑动窗口在大尺度条件下对目标进行检测易出现块效应的问题，提出了一种基于LOG滤波的双向加权局部对比度的红外小目标检测算法。首先，利用LOG滤波对原始图像进行平滑，滤除高频噪声，以快速提取候选目标像素；然后，利用正交和对角方向对比度构建双向局部对比度对目标像素点不同方向信息特征进行提取，并引入一加权因子，通过双向加权对比度的计算，以进一步增强目标的显著性；最后，通过自适应阈值分割技术对真实目标进行分离。实验结果表明：本文所提算法能够实现对不同尺寸目标的检测，不仅可以避免现有算法在大尺度下导致的块效应，还能显著提高目标的检测率。

 （2）针对地空强杂波背景下小目标易受到杂波干扰而导致目标检测出现虚警的问题，提出了一种基于双邻域局部加权对比的红外小目标检测算法。该算法能缓解背景强杂波对检测带来的干扰，提高小目标在地空背景下的检测率。所提算法采用了三层模板的构造方式，充分利用三层滑动窗口不同层之间的灰度差异，分别计算中心窗口内外层邻域最小局部方向对比度并结合内外邻域差异获取双邻域局部对比度。运用权重函数对所得显著性图进一步增强，实现在抑制背景杂波的同时对目标进行增强，最后通过自适应阈值分割技术提取显著性图中的真实目标。由于该算法利用单尺度对不同尺寸目标进行检测，减小了多尺度算法的计算复杂度。另外，实验结果表明：所提算法可以充分抑制背景强杂波，有效避免检测虚警的发生。

    Since infrared small target detection technology plays an important role in precision guidance, air defense and anti-missile, target warning in the field of national defense, and traffic monitoring, medical imaging analysis, forest fire warning in the field of civil use, it has received extensive attention from scholars. In practical applications, due to the large distance between the target and the infrared detector, the corresponding pixel points account for a relatively low proportion in the whole image, lacking clear texture characteristics and physical structure. At the same time, during the process of image acquisition, noises and complex backgrounds such as strong clutters and bright edges will be inevitably introduced, which will cause serious interference to the target detection. To address this issue, this paper combines the human visual contrast method to improve the target detection rate and solve the shortcomings of existing contrast algorithms. The main research contents are summarized as follows:

    (1) Aiming at the problem that the local contrast algorithm is prone to block effect when using multi-scale sliding window to detect the target under large-scale conditions, a bidirectional weighted local contrast infrared small target detection algorithm based on LOG filtering is proposed. Firstly, LOG filtering is used to smooth the original image and filter out high-frequency noise to quickly extract candidate target pixels. Then, the bidirectional local contrast is constructed by using the orthogonal and diagonal contrast to extract the information features of the target pixels in different directions, and a weighting factor is introduced to further enhance the saliency of the target by calculating the bidirectional weighted contrast. Finally, the real target is separated by adaptive threshold segmentation technology. The experimental results show that the proposed algorithm can realize the detection of targets with different sizes, which can not only avoid the block effect caused by the existing algorithms in large scale, but also significantly improve the detection rate of targets.

    (2) Aiming at the problem that small targets are susceptible to clutter interference in the background of strong ground-air clutter, which leads to false alarm in target detection, an infrared small target detection algorithm based on double neighborhood local weighted comparison is proposed. The algorithm can alleviate the interference of strong background clutter on detection and improve the detection rate of small targets in the ground-sky background. The proposed algorithm adopts a three-layer template construction method, makes full use of the gray difference between different layers of the three-layer sliding window, calculates the minimum local directional contrast of the inner and outer layers of the central window respectively, and combines the difference between the inner and outer neighborhoods to obtain the local contrast of the double neighborhoods. The weight function is used to further enhance the obtained saliency map, so as to enhance the target while suppressing the background clutter. Finally, the real target in the saliency map is extracted by the adaptive threshold segmentation technology. Since the algorithm uses a single scale to detect targets of different sizes, which reduces the computational complexity of the multi-scale algorithm. In addition, the experimental results show that the proposed algorithm can fully suppress the strong background clutter and effectively avoid the occurrence of detection false alarm.

[1] Hou F J, Zhang Y, Zhou Y, et al. Review on infrared imaging technology[J]. Sustainability, 2022, 14(18): 11161.

[2] 唐凌霄, 黄昶. 基于双层局部能量因子的红外小目标检测方法[J]. 华东师范大学学报(自然科学版), 2024(02): 97-107.

[3] 徐正军, 张强, 许亮. 一种基于改进YOLOv5s-Ghost网络的交通标志识别方法[J]光电子·激光, 2023, 34(01): 52-61.

[4] 余祉祺. 红外图像的目标检测研究[J]. 数字通信世界, 2024(01): 34-37.

[5] 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(04): 438-461.

[6] 何青叶. 基于单帧图像的红外弱小目标检测技术研究综述[J]. 红外, 2022, 43(04): 9-19.

[7] 李文博, 王琦, 高尚. 基于深度学习的红外小目标检测算法综述[J]. 激光与红外, 2023, 53(10): 1476-1484.

[8] 张海松. 复杂背景下的红外弱小目标检测方法研究[D]. 太原: 中北大学, 2023.

[9] 孙士新, 郑志蕴. 基于多尺度NNLoG特征提取的红外多目标检测遗传算法[J]. 红外技术, 2019, 41(09): 837-842.

[10] 詹令明, 李翠芸, 姬红兵. 基于显著图的红外弱小目标动态规划检测前跟踪算法[J]. 计算机辅助设计与图形学学报, 2019, 31(7): 1061-1066.

[11] Lim J, Kim H S, Park H M. Interactive-multiple-model algorithm based on minimax particle filtering[J]. IEEE Signal Processing Letters, 2020, 27: 36-40.

[12] 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): 1133-1140.

[13] Guo Q, Li Z W, Song W M, et al. Parallel computing based dynamic programming algorithm of track-before-detect[J]. Symmetry, 2018, 11(1): 29.

[14] 任向阳, 王杰, 马天磊, 等. 红外弱小目标检测技术综述[J]. 郑州大学学报: 理学版, 2020, 52(2): 1-21.

[15] Lv P Y, Sun S L, Lin C Q, et al. Space moving target detection and tracking method in complex background[J]. Infrared Physics and Technology, 2018, 91: 107-118.

[16] 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(02): 154-162.

[17] Huang J, Ma Y, Zhang Y, et al. Infrared image enhancement algorithm based on adaptive histogram segmentation [J]. Applied Optics, 2017, 56(35): 9686-9697.

[18] 李俊宏, 张萍, 王晓玮, 等. 红外弱小目标检测算法综述[J]. 中国图象图形学报, 2020, 25(09): 1739-1753.

[19] Wang X Y, Peng Z M, Zhang P, et al. Infrared small target detection via nonnegativity-constrained variational mode decomposition[J]. IEEE Geoence and Remote Sensing Letters, 2017: 1700-1704.

[20] Deshpande S D, Er M H, Venkateswarlu R, et al. Max-mean and max-median filters for detection of small-targets[C]//Processing of small targets international society for optics and photonics, Denver, Colorado, 1999.

[21] Bai X Z, Zhou F G. Analysis of new top-hat transformation and the application for infrared dim small target detection[J]. Pattern Recognition, 2010, 43(6): 2145-2156.

[22] Bae T W, Kim B I, Lee S H, et al. Small target detection using bilateral filter based on edge component[J]. Journal of Infrared Milli Terahz Waves, 2009, 34(9): 863-870.

[23] Wang X, Lv G F, Xu L Z. Infrared dim target detection based on visual attention[J]. Infrared Physics & Technology, 2012, 55(6): 513-521.

[24] 李越强, 李庶中, 王全喜, 等. 一种基于Wiener滤波的海天背景红外目标检测算法[J]. 兵工学报, 2015, 36(S2): 139-143.

[25] Kim S, Lee J. Scale invariant small target detection by optimizing signal-to-clutter ratio in heterogeneous background for infrared search and track[J]. Pattern Recognition, 2012, 45(1): 393-406.

[26] Dehghani A, Pourmohammad A. Small target detection and tracking based on the background elimination and Kalman filter[C]//The International Symposium on Artificial Intelligence and Signal Processing (AISP), Mashhad, Iran, 2015: 328-333.

[27] Qi S X, Ma J, Li H, et al. Infrared small target enhancement via phase spectrum of quaternion Fourier transform[J]. Infrared Physics & Technology, 2014, 62: 50-58.

[28] 张晓露, 李玲, 辛云宏. 基于小波变换的自适应多模红外小目标检测[J]. 激光与红外, 2017, 47(05): 647-652.

[29] Deng H, Sun X P, Liu M L, et al. Infrared small-target detection using multiscale gray difference weighted image entropy[J]. IEEE Transactions on Aerospace and Electronic System, 2016, 52(1): 60-72.

[30] 李燕苹, 谢维信, 裴继红. 基于小波变换的红外弱小目标检测新方法[J]. 红外技术, 2006(07): 419-422.

[31] Lu L P. Research on infrared small target detection and tracking algorithms based on wavelet transformation[J]. Sensors & Transducers, 2013, 156(9): 116.

[32] Wang H, Xin Y. H Wavelet-based contourlet transform and Kurtosis map for infrared small target detection in complex background[J]. Sensors, 2020, 20(3): 755.

[33] 张晔. 结合频域显著性分析和形态学滤波的红外小目标检测算法[J]. 激光与红外, 2022, 52(10): 1487-1493.

[34] 王刚, 陈永光, 杨锁昌, 等. 采用图像块对比特性的红外弱小目标检测[J]. 光学精密工程, 2015, 23(5): 1424-1433.

[35] 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.

[36] Han J H, Ma Y, Zhou B, et al. A robust infrared small target detection algorithm based on human visual system[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(12): 2168-2172.

[37] 王晓阳, 彭真明, 张萍, 等. 局部对比度结合区域显著性红外弱小目标检测[J]. 强激光与粒子束, 2015, 27(9): 38-44.

[38] 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.

[39] Qin Y, Li B. Effective infrared small target detection utilizing a novel local contrast method[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(12): 1890-1894.

[40] Zhang H, Zhang L, Ding Y, et al. Infrared small target detection based on local intensity and gradient[J]. Infrared Physics and Technology, 2017, 89 (12): 88-96.

[41] Han J H, Liang K, Zhou B, et al. Infrared small target detection utilizing the multiscale relative local contrast measure[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(4): 612-616.

[42] 潘胜达, 张素, 赵明, 等. 基于双层局部对比度的红外弱小目标检测方法[J]. 光子学报, 2020, 49(1): 178-186.

[43] Wu L, Ma Y, Fan F, et al. A double-neighborhood gradientmethod for infrared small target detection [J]. IEEE Geoscienceand Remote Sensing Letters, 2020, 18(8): 1476-1480.

[44] 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, 2019, 17(10): 1822-1826.

[45] 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.

[46] 袁帅, 延翔, 张昱赓, 等. 双邻域差值放大的高动态红外弱小目标检测方法(特邀)[J]. 红外与激光工程, 2022, 51(04): 81-91.

[47] 吴安茂, 骆定辉. 红外探测技术的应用及发展[J]. 电子技术与软件工程, 2019, 156(10): 88.

[48] Qi S, Ma J, Tao C, et al. A Robust Directional Saliency-Based Method for Infrared Small-Target Detection Under Various Complex Background[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 495-499.

[49] 孙青, 李玲, 辛云宏. 基于局部多尺度低秩分解的红外小目标检测算法[J]. 激光与红外, 2019, 49(03): 369-375.

[50] Yao S B, Zhu Q Y, Zhang T, et al. Infrared image small-target detection based on improved FCOS and spatio-temporal features[J]. Electronics, 2022, 11(06): 933.

[51] 孙学超. 复杂云层背景下红外小目标检测算法研究[D]. 哈尔滨: 哈尔滨工程大学, 2018.

[52] 张国峰, 艾斯卡尔·艾木都拉. 双边滤波下局部强度与梯度融合的小目标检测[J]. 电讯技术, 2019, 59(11): 1357-1363.

[53] 彭闪. 基于空时滤波的红外弱小目标检测算法研究[D]. 成都: 电子科技大学, 2020.

[54] Zhou X, Deng H, Sun X P. A multiscale fuzzy metric for detecting small infrared targets against chaotic cloudy/sea-sky backgrounds[J]. IEEE Transactions on Cybernetics, 2018, 49(5): 1694-1707.

[55] Zhao J J, Tang Z Y, Yang J, et al. Infrared small target detection using sparse representation[J]. Journal of Systems Engineering and Electronics, 2011, 22(6): 897-904.

[56] Cui Z, Yang J L, Li J B, et al. An infrared small target detection framework based on local contrast method[J]. Measurement, 2016, 91: 405-413.

[57] Moradi S, Moallem P, Sabahi M F. Scale-space point spread function based framework to boost infrared target detection algorithms[J]. Infrared Physics and Technology, 2016, 77: 27-34.

[58] 周苑, 张健民, 林晓. 基于加权LoG算子的红外弱小目标检测方法研究[J]. 应用光学, 2017, 38(1): 114-119.

[59] 贺顺, 谢永妮, 杨志伟, 等. 基于IHBF的增强局部对比度红外小目标检测方法[J]. 红外技术, 2022, 44(11): 1132-1138.

[60] 袁明, 宋延嵩, 张梓祺, 等. 基于增强局部对比度的红外弱小目标检测方法[J]. 激光与光电子学进展, 2023, 60(04): 85-91.