Aerial Infrared Target Detection Based on Polarization Feature Reconstruction and Local Difference Measurement

doi:10.19678/j.issn.1000-3428.0252022

Abstract

Abstract:

Under complex sky backgrounds, the low local contrast between small targets and backgrounds reduces the accuracy of infrared intensity detection. Although infrared polarization imaging can effectively improve the local contrast between targets and backgrounds, it also raises the contrast of high-brightness background edges, bringing new challenges to target detection. To solve this problem, an aerial infrared small target detection method based on polarization feature reconstruction and local difference metric weighting is proposed in this paper. Firstly, considering the unique gradient characteristics of small targets, a global background gradient feature suppression matrix for Stokes vector components S₁ and S₂ is constructed by using image gradient vector information. Secondly, in view of the spatial correlation between S₁ and S₂, a polarization feature reconstruction method is established to suppress most background clutter while retaining target features. Meanwhile, according to the feature differences among targets, residual background and noise, an improved Variance Change Rate of Local Region (VSL) is proposed to quantify the complexity of local regions, so as to better suppress residual background. Comparative experiments with LCM, TLLCM, IPI, PSTNN and other algorithms are conducted in multiple scenarios. The experimental results show that the Signal-to-Clutter Ratio (SCR), Signal-to-Clutter Ratio Gain (SCRG) and Background Suppression Factor (BSF) of the proposed method are increased by 14.06%, 4.79% and 14.43% compared with the suboptimal algorithm, respectively. It can maintain excellent detection performance under various complex backgrounds and possesses strong robustness.

Key words: infrared polarization, background suppression, gradient vector, polarization feature reconstruction, weight function

摘要：

复杂天空背景下, 小目标与背景局部对比度低导致红外强度检测的准确率降低。红外偏振成像技术能有效提高目标与背景之间的局部对比度, 但同时也带来了背景高亮边缘处的对比度提升, 给检测工作带来新的挑战。针对这一问题, 提出一种基于偏振特征重构与局部差异度量加权的空中红外目标检测方法。首先, 该方法考虑了小目标独有的梯度特性, 通过图像的梯度矢量信息构建了偏振特征(Stokes矢量分量S₁、S₂)的全局背景梯度特征抑制矩阵。然后, 考虑到S₁、S₂之间的空间关联性, 构建了一种偏振特征重构方法, 在保留目标的同时抑制了绝大多数背景杂波。同时, 根据目标、残留背景、噪声之间的特征差异, 提出一种改进的局部灰度值方差变化率(VSL)来估计局部区域的复杂程度, 从而更好地实现残留背景的抑制。在不同场景下与LCM、TLLCM、IPI、PSTNN等算法进行对比, 实验结果表明, 该方法信杂比(SCR)、信杂比增益(SCRG)和背景抑制因子(BSF)分别较次优算法提高了14.06%、4.79%和14.43%, 且在不同类型背景下均能取得良好的目标检测性能, 具有较好的鲁棒性。

关键词: 红外偏振, 背景抑制, 梯度矢量, 偏振特征重构, 权重函数

HU Quan, HU Yunyou, MENG Xianmeng, ZHANG Siwei, FAN Zhiguo. Aerial Infrared Target Detection Based on Polarization Feature Reconstruction and Local Difference Measurement[J]. Computer Engineering, 2026, 52(9): 165-175.

胡泉, 胡运优, 孟宪猛, 张思维, 范之国. 基于偏振特征重构与局部差异度量的空中红外目标检测[J]. 计算机工程, 2026, 52(9): 165-175.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0252022

https://www.ecice06.com/EN/Y2026/V52/I9/165

Figures/Tables 12

Fig.1 Infrared intensity image and DoLP image

Fig.2 Infrared polarization feature images

Fig.3 DoLP image and reconstructed polarization feature image

Fig.4 Reconstructed polarization feature image, residual edge window, and target window

Fig.5 Weight map and 3D weight distribution of reconstructed polarization feature image

Fig.6 Flow chart of the algorithm

Fig.7 Infrared polarization imaging system and polarization data for different scenes

Fig.8 Detection results of different methods

Fig.9 ROC curves for Scene 1 to Scene

Fig.10 Results of ablation experiments

References 29

1	MA J K , GUO H R , RONG S H , et al. Infrared dim and small target detection based on background prediction. Remote Sensing, 2023, 15 (15): 3749. doi: 10.3390/rs15153749
2	LIU F C , GAO C Q , CHEN F , et al. Infrared small and dim target detection with transformer under complex backgrounds. IEEE Transactions on Image Processing, 2023, 32, 5921- 5932. doi: 10.1109/TIP.2023.3326396
3	张景程, 乔新博, 赵永强. 红外偏振摄像机动目标检测跟踪系统(特邀). 红外与激光工程, 2022, 51 (4): 115- 124.
	ZHANG J C , QIAO X B , ZHAO Y Q . Maneuvering object detection and tracking system based on infrared polarization imaging (invited). Infrared and Laser Engineering, 2022, 51 (4): 115- 124.
4	ZHAO M J , LI W , LI L , et al. Single-frame infrared small-target detection: a survey. IEEE Geoscience and Remote Sensing Magazine, 2022, 10 (2): 87- 119. doi: 10.1109/MGRS.2022.3145502
5	GAO C Q , MENG D Y , YANG Y , et al. Infrared patch-image model for small target detection in a single image. IEEE Transactions on Image Processing, 2013, 22 (12): 4996- 5009. doi: 10.1109/TIP.2013.2281420
6	ZHANG L D , PENG Z M . Infrared small target detection based on partial sum of the tensor nuclear norm. Remote Sensing, 2019, 11 (4): 382. doi: 10.3390/rs11040382
7	LU C Y , FENG J S , CHEN Y D , et al. Tensor robust principal component analysis with a new tensor nuclear norm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (4): 925- 938. doi: 10.1109/TPAMI.2019.2891760
8	CHEN C L P , LI H , WEI Y T , et al. A local contrast method for small infrared target detection. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52 (1): 574- 581. doi: 10.1109/TGRS.2013.2242477
9	HAN J H , MORADI S , FARAMARZI I , et al. A local contrast method for infrared small-target detection utilizing a tri-layer window. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (10): 1822- 1826. doi: 10.1109/LGRS.2019.2954578
10	TANG Y , XIONG K , WANG C X . Fast infrared small target detection based on global contrast measure using dilate operation. IEEE Geoscience and Remote Sensing Letters, 2023, 20, 8000105.
11	吴强, 刘华凯, 稂时楠. 基于HVS的空中红外小目标快速检测算法. 计算机工程, 2019, 45 (5): 210-215, 221. doi: 10.19678/j.issn.1000-3428.0050823
	WU Q , LIU H K , LANG S N . Aerial infrared small target fast detection algorithm based on HVS. Computer Engineering, 2019, 45 (5): 210-215, 221. doi: 10.19678/j.issn.1000-3428.0050823
12	FORSSELL G. Test and analysis of the detectability of personnel mines in a realistic minefield by polarization in the infrared LW region[C]//Detection and Remediation Technologies for Mines and Minelike Targets IX. Orlando, USA: SPIE, 2004: 187.
13	ARON Y, GRONAU Y. Polarization in the LWIR: a method to improve target acquisition[C]//Infrared Technology and Applications XXXI. Orlando, USA: SPIE, 2005: 653-661.
14	赵永强, 张景程, 乔新博. 基于偏振权重局部对比度的目标检测. 红外与毫米波学报, 2023, 42 (1): 102- 110.
	ZHAO Y Q , ZHANG J C , QIAO X B . Object detection based on polarization-weighted local contrast method. Journal of Infrared and Millimeter Waves, 2023, 42 (1): 102- 110.
15	RATLIFF B M, LEMASTER D A, MACK R T, et al. Detection and tracking of RC model aircraft in LWIR microgrid polarimeter data[C]//Polarization Science and Remote Sensing V. San Diego, USA: SPIE, 2011: 29-41.
16	ZHAI H, LUO X L, JIANG Z Z, et al. Infrared polarization detection method for weak target in sky background[C]//Proceedings of the AOPC 2020: Optical Sensing and Imaging Technology. Beijing, China: SPIE, 2020: 212-221.
17	宋敏敏, 王爽, 吕弢. 红外偏振成像下的弱小目标检测. 红外, 2015, 36 (10): 1- 4.
	SONG M M , WANG S , LÜ T . Detection of dim target with infrared polarization imaging. Infrared, 2015, 36 (10): 1- 4.
18	LIU M, DU H Y, ZHAO Y J, et al. Image small target detection based on deep learning with SNR controlled sample generation[C]//Current Trends in Computer Science and Mechanical Automation Vol. 1: Selected Papers from CSMA2016. [S. l. ]: de Gruyter, 2022: 211-220.
19	DAI Y M , WU Y Q , ZHOU F , et al. Attentional local contrast networks for infrared small target detection. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59 (11): 9813- 9824. doi: 10.1109/TGRS.2020.3044958
20	寻华生, 张晶晶, 刘晓, 等. 基于偏振图像的低照度场景多目标检测算法. 红外技术, 2022, 44 (5): 483- 491.
	XUN H S , ZHANG J J , LIU X , et al. Multi-target detection of low-illuminance scene based on polarization image. Infrared Technology, 2022, 44 (5): 483- 491.
21	沈英, 张硕, 王舒, 等. 复杂场景伪装小目标机载偏振遥感检测方法. 兵工学报, 2025, 46 (7): 339- 350.
	SHEN Y , ZHANG S , WANG S , et al. A method for detecting the camouflaged small target in complex scene using airborne polarization remote sensing. Acta Armamentarii, 2025, 46 (7): 339- 350.
22	WANG X , LÜ G F , XU L Z . Infrared dim target detection based on visual attention. Infrared Physics & Technology, 2012, 55 (6): 513- 521.
23	LOWE D G . Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60 (2): 91- 110. doi: 10.1023/B:VISI.0000029664.99615.94
24	ZHANG X Y , RU J Y , WU C D . Infrared small target detection based on gradient correlation filtering and contrast measurement. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61, 5603012.
25	CHEN J , WU K L , CHENG Z , et al. A saliency-based multiscale approach for infrared and visible image fusion. Signal Processing, 2021, 182, 107936. doi: 10.1016/j.sigpro.2020.107936
26	LÜ P Y , SUN S L , LIN C Q , et al. A method for weak target detection based on human visual contrast mechanism. IEEE Geoscience and Remote Sensing Letters, 2019, 16 (2): 261- 265. doi: 10.1109/LGRS.2018.2866154
27	ZHANG T F , LI L , CAO S Y , et al. Attention-guided pyramid context networks for detecting infrared small target under complex background. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59 (4): 4250- 4261. doi: 10.1109/TAES.2023.3238703
28	石瑞年, 何强, 王恒友, 等. 动态运动约束下的视频异常检测. 重庆邮电大学学报(自然科学版), 2025, 37 (1): 110- 120.
	SHI R N , HE Q , WANG H Y , et al. Dynamic motion constraints for video anomaly detection. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2025, 37 (1): 110- 120.
29	孔祥阳, 赵永强, 彭群聂, 等. 基于互结构正则约束的红外偏振图像增强算法. 光子学报, 2020, 49 (5): 160- 165.
	KONG X Y , ZHAO Y Q , PENG Q N , et al. Infrared polarization image enhancement algorithm based on mutual structure regularization constraint. Acta Photonica Sinica, 2020, 49 (5): 160- 165.

[1]	WANG Li,XU Tiantian. An Improved Canny Algorithm in GVF Snake Model [J]. Computer Engineering, 2016, 42(10): 231-235,241.
[2]	JIANG Donglin,LIN Zhenmei,WANG Meiqing. AOS Implementation of Improved Geodesic Active Contour Model [J]. Computer Engineering, 2014, 40(11): 220-224.
[3]	XU Dun-Gong, DING Chun-Feng, SU Hai-Bin, WANG Ting-Ling. Moving Object Extraction Algorithm Based on Improved GVF [J]. Computer Engineering, 2012, 38(9): 199-201.
[4]	HONG You-Sheng, ZHANG Li-Jie, WANG Zhi-Dong, CHEN Jian-Xin. Automatic Edge Detection Method of Intravascular Ultrasound Image Sequence [J]. Computer Engineering, 2012, 38(20): 200-203.
[5]	DU Hai-Long, TUN Ti-Sheng. New GVF-Snake Model [J]. Computer Engineering, 2011, 37(9): 196-197,200.
[6]	WANG Yu; ZHANG Jian-wei; CHEN Yun-jie; ZHAN Tian-ming; RUAN Jing. New GVF Model Based on Non-linear Diffusion [J]. Computer Engineering, 2010, 36(4): 215-217.
[7]	CHEN Shen, HOU Yu-Jing, YANG Xu-Lang, HAN Min. CHEN Shen, HOU Yu-qing, YANG Xu-lang, HAN Min [J]. Computer Engineering, 2010, 36(10): 193-195.
[8]	WANG Yong; XUE Mu-gen; HUANG Qin-chao. Polarization Dehazing Algorithm Based on Atmosphere Background Suppression [J]. Computer Engineering, 2009, 35(4): 271-273.
[9]	LI Qi-he; LUO Yu-pin; XIAO De-yun. Image Segmentation Algorithm Based on Nodes of Vector Flow Field [J]. Computer Engineering, 2009, 35(4): 223-225.
[10]	CHE Jian-bo; YE De-qian. Segmentation and Tracking of Moving Object Based on Prior Information [J]. Computer Engineering, 2009, 35(12): 140-142.
[11]	CAO Zhi-Jiang; HAO Kuang-rong; DING Yong-sheng;. Optimization Algorithm Based on GVF-Snake for Body Contour Extraction [J]. Computer Engineering, 2008, 34(22): 204-206.
[12]	WANG Bin; SUN Lei. Classification of Tumor Shape Feature Based on Support Vector Machine [J]. Computer Engineering, 2007, 33(17): 46-48.

Please choose a citation manager

Content to export