层次卷积滤波红外弱小目标检测方法

陈灿灿; 夏润秋; 刘洋; 刘力双; 陈青山

doi:10.5768/JAO202344.0403003

层次卷积滤波红外弱小目标检测方法

doi: 10.5768/JAO202344.0403003

北京信息科技大学仪器科学与光电工程学院，北京 100092

基金项目: 国防军工重点计量科研项目（J*********1）

详细信息

作者简介:
陈灿灿（1995—），女，硕士，主要从事红外图像小目标检测算法研究。E-mail：chencc2580@163.com

中图分类号: TN219
计量
- 文章访问数: 270
- HTML全文浏览量: 191
- PDF下载量: 46
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-18
- 修回日期: 2022-09-09
- 网络出版日期: 2022-09-24
- 刊出日期: 2023-07-15

Hierarchical convolution filtering method for infrared dim small target detection

School of Instrument Science and Opto-electronic Engineering, Beijing Information Science and Technology University, Beijing 100089, China

摘要

摘要: 针对单帧复杂背景红外图像点目标检测算法存在复杂背景下处理效果不理想、处理时间长的问题，提出了一种层次卷积滤波检测算法。主要分为两个部分：第一，根据红外小目标特性，设计一种层次卷积滤波的算子，对图像进行滤波处理，实现图像中小目标的增效和背景抑制的效果；第二，采用基于最大值的自适应阈值方法，对图像进行二值化操作，过滤背景杂波，最终提取到待检测的目标。在大量不同背景红外图像中进行实验，论文算法在背景抑制因子和信噪比增益的性能量化结果上优于现有5种典型红外弱小目标检测算法的性能结果，且平均处理时间仅为高斯拉普拉斯（Laplacian of Gaussian，LoG）滤波算法的30.42%。通过实验对比，表明该层次卷积滤波算法可以有效解决在不同复杂背景下的红外图像中对小目标检测的问题。
- 复杂背景 /
- 红外图像 /
- 红外弱小目标检测 /
- 卷积滤波 /
- 自适应阈值
Abstract: Aiming at the problems of unsatisfactory processing effect and long processing time in point target detection algorithm of single-frame infrared image with complex background, a hierarchical convolution filtering detection algorithm was proposed. It was mainly divided into two parts: firstly, according to the characteristics of small infrared targets, a hierarchical convolution filtering operator was designed to filter the image, so as to achieve the effect of efficiency increase and background suppression of small targets in the image. Secondly, the adaptive threshold method based on the maximum value was used to binarize the image to filter the background clutter, and finally extracted the target to be detected. Experiments in a large number of infrared images with different backgrounds show that the performance quantization results of background suppression factor and signal-to-noise ratio gain of the algorithm are better than that of the existing five typical infrared dim and small target detection algorithms, and the average processing time is only 30.42% of Laplacian of Gaussian (LoG) filtering algorithm. Through the experimental comparison, the hierarchical convolution filtering method can effectively solve the problem of small target detection in infrared images under different complex backgrounds.
- complex background /
- infrared image /
- infrared dim small target detection /
- convolution filtering /
- adaptive threshold

HTML全文

图 1 整体算法流程

Fig. 1 Overall flow chart of algorithm

下载: 全尺寸图片幻灯片

图 2 含有小目标的红外图像

Fig. 2 Infrared image with small targets

下载: 全尺寸图片幻灯片

图 3 算子模型介绍

Fig. 3 Introduction of operator model

下载: 全尺寸图片幻灯片

图 4 该算子的不同应用情况

Fig. 4 Different applications of proposed operator

下载: 全尺寸图片幻灯片

图 5 6种算法处理后的单帧图像

Fig. 5 Single-frame images processed by six algorithms

下载: 全尺寸图片幻灯片

图 6 6种算法处理后的序列图像

Fig. 6 Sequence images processed by six algorithms

下载: 全尺寸图片幻灯片

图 8 不同算法的ROC曲线图

Fig. 8 ROC curves of different algorithms

下载: 全尺寸图片幻灯片

表 1 红外序列图像信息

Table 1 Infrared sequence image information

图像序列	帧数	图像大小	目标数量	目标尺寸
Seq.6	325	256×256	1	3×3
Seq.7	597	256×256	1	3×3
Seq.8	266	256×256	1	3×3
Seq.9	276	256×256	1	3×3
Seq.10	290	256×256	1	3×3

下载: 导出CSV

表 2 6种方法在Seq.6~10上的SCRG值比较

Table 2 Comparison of SCRG values of six methods on Seq.6~10

算法	图像序列
算法	Seq.6	Seq.7	Seq.8	Seq.9	Seq.10
TopHat	1 501.57	78.90	0.93	1 062.44	12.55
IPI	24 184.64	332.68	8.66	70.49	19.08
LCM	7 971.7	512.41	4.09	8 441.12	29.78
MPCM	10 099.61	61.68	10.67	10 891.93	55.73
LoG	3 613.22	81.99	2.2	2 967.2	15.06
Ours	30 663	734.65	28.14	16 763.96	57.51

下载: 导出CSV

表 3 6种方法在Seq.6~10上的BSF值比较

Table 3 Comparison of BSF values of six methods on Seq.6~10

算法	图像序列
算法	Seq.6	Seq.7	Seq.8	Seq.9	Seq.10
TopHat	268.01	228.77	265.74	246.53	639.97
IPI	25.19	10.48	10.35	14.87	12.84
LCM	165.27	134.29	173.25	193.29	178.09
MPCM	124.59	327.89	227.86	207.17	563.92
LoG	555.63	421.91	493.86	506.00	1 182.76
Ours	888.35	1 503.29	8 004.54	1 231.68	3 992.90

下载: 导出CSV

表 4 6种方法在Seq.6-10中平均运行时间

Table 4 Average running time of six methods on Seq.6~10 1 s

算法	图像序列
算法	Seq.6	Seq.7	Seq.8	Seq.9	Seq.10
TopHat	0.010 0	0.010 6	0.010 5	0.010 9	0.011 6
IPI	6.925 6	7.152 9	7.287 3	7.041 5	8.189 0
LCM	0.081 5	0.083 0	0.081 4	0.084 2	0.086 0
MPCM	0.068 3	0.068 2	0.066 7	0.068 9	0.068 8
LoG	0.019 2	0.020 7	0.020 6	0.020 0	0.020 9
Ours	0.006 4	0.006 4	0.005 9	0.005 6	0.006 5

下载: 导出CSV

参考文献(29)

[1]	王好贤, 董衡, 周志权. 红外单帧图像弱小目标检测技术综述[J]. 激光与光电子学进展,2019,56(8):114. WANG Haoxian, DONG Heng, ZHOU Zhiquan. Review on dim small target detection technologies in infrared single frame images[J]. Laser & Optoelectronics Progress,2019,56(8):114.
[2]	何巍, 安博文, 潘胜达. 局部对比度先验下基于低秩模型的红外小目标检测方法[J]. 光子学报,2021,50(11):17. HE Wei, AN Bowen, PAN Shengda. Infrared small target detection method based on low rank model with local contrast prior[J]. Acta Photonica Sinica,2021,50(11):17.
[3]	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. doi: 10.13705/j.issn.1671-6841.2019557 REN Xiangyang, WANG Jie, MA Tianlei, et al. Review on infrared dim and small target detection technology[J]. Journal of Zhengzhou University(Natural Science Edition),2020,52(2):1-21. doi: 10.13705/j.issn.1671-6841.2019557
[4]	范鹏程, 张卫国, 刘万刚, 等. 基于嵌入式GPU的红外弱小目标检测算法[J]. 应用光学,2020,41(5):1089-1095. doi: 10.5768/JAO202041.0506004 FAN Pengcheng, ZHANG Weiguo, LIU Wangang, et al. Infrared weak small target detection algorithm based on embedded GPU[J]. Journal of Applied Optics,2020,41(5):1089-1095. doi: 10.5768/JAO202041.0506004
[5]	李佳. 低慢小无人机目标红外成像探测关键技术研究[D]. 西安: 西安电子科技大学, 2020. LI Jia. Research on the key technology of infrared imaging detection for low-slow-small UAV[D]. Xi’ An: Xidian University, 2020.
[6]	张祥越, 丁庆海, 罗海波, 等. 基于改进LCM的红外小目标检测算法[J]. 红外与激光工程,2017(7):270-276. ZHANG Xiangyue, DING Qinghai, LUO Haibo, et al. Infrared dim target detection algorithm based on improved LCM[J]. Infrared and Laser Engineering,2017(7):270-276.
[7]	LIU C, XIE F Y, DONG X M, et al. Small target detection from infrared remote sensing images using local adaptive thresholding[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:1941-1952. doi: 10.1109/JSTARS.2022.3151928
[8]	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(9):1739-1753. LI Junhong, ZHANG Ping, WANG Xiaowei, et al. Infrared small-target detection algorithms: a survey[J]. Journal of Image and Graphics,2020,25(9):1739-1753.
[9]	SHAO X P, FAN H, LU G X, et al. An improved infrared dim and small target detection algorithm based on the contrast mechanism of human visual system[J]. Infrared Physics & Technology,2012,55(5):403-408.
[10]	MARVASTI F S, MOSAVI M R, NASIRI M. Flying small target detection in IR images based on adaptive toggle operator[J]. IET Computer Vision,2018,12(4):527-534. doi: 10.1049/iet-cvi.2017.0327
[11]	王笛, 沈涛. 基于三阶累积量的红外弱小目标单帧检测算法[J]. 电光与控制, 2020, 27(10): 27-30. WANG Di, SHEN Tao. Single-frame detection algorithm for infrared dim target based on third-order cumulant[J]. Electronics Optics & Control, 2020, 27(10): 27-30.
[12]	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 & Remote Sensing,2014,52(1):574-581.
[13]	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
[14]	DENG H, SUN X P, LIU M L, et al. Small infrared target detection based on weighted local difference measure[J]. IEEE Transactions on Geoscience & Remote Sensing,2016,54(7):4204-4214.
[15]	GAO C G, 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. doi: 10.1109/TIP.2013.2281420
[16]	DAI Y M, WU Y Q, SONG Y. Infrared small target and background separation via column-wise weighted robust principal component analysis[J]. Infrared Physics & Technology,2016(77):421-430.
[17]	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,2021(99):1-21.
[18]	YANG X H, HU X C, ZHOU S H, et al. Interpolation-based contrastive learning for few-label semi-supervised learning[J/OL]. arXiv, [2022-06-22].https://arxiv.org/abs/2202.11915.
[19]	ZHOU W C S, XU C W, MCAULEY J L. BERT learns to teach: Knowledge distillation with meta learning[C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Dublin, Ireland: Association for Computational Linguistics, 2022: 7037-7049.
[20]	LIU Y, TU W X, ZHOU S H, et al. Deep graph clustering via dual correlation reduction[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Vancouver, Canada: AAAI, 2022: 7603-7611.
[21]	LIU Y, YANG X H, ZHOU S H, et al. Simple contrastive graph clustering[J/OL]. arXiv,[2022-06-26].https://arxiv.org/abs/2205.07865.
[22]	张汝榛, 张建林, 祁小平, 等. 复杂场景下的红外目标检测[J]. 光电工程,2020,47(10):128-137. ZHANG Ruzhen, ZHANG Jianlin, QI Xiaoping, et al. Infrared target detection and recognition in complex scene[J]. Opto-Electronic Engineering,2020,47(10):128-137.
[23]	LIN L K, WANG H Y, TANG Z X. Using deep learning to detect small targets in infrared oversampling images[J]. Journal of Systems Engineering and Electronics,2018,29(5):71-76.
[24]	蔡伟, 徐佩伟, 杨志勇, 等. 复杂背景下红外图像弱小目标检测[J]. 应用光学,2021,42(4):643-650. doi: 10.5768/JAO202142.0402002 CAI Wei, XU Peiwei, YANG Zhiyong, et al. Dim-small targets detection of infrared images in complex backgrounds[J]. Journal of Applied Optics,2021,42(4):643-650. doi: 10.5768/JAO202142.0402002
[25]	杜鹏. 复杂背景条件下红外弱小目标检测关键技术研究[D]. 新疆: 新疆大学, 2020. DU Peng. Research on key technology of infrared detection of dim and small target under complex background conditions[D]. Xinjiang: Xinjiang University, 2020.
[26]	PANG D D, SHAN T, LI W, et al. Facet derivative-based multidirectional edge awareness and spatial–temporal tensor model for infrared small target detection[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-15.
[27]	LI Q, NIE J Y, QU S C. A small target detection algorithm in infrared image by combining multi-response fusion and local contrast enhancement[J]. Optik International Journal for Light and Electron Optics,2021,241(3):166919.
[28]	陈紫强, 梁晨. 低虚警率的红外弱小目标检测算法[J/OL]. 电讯技术, [2022-07-11]. http://kns.cnki.net/kcms/detail/51.1267.TN.20211117.0837.002.html. CHEN Ziqiang, LIANG Chen. Infrared dim target detection algorithm with low false alarm rate[J/OL]. Telecommunication Engineering,[2022-07-11]. http://kns.cnki.net/kcms/detail/51.1267.TN.20211117.0837.002.html.
[29]	韩金辉, 蒋亚伟, 张小件, 等. 采用三层窗口局部对比度的红外小目标检测[J]. 红外与激光工程,2021,50(2):244-253. HAN Jinhui, JIANG Yawei, ZHANG Xiaojian, et al. Infrared small target detection using tri-layer window local contrast[J]. Infrared and Laser Engineering,2021,50(2):244-253.