基于高斯-拉普拉斯滤波的增强局部对比度红外小目标检测算法

doi:10.12382/bgxb.2021.0767

摘要/Abstract

摘要：

针对单帧图像红外小目标检测算法在低空复杂背景下虚警率高的问题,提出一种基于高斯-拉普拉斯(LOG)滤波的增强局部对比度算法来检测低空复杂背景下的红外小目标。通过LOG滤波运算快速提取候选目标像素,同时通过像素灰度指数运算增强目标。根据局部区域目标与背景的灰度特征计算目标显著图,通过自适应阈值分割提取目标。针对不同的低空复杂场景,构建了测试数据集,从信噪比增益、背景抑制因子、检测率、虚警率及算法计算效率方面将所提算法与Top-Hat算法、Max-median算法、RLCM算法、IPI算法及MPCM算法进行对比分析。实验结果表明,在不同场景中,所提算法相较于对比算法不仅具有较高的信噪比增益和背景抑制因子,而且具有较高的检测率、较低的虚警率和较高计算效率,验证了该算法的有效性和鲁棒性。

关键词: 目标检测, 红外小目标, 高斯-拉普拉斯滤波

Abstract:

To address the problem of high false alarm rate of single-frame infrared small-target detection algorithm in low-altitude and complex backgrounds, a Laplacian of Gaussian (LOG) filter-based enhanced local contrast algorithm is proposed. First, the candidate target pixels are extracted quickly by LOG filtering, while the target is enhanced using pixel grayscale indexing. Then, the target saliency map is calculated based on the grayscale features of the target and the background in the local area. Finally, the target is extracted by adaptive threshold segmentation. Test datasets are constructed for different low-altitude complex scenarios, and the proposed algorithm is compared with the Top-Hat algorithm, Max-median algorithm, RLCM algorithm, IPI algorithm, and MPCM algorithm in terms of signal-to-noise ratio gain, background rejection factor, detection rate, false alarm rate, and computational efficiency. Results show that in different scenarios, the newly proposed algorithm not only has higher signal-to-noise ratio gain and background rejection factor, but also has higher detection rate, lower false alarm rate and higher computational efficiency than other algorithms, demonstrating the method’s effectiveness and robustness.

Key words: target detection, infrared small target, LOG filtering

马鹏阁, 魏宏光, 孙俊灵, 陶然, 庞栋栋, 单涛, 蔡志勇, 刘兆瑜. 基于高斯-拉普拉斯滤波的增强局部对比度红外小目标检测算法[J]. 兵工学报, 2023, 44(4): 1041-1049.

MA Pengge, WEI Hongguang, SUN Junling, TAO Ran, PANG Dongdong, SHAN Tao, CAI Zhiyong, LIU Zhaoyu. A LOG Filter Based Enhanced Local Contrast Algorithm to Detect Infrared Small Targets[J]. Acta Armamentarii, 2023, 44(4): 1041-1049.

图/表 12

参考文献 20

[1]	QI S X, XU G J, MOU Z Y, et al. A fast-saliency method for real-time infrared small target detection[J]. Infrared Physics & Technology, 2016, 77:440-450.
[2]	QI H, MO B, LIU F X, et al. Small infrared target detection utilizing local region similarity difference map[J]. Infrared Physics and Technology, 2015, 71:131-139. doi: 10.1016/j.infrared.2015.03.007 URL
[3]	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. doi: 10.1016/j.patcog.2009.12.023 URL
[4]	DESHPANDE S D, MENG H E, RONDA V, et al. max-mean and max-median filters for detection of small-targets[J]. Proceedings of SPIE—The International Society for Optical Engineering, 1999, 3809(1):74-83.
[5]	李红艳, 吴成柯. 一种基于小波变换的序列图像中小目标检测与跟踪算法[J]. 电子与信息学报, 2001, 23(10):943-948.
	LI H Y, WU C K. A wavelet transform-based algorithm for small target detection and tracking in sequential images[J]. Journal of Electronics and Information, 2001, 23(10):943-948. (in Chinese)
[6]	GAO C Q, 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: a Publication of the IEEE Signal Processing Society, 2013, 22(12):4996-5009. doi: 10.1109/TIP.2013.2281420 URL
[7]	CHEN C L, LI H, WEI Y T, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience & Remote Sensing, 2013, 52(1):574-581.
[8]	HAN J H, MA Y, ZHOU B, et al. A robust infrared small target detection algorithm based on human visual system[J]. IEEE Geoscience & Remote Sensing Letters, 2014, 11(12):2168-2172.
[9]	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. doi: 10.1109/LGRS.2018.2790909 URL
[10]	WEI Y T, YOU X G, LO H. Multiscale patch-based contrast measure for small infrared target detection[J]. Pattern Recognition: The Journal of the Pattern Recognition Society, 2016, 58:216-226.
[11]	DENG L Z, ZHU H, TAO C, et al. Infrared moving point target detection based on spatial-temporal local contrast filter[J]. Infrared Physics & Technology, 2016, 76:168-173.
[12]	ZHAO B D, XIAO S Z, LU H Z, et al. Spatial-temporal local contrast for moving point target detection in space-based infrared imaging system[J]. Infrared Physics & Technology, 2018, 95:53-60.
[13]	DU P, HAMDULLA A. Infrared moving small-target detection using spatial-temporal local difference measure[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(10):1817-1821. doi: 10.1109/LGRS.8859 URL
[14]	LIU H K, ZHANG L, HUANG H. Small target detection in infrared videos based on spatio-temporal tensor model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(12):8689-8700. doi: 10.1109/TGRS.36 URL
[15]	PANG D D, SHAN T, MA P G, et al. A novel spatiotemporal saliency method for low-altitude slow small infrared target detection[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19:1-5.
[16]	MORADI S, MOLLEM 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. doi: 10.1016/j.infrared.2016.05.007 URL
[17]	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. doi: 10.5768/JAO201738.0106003
	ZHOU Y, ZHANG J M, LIN X. Research on infrared dim small target detection method based on weighted LOG operator[J]. Applied Optics, 2017, 38(1):114-119. (in Chinese)
[18]	CUO 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. doi: 10.1016/j.measurement.2016.05.071 URL
[19]	段思韦, 王忠华, 叶铮. 空域加权局部对比度的红外小目标检测算法[J]. 激光与红外, 2020, 50(10):1200-1206.
	DUAN S W, WANG Z H, YE Z. Infrared small target detection algorithm with space-weighted local contrast[J]. Laser and Infrared, 2020, 50(10):1200-1206. (in Chinese)
[20]	PANG D D, SHAN T, LI W, et al. Infrared dim and small target detection based on greedy bilateral factorization in image sequences[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:3394-3408. doi: 10.1109/JSTARS.4609443 URL

组编号	帧数	图像分辨率/像素	背景描述	目标
Group 1	57	281×209	较弱云杂波多目标场景	无人机
Group 2	97	281×209	较强云杂波空天场景	无人机
Group 3	125	281×209	目标淹没在较强云杂波空天场景	无人机
Group 4	86	281×209	背景复杂的低空场景	无人机
Group 5	67	281×209	较强杂波低空场景	无人机
Group 6	147	640×512	田地少建筑物低空场景	直升机
Group 7	86	640×512	多建筑物低空场景	直升机

组编号	帧数	图像分辨率/像素	背景描述	目标
Group 1	57	281×209	较弱云杂波多目标场景	无人机
Group 2	97	281×209	较强云杂波空天场景	无人机
Group 3	125	281×209	目标淹没在较强云杂波空天场景	无人机
Group 4	86	281×209	背景复杂的低空场景	无人机
Group 5	67	281×209	较强杂波低空场景	无人机
Group 6	147	640×512	田地少建筑物低空场景	直升机
Group 7	86	640×512	多建筑物低空场景	直升机

算法	Group 1	Group 2	Group 3	Group 4	Group 5	Group 6	Group 7
Top-Hat算法^[3]	90.82	97.94	89.61	77.78	59.65	82.99	83.72
Max-median算法^[4]	94.89	96.53	73.63	91.86	84.21	76.87	73.25
RLCM算法^[9]	87.76	96.91	89.92	90.81	87.72	92.52	91.86
IPI算法^[6]	94.92	98.97	96.82	95.41	91.23	80.27	67.44
MPCM算法^[10]	93.88	96.91	88.82	91.52	86.67	72.11	63.95
本文算法	96.47	100.00	93.19	98.63	95.87	95.59	98.92

算法	Group 1	Group 2	Group 3	Group 4	Group 5	Group 6	Group 7
Top-Hat算法^[3]	90.82	97.94	89.61	77.78	59.65	82.99	83.72
Max-median算法^[4]	94.89	96.53	73.63	91.86	84.21	76.87	73.25
RLCM算法^[9]	87.76	96.91	89.92	90.81	87.72	92.52	91.86
IPI算法^[6]	94.92	98.97	96.82	95.41	91.23	80.27	67.44
MPCM算法^[10]	93.88	96.91	88.82	91.52	86.67	72.11	63.95
本文算法	96.47	100.00	93.19	98.63	95.87	95.59	98.92

算法	Group 1	Group 2	Group 3	Group 4	Group 5	Group 6	Group 7
Top-Hat算法^[3]	14.29	4.12	12.82	22.22	24.56	-	-
Max-median算法^[4]	12.24	5.16	41.61	10.47	28.07	-	-
RLCM算法^[9]	16.32	3.09	12.42	10.35	15.79	21.09	18.61
IPI算法^[6]	7.42	2.06	8.16	9.19	12.28	-	-
MPCM算法^[10]	6.22	7.23	16.80	10.65	15.35	-	-
本文算法	5.24	1.58	8.43	4.86	7.39	10.69	6.68