基于改进顶帽变换的红外弱小目标检测

张晶晶; 曹思华; 崔文楠; 张涛

doi:10.11999/JEIT221562

基于改进顶帽变换的红外弱小目标检测

doi: 10.11999/JEIT221562

张晶晶^{1, 4, 5, ,},
曹思华¹,
崔文楠^{2, 3},
张涛^{2, 3}

1.
中国地质大学(武汉)自动化学院武汉 430074
2.
中国科学院智能红外感知重点实验室上海 200083
3.
中国科学院上海技术物理研究所上海 200083
4.
复杂系统先进控制与智能自动化湖北省重点实验室武汉 430074
5.
地球探测智能化技术教育部工程研究中心武汉 430074

基金项目: 中国科学院智能红外感知重点实验室开放课题(CAS-IIRP-2021-03)

详细信息

作者简介:
张晶晶：男，博士，副教授，博士生导师，研究方向为计算成像、图像处理

曹思华：女，硕士生，研究方向为目标检测

崔文楠：男，博士，研究员，硕士生导师，研究方向为光电探测、红外仿真、图像处理

张涛：男，博士，研究员，博士生导师，研究方向为光电成像及微弱信号处理

通讯作者:
张晶晶　jingjingzhang@cug.edu.cn

中图分类号: TN911.7; TP391
计量
- 文章访问数: 327
- HTML全文浏览量: 185
- PDF下载量: 115
- 被引次数: 0
出版历程
- 收稿日期: 2022-12-21
- 修回日期: 2023-04-23
- 网络出版日期: 2023-04-27
- 刊出日期: 2024-01-17

Improved Top-hat Transform–based Algorithm for Infrared Dim and Small Target Detection

ZHANG Jingjing^{1, 4, 5
, ,},
CAO Sihua¹,
CUI Wennan^{2, 3},
ZHANG Tao^{2, 3}

1.
School of Automation, China University of Geosciences, Wuhan 430074, China
2.
Key Laboratory of Intelligent Infrared Perception, Chinese Academy of Sciences, Shanghai 200083, China
3.
Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China
4.
Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan 430074, China
5.
Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan 430074, China

Funds: Open project of Key Laboratory of Intelligent Infrared Perception, Chinese Academy of Sciences (CAS-IIRP-2021-03)

摘要

摘要: 天空背景下的红外弱小目标检测技术较为成熟，但在近地复杂背景下，红外弱小目标的检测存在准确率不高、虚警目标多、实时性差的问题。针对以上问题，该文提出一种基于改进顶帽变换的红外弱小目标检测算法(OTHOLCM)。该算法采用基于改进顶帽变换的图像预处理算法(OTH)，通过对不同灰度值的图像采取不同的策略针对性地处理图像，达到目标增强、背景抑制的效果。并在此基础上，采用基于改进多尺度局部对比度的红外弱小目标检测算法(OLCM)，通过针对目标尺寸特点进行尺度设计，使得在保证算法实时性的基础上扩大目标尺寸检测范围。实验证明：OTHOLCM算法可以保证实时性并明显提高目标检测准确率、减少虚警目标数量。与3层模板局部差异度量算法(TTLDM)、基于边角感知的时空张量模型(ECASTT)等先进算法相比，OTHOLCM算法可使真阳性率分别提高近79%, 61%，假阳性率分别降低近77%, 73%，目标检测速度达到每秒25帧。
- 红外弱小目标 /
- 目标检测 /
- 顶帽变换 /
- 局部对比度 /
- 目标增强
Abstract: The technology for detecting infrared dim and small targets in the sky background is relatively mature. However, detecting these targets in near-ground complex backgrounds poses challenges such as low accuracy, high false alarm rates, and poor real-time performance. To address these problems, a novel algorithm for detecting infrared dim and small targets based on an improved top-hat transform, referred to as OTHOLCM, is proposed in this study. The algorithm uses an image preprocessing method, OTH, based on an improved top-hat transformation to enhance the target and suppress the background. Different strategies are employed to process images with different gray values. Additionally, the algorithm uses an infrared dim and small target detection technique, OLCM, based on improved multi-scale local contrast. The OLCM uses target size characteristics to expand the target detection range while ensuring real-time performance. Experimental results show that the OTHOLCM algorithm can guarantee good real-time performance, improve target detection accuracy, and reduce the number of false alarms. Compared with advanced algorithms such as the three-layer template local difference measurement algorithm and the edge and corner awareness-based spatial-temporal tensor, the OTHOLCM algorithm increases the actual positive rate by almost 79% and 61%, respectively. In addition, it reduces the false positive rate by nearly 77% and 73%, respectively. Moreover, the target detection speed reaches 25 frames per second.
- Infrared dim and small targets /
- Target detection /
- Top-hat transform /
- Local contrast /
- Target enhancement

HTML全文

图 1 改进白顶帽变换算法处理结果及其3维灰度图对比图

下载: 全尺寸图片幻灯片

图 2 不同场景和学习系数组合情况下的目标检测结果对比图

下载: 全尺寸图片幻灯片

图 3 OLCM算法和MLCM算法检测结果比较图

下载: 全尺寸图片幻灯片

图 4 先进目标检测算法目标检测结果对比图

下载: 全尺寸图片幻灯片

图 5 先进目标检测算法目标检测结果

下载: 全尺寸图片幻灯片

表 1 不同系数组合下OTHOLCM算法性能的对比

实验组	学习系数组合	Precision(%)	TPR(%)	FPR(%)	SNR
1	(0.1,0.6,0.3)	12.35	90.63	0.28	3.33
2	(0.2,0.6,0.3)	9.92	91.25	0.33	2.78
3	(0.3,0.6,0.3)	9.53	91.25	0.34	2.40
4	(0.1,0.5,0.3)	11.65	85.59	0.32	3.50
5	(0.1,0.7,0.3)	10.84	93.75	0.31	3.20
6	(0.1,0.6,0.2)	12.39	93.75	0.32	2.71
7	(0.1,0.6,0.4)	10.52	90.00	0.31	2.99

下载: 导出CSV

表 2 图像预处理算法性能对比结果

指标	SAMF^[3]	AF^[4]	CABF^[10]	DWTH^[20]	CWTH^[7]	IDCP^[22]	CWBTH^[23]	OTH
时间(s)	0.15	0.07	0.12	0.01	0.07	0.15	0.14	0.01
SNR(dB)	1.53	1.51	2.33	4.62	41.94	5.02	5.85	5.52

下载: 导出CSV

表 3 经典目标检测算法性能对比结果

指标	IPI^[13]	PSTNN^[14]	Top-hat^[7]	MPCM^[17]	RLCM^[18]	MLCM^[15]	OLCM
时间(s)	3.582	0.102	0.002	0.039	1.718	0.040	0.053
AUC	0.533	0.524	0.551	0.624	0.776	0.804	0.851

下载: 导出CSV

表 4 先进算法和组合目标检测算法性能对比

指标	MLCM	OLCM	IDCPLCM	CWBLCM	OTHLCM	IDCPOLCM	CWBOLCM	OTHOLCM
时间(s)	0.040	0.053	0.140	0.140	0.043	0.142	0.032	0.045
AUC	0.805	0.852	0.803	0.833	0.846	0.852	0.878	0.893

下载: 导出CSV

表 5 先进目标检测算法性能对比(%)

指标	OLCM	OTHOLCM	ECASTT^[24]	TTLDM^[19]
TPR	95.17	95.35	34.76	16.82
FPR	14.94	12.35	85.17	89.23

下载: 导出CSV

参考文献(24)

[1]	于强, 黄树彩, 赵炜, 等. 红外弱小目标检测方法综述[J]. 飞航导弹, 2014(4): 59–63,94. doi: 10.16338/j.issn.1009-1319.2014.04.020 YU Qiang, HUANG Shucai, ZHAO Wei, et al. Infrared dim and small target detection: A review[J]. Aerodynamic Missile Journal, 2014(4): 59–63,94. doi: 10.16338/j.issn.1009-1319.2014.04.020
[2]	杜鹏. 复杂背景条件下红外弱小目标检测关键技术研究[D]. [博士论文], 新疆大学, 2020: 6. DU Peng. Research on key technology of infrared detection of dim and small target under complex background conditions[D]. [Ph. D. dissertation], Xinjiang University, 2020: 6.
[3]	HWANG H and HADDAD R A. Adaptive median filters: New algorithms and results[J]. IEEE Transactions on Image Processing, 1995, 4(4): 499–502. doi: 10.1109/83.370679
[4]	BOVIK A C. Introduction to digital image and video processing[M]. BOVIK A. Handbook of Image and Video Processing. 2nd ed. Burlington: Academic Press, 2010: 102–105.
[5]	樊华. 红外弱小目标检测跟踪技术研究[D]. [硕士论文], 北华航天工业学院, 2021: 10. FAN Hua. Research on infrared dim small target detection and tracking technology[D]. [Master dissertation], North China Institute of Aerospace Engineering, 2021: 10.
[6]	TOMASI C and MANDUCHI R. Bilateral filtering for gray and color images[C]. Proceedings of the Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271), Bombay, India, 1998: 839–846.
[7]	BAI Xiangzhi and ZHOU Fugen. Analysis of new top-hat transformation and the application for infrared dim small tar-get detection[J]. Pattern Recognition, 2010, 43(6): 2145–2156. doi: 10.1016/j.patcog.2009.12.023
[8]	杨卫平, 沈振康. 红外图像序列小目标检测预处理技术[J]. 红外与激光工程, 1998, 27(1): 23–28. YANG Weiping and SHEN Zhenkang. Small target detection and preprocessing technology in infrared image sequences[J]. Infrared and Laser Engineering, 1998, 27(1): 23–28.
[9]	高陈强, 张天骐, 李强, 等. 几种典型红外弱小目标检测算法的性能评估[J]. 重庆邮电大学学报(自然科学版), 2010, 22(3): 386–391. GAO Chenqiang, ZHANG Tianqi, LI Qiang, et al. Performance evaluation of several typical infrared weak and small target detection algorithms[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2010, 22(3): 386–391.
[10]	NAIR P, GAVASKAR R G, and CHAUDHURY K N. Compressive adaptive bilateral filtering[C]. Proceedings of the ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020: 2078–2082.
[11]	白相志, 周付根, 解永春, 等. 新型Top-hat变换及其在红外小目标检测中的应用[J]. 数据采集与处理, 2009, 24(5): 643–649. doi: 10.16337/j.1004-9037.2009.05.002 BAI Xiangzhi, ZHOU Fugen, XIE Yongchun, et al. New top-hat transformation and application on infrared small target detection[J]. Journal of Data Acquisition and Processing, 2009, 24(5): 643–649. doi: 10.16337/j.1004-9037.2009.05.002
[12]	DENG Lizhen, ZHANG Jieke, XU Guoxia, et al. Infrared small target detection via adaptive M-estimator ring top-hat transformation[J]. Pattern Recognition, 2021, 112: 107729. doi: 10.1016/j.patcog.2020.107729
[13]	GAO Chenqiang, MENG Deyu, YANG Yi, 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
[14]	ZHANG Landan and PENG Zhenming. Infrared small target detection based on partial sum of the tensor nuclear norm[J]. Remote Sensing, 2019, 11(4): 382. doi: 10.3390/rs11040382
[15]	CHEN C L P, LI Hong, WEI Yantao, 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
[16]	鞠默然, 罗海波, 刘广琦, 等. 采用空间注意力机制的红外弱小目标检测网络[J]. 光学精密工程, 2021, 29(4): 843–853. doi: 10.37188/OPE.20212904.0843 JU Moran, LUO Haibo, LIU Guangqi, et al. Infrared dim and small target detection network based on spatial attention mechanism[J]. Optics and Precision Engineering, 2021, 29(4): 843–853. doi: 10.37188/OPE.20212904.0843
[17]	WEI Yantao, YOU Xinge, and LI Hong. 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
[18]	HAN Jinhui, LIANG Kun, ZHOU Bo, 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
[19]	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.20223007.0869 MU 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
[20]	邓剑鑫. 红外弱小目标检测方法研究[D]. [硕士论文], 哈尔滨理工大学, 2021: 13–17. DENG Jianxin. Research on infrared weak and small target detection method[D]. [Master dissertation], Harbin University of Science and Technology, 2021: 13–17.
[21]	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[EB/OL]. 中国科学数据. https://doi.org/10.11922/sciencedb.902,2020, 2019. HUI Bingwei, SONG Zhiyong, FAN Hongqi, et al. A dataset for infrared image dim-small aircraft target detection and tracking under ground / air background[EB/OL]. Science Data Bank. https://doi.org/10.11922/sciencedb.902,2020, 2019.
[22]	王亚平, 周裕丰, 张宝华. 基于去雾增强和张量恢复的红外小目标检测[J]. 红外与激光工程, 2022, 51(4): 20210417. doi: 10.3788/IRLA20210417 WANG Yaping, ZHOU Yufeng, and ZHANG Baohua. Infrared small target detection based on Dehazing enhancement and tensor recovery[J]. Infrared and Laser Engineering, 2022, 51(4): 20210417. doi: 10.3788/IRLA20210417
[23]	李斌. 基于图像增强的红外小目标检测技术研究与系统开发[D]. [硕士论文], 新疆大学, 2021: 17–21. LI Bin. Research and system development of infrared small target detection technology based on image enhancement[D]. [Master dissertation], Xinjiang University, 2021: 17–21.
[24]	ZHANG Ping, ZHANG Lingyi, WANG Xiaoyang, et al. Edge and corner awareness-based spatial–temporal tensor model for infrared small-target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(12): 10708–10724. doi: 10.1109/TGRS.2020.3037938