基于特征波段偏振成像的差异增强伪装目标检测

doi:10.12382/bgxb.2023.0761

摘要/Abstract

摘要：

光谱偏振探测技术利用目标多维度信息,提高伪装目标检测的精度和可靠性。现有的光谱偏振成像系统产生的高维度数据难以实时解算,复杂场景下光谱偏振探测的性能不佳。为此,提出一种基于特征波段偏振成像系统的伪装目标检测算法。针对目标场景筛选特征波段,定制751nm窄带滤光片结合快照式偏振阵列相机,构建特征波段偏振图像采集系统,实时获取目标图像。提出差异增强和交织序列融合检测算法,设计偏振参数图像,增强特征波段偏振图像的目标对比度;融合差异增强和交织序列映射结果,对目标图像背景噪声进行抑制,进一步突出目标特征;通过阈值分割提取伪装目标。实验结果表明:所提的伪装目标检测算法在不同场景下的综合评价指标F均在0.90以上,检测速度达到20帧/s,实现了复杂场景下伪装目标的快速精准探测。

关键词: 伪装目标检测, 光谱偏振图像, 成像系统, 特征波段, 差异增强

Abstract:

The spectral polarization detection technology utilizes the multidimensional information to improve the accuracy and reliability of camouflage target detection. The high-dimensional data generated by the existing spectral polarization imaging systems are difficultly processedin real-time, and the performance of spectral polarization detection in complex scenes is unsatisfied. To address this concern, a contrast enhancement camouflage target detection algorithm based on feature band polarization imaging is proposed. Specific feature bands are selected for the target scenes, and a feature band polarization image acquisition system is constructed by combining a 751nm narrowband filter with a snapshot polarized array camera to capture the feature band polarization images in real-time. Additionally, acontrast enhancement and interleaved sequence fusion detection (CEISFD) algorithm is proposed. It enhances the target contrast in the feature band polarization images through the designed polarization parameter image. The CEISFD algorithm fuses the results of contrast enhancement and interleaved sequence mapping, thus suppressing the background noises in the target images and further highlighting the target features. The camouflage target is then extracted by threshold segmentation. Experimental results demonstrate that the proposed algorithm achieves comprehensive evaluation metrics F above 0.90 in various scenarios, and its detection rate reaches 20 FPS, enabling fast and accurate detection of camouflage targets in complex environments.

Key words: camouflage target detection, spectral polarization image, imaging system, feature band, contrast enhancement

中图分类号:

TP391

沈英, 黄伟达, 周则兵, 黄峰, 王舒. 基于特征波段偏振成像的差异增强伪装目标检测[J]. 兵工学报, 2024, 45(10): 3488-3498.

SHEN Ying, HUANG Weida, ZHOU Zebing, HUANG Feng, WANG Shu. Contrast Enhancement for Camouflage Target Detection Based on Feature Band Polarization Imaging[J]. Acta Armamentarii, 2024, 45(10): 3488-3498.

图/表 10

图1 基于SPI的伪装目标检测算法流程

Fig.1 Flowchart of camouflage target detection algorithm based on SPI

表1 实验条件

Table 1 Experimental conditions

实验名称	背景	距离/ m	入射角度/(°)	数据类型
波段筛选	草地	15	60	偏振多光谱图像
不同角度检测	草地	15	15,30, 45,60,75	SPI,VPI
小目标检测	草地	20	60	SPI,VPI
不同背景检测	草地、灌木、荒地	15	60	SPI,VPI
对比度增强	草地、灌木、荒地	15	60	SPI

图2 不同波段下参数图像的目标对比度

Fig.2 Target contrast of parameter images in different bands

表2 751nm波段下不同背景参数图像的目标对比度

Table 2 Target contrast of parameter images in different backgrounds at 751nm band

背景	I_dolp,_s	I_d,_s	增长率/%
草地	0.58	0.85	46.55
灌木	0.38	0.50	31.58
荒地	0.59	0.75	27.12

表3 751nm波段下不同背景的参数图像

Table 3 Parameter images in different backgrounds at 751nm band

图3 不同入射角下各算法检测结果对比

Fig.3 Comparison of detected results of different algorithms at different incidence angles

表4 不同入射角下各算法检测结果

Table 4 Detected results of different algorithms at different incidence angles

图4 不同场景下各算法检测结果对比

Fig.4 Comparison of detected results of different algorithms in different scenarios

表5 不同场景下各算法检测结果

Table 5 Detected results of different algorithms in different scenarios

表6 CEISF检测算法计算效率

Table 6 Computational efficiency of CEISF algorithm

组别	草地	草地小目标	灌木	荒地
运行时间/ms	36.26	38.15	37.52	38.33

参考文献 25

[1]	SHEN Y, LI J, LIN W F, et al. Camouflaged target detection based on snapshot multispectral imaging[J]. Remote Sensing, 2021, 13(19): 3949.
[2]	甘鑫, 高欣健, 钟彬彬, 等. 基于有限样本的大气偏振模式生成方法[J]. 光电工程, 2021, 48(5): 200331.
	GAN X, GAO X J, ZHONG B B, et al. A few-shot learning based generative method for atmospheric polarization modelling[J]. Opto-Electronic Engineering, 2021, 48(5): 200331. (in Chinese)
[3]	KARIM S, TONG G, LI J, et al. Current advances and future perspectives of image fusion: a comprehensive review[J]. Information Fusion, 2023, 90: 185-217.
[4]	SATTAR S, LAPRAY P, FOULONNEAU A. Review of spectral and polarization imaging systems[J]. Proceedings of SPIE, 2020, 11351: 113511Q.
[5]	WANG X, ZHANG Y H, MA X, et al. Compressive spectral imaging system based on liquid crystal tunable filter[J]. Optics Express, 2018, 26(19): 25226-25243. doi: 10.1364/OE.26.025226 pmid: 30469627
[6]	ZHOU P W, WANG Y, HE Z E, et al. Blurred spectral images restoration technology for AOTF imaging spectrometer based on dual-path architecture[J]. Optics Express, 2022, 30(12): 21746-21757. doi: 10.1364/OE.459972 pmid: 36224887
[7]	李虎, 刘雪峰, 姚旭日, 等. 并行压缩感知计算层析成像光谱[J]. 光谱学与光谱分析, 2023, 43(2): 348-355.
	LI H, LIU X F, YAO X R, et al. Blockcompressed sensing computed tomography imaging spectrometry[J]. Spectroscopy and Spectral Analysis, 2023, 43(2): 348-355. (in Chinese)
[8]	ZHANG Y, WANG H, SUN J H, et al. Real-time polarization spectral detection based on a dual-dispersion and coded-aperture imaging system[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5602412.
[9]	SATTAR S, LAPRAY P, AKSAS L, et al. Snapshot spectropolarimetric imaging using a pair of filter array cameras[J]. Optical Engineering, 2022, 61(4): 043104.
[10]	聂晓风, 唐林波, 张国阳, 等. 基于偏振信息的低可探测目标检测方法[C]// 第十五届全国信号和智能信息处理与应用学术会议论文集. 重庆: 中国高科技产业化研究会智能信息处理产业化分会, 2022: 220-225.
	NIE X F, TANG L B, ZHANG G Y, et al. Low detectable target detection based on polarization information[C]// Proceedings of the 15th National Conference on Signal and Intelligent Information Processing and Application. Chongqing: Intelligent Information Processing Industrialization Branch, China High-tech Industrialization Association, 2022: 220-225. (in Chinese)
[11]	YANG X L, ZHAO M, SHI S, et al. Deep constrained energy minimization for hyperspectral target detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 8049-8063.
[12]	CHANG C, CAO H J, SONG M P. Orthogonal subspace projection target detector for hyperspectral anomaly detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 4915-4932.
[13]	杨威, 王晓曼, 赵海丽, 等. 一种改进的水下偏振图像融合算法研究[J]. 长春理工大学学报(自然科学版), 2021, 44(4): 43-49.
	YANG W, WANG X M, ZHAO H L, et al. Research on an improved underwaterpolarization image fusion algorithm[J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2021, 44(4): 43-49. (in Chinese)
[14]	SHEN Y, LIN W F, WANG Z F, et al. Rapid detection of camouflaged artificial target based on polarization imaging and deep learning[J]. IEEE Photonics Journal, 2021, 13(4): 7800309.
[15]	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. doi: 10.1109/TPAMI.2016.2577031 pmid: 27295650
[16]	WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC, Canada:IEEE, 2023: 7464-7475.
[17]	HUBER-LERNER M, HADAR O, ROTMAN S R, et al. Hyperspectral band selection for anomaly detection: the role of data gaussianity[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(2): 732-743.
[18]	王霞, 苏子航, 赵家碧, 等. 基于交织序列的偏振方向映射方法[J]. 应用光学, 2021, 42(5): 877-883. doi: 10.5768/JAO202142.0503001
	WANG X, SU Z H, ZHAO J B, et al. Sequence-interleaving mapping method for direction of polarization[J]. Journal of Applied Optics, 2021, 42(5): 877-883. (in Chinese) doi: 10.5768/JAO202142.0503001
[19]	XU H, WANG Y, WU Y J, et al. Infrared and multi-type images fusion algorithm based on contrast pyramid transform[J]. Infrared Physics & Technology, 2016, 78: 133-146.
[20]	WAN M J, GU G H, QIAN W X, et al. Stokes-vector-based polarimetric imaging system for adaptive target/background contrast enhancement[J]. Applied Optics, 2016, 55(21): 5513-5519.
[21]	高新波, 莫梦竟成, 汪海涛, 等. 小目标检测研究进展[J]. 数据采集与处理, 2021, 3(36): 391-417.
	GAO X B, MO M J C, WANG H T,etal. Recent advances in small object detection[J]. Journal of Data Acquisition and Processing, 2021, 3(36): 391-417. (in Chinese)
[22]	ZHANG Y, ZHANG Y, ZHAO H J, et al. Improved atmospheric effects elimination method for pBRDF models of painted surfaces[J]. Optics Express, 2017, 25(14): 16458-16475. doi: 10.1364/OE.25.016458 pmid: 28789150
[23]	ZHANG Y, WANG H, LI H S, et al. Optimization model of signal-to-noise ratio for a typical polarization multispectral imaging remote sensor[J]. Sensors, 2022, 22(17): 6624.
[24]	CHEN G, WANG H T, CHEN K, et al. A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(2): 936-953.
[25]	沈英, 刘贤财, 王舒, 等. 基于偏振编码图像的低空伪装目标实时检测[J]. 兵工学报, 2024, 45(5): 1374-1383. doi: 10.12382/bgxb.2022.1289
	SHEN Y, LIU X C, WANG S, et al. Real-time detection of low-altitude camouflage targets based on polarization coded images[J]. Acta Armamentarii, 2024, 45(5): 1374-1383. (in Chinese) doi: 10.12382/bgxb.2022.1289