反无人机图像导引头远距空中目标探测技术

doi:10.12382/bgxb.2021.0873

摘要/Abstract

摘要：

以低成本反无人机制导弹药为研究背景,开展针对远距无人机目标探测的研究工作,并设计一种局部视觉显著聚类测量算法。将局部对比测量思想引入可见光图像中,通过度量局部成像域的光谱聚类性实现对目标的检测,更具体的是度量局部像域的平均光谱值与相邻像素光谱值的最小距离。为解决多尺度目标问题,设计相应的多尺度滑窗测量方法。对原始RGB图像帧进行分频中值滤波,将滤波后的RGB图像转换到Lab颜色空间;通过滑窗模型进行无人机成像域搜索;使用显著性检测方法度量光谱差异性,得到显著测量图;利用阈值化算法获得潜在无人机目标的像素位置。根据无人机目标成像条件,开展远距无人机图像数据集的实地拍摄和人工合成工作。定性实验结果表明局部视觉显著聚类测量算法可在复杂背景下将小尺度无人机辨识,定量实验结果表明该算法的检测准确率可达到100%。

关键词: 反无人机技术, 图像导引头, 显著性检测

Abstract:

Taking the low-cost counter-UAV guided munitions as the research object, this study focuses on long-distance UAV target detection, and the design of a local visual saliency-based clustering measurement algorithm. In this algorithm, the idea of local contrast measurement is introduced into the visible light image for the first time, and the detection of the target by measuring the spectral clustering of the local imaging domain is realized.More specifically, it measures the minimum distance between the average spectral value of the local image domain and the spectral values of adjacent pixels. In addition, to solve the multi-scale target problem, a corresponding multi-scale sliding window measurement method is designed.The brief flow of the whole algorithm is as follows: frequency-division median filtering was performed on the original RGB image frame; to better measure the spectral difference, the filtered RGB image was converted to the Lab color space; the sliding window model was used for UAV imaging domain search; the saliency detection method was adopted to measure the spectral difference to obtain a saliency measurement map; finally, a thresholding algorithm was used to obtain the pixel position of the potential UAV target. According to the UAV target imaging conditions, field shooting and artificial synthesis of long-distance UAV image datasets were carried out. The experimental results showed that the algorithm can successfully separate the UAV target from the background under various complex meteorological conditions.

Key words: counter-UAV technology, image seeker, saliency detection

赵飞, 娄文忠, 冯恒振, 苏子龙, 汪金奎, 宣炜琨. 反无人机图像导引头远距空中目标探测技术[J]. 兵工学报, 2023, 44(4): 1023-1033.

ZHAO Fei, LOU Wenzhong, FENG Huanzhen, SU Zilong, WANG Jinkui, XUAN Weikun. Long-Distance Aerial Target Detection Technology of Counter-UAV Image Seeker[J]. Acta Armamentarii, 2023, 44(4): 1023-1033.

图/表 23

图1 反无人机制导弹药弹道飞行示意图

Fig.1 Schematic diagram of ballistic flight of counter-UAV guided munitions

图2 无人机目标探测算法框图

Fig.2 Block diagram of UAV target detection algorithm

图3 典型中值滤波窗口

Fig.3 Typical median filter windows

图4 中值滤波处理效果

Fig.4 Median filter processing effects

图5 滑窗模型

Fig.5 Sliding window model

图6 图像块vi与wi

Fig.6 Image patches vi and wi

图7 局部视觉显著度测量算法

Fig.7 Local visual saliency measurement algorithm

图8 多尺度像素域测量算法

Fig.8 Multi-scale pixel domain measurement algorithm

图9 待检测RGB图像

Fig.9 RGB image to be detected

图10 多尺度显著测量图

Fig.10 Multi-scale saliency measurement maps

图11 多尺度测量图池化结果$\hat{S}$

Fig.11 Multi-scale measurement graph pooling results $\hat{S}$

图12 阈值化搜索算法

Fig.12 Thresholding search algorithm

图13 双目标图像

Fig.13 Dual-target image

图14 双目标显著测量图

Fig.14 Saliency measurement maps of two targets

图15 阈值化二值图像

Fig.15 Thresholding binary image

图16 制导信息关系图

Fig.16 Guidance information diagram

图17 目标成像几何模型

Fig.17 Target imaging geometric model

图18 无人机远距成像帧

Fig.18 Long-distance UAV imaging frame

图19 人工合成图像

Fig.19 Synthetic image

图20 测试样机

Fig.20 Test prototype

表1 算法测试结果

Table 1 Algorithm test results

测试图像	显著测量图	检测结果

表2 算法测试结果

Table 2 Algorithm test results

测试图像	显著测量图	检测结果

表3 测试数据说明

Table 3 Test data description

视频序号	帧数	单帧大小	目标大小	速度/ (帧·s^-1)	准确度/ %
1	50	640×512	<10×10	8	100
2	50	640×512	<10×10	8	100
3	50	640×512	<10×10	8	100
4	50	640×512	<10×10	8	100
5	50	640×512	<10×10	8	100

参考文献 20

[1]	PARK S, KIM H T, LEE S, et al. Survey on anti-drone systems: components, designs, and challenges[J]. IEEE Access, 2021, 9:42635-42659. doi: 10.1109/ACCESS.2021.3065926 URL
[2]	SHI X F, YANG C Q, XIE W G, et al. Anti-drone system with multiple surveillance technologies:architecture, implementation, and challenges[J]. IEEE Communications Magazine, 2018, 56(4):68-74.
[3]	UZAIR M, BRINKWORTH R S, FINN A. Bio-inspired video enhancement for small moving target detection[J]. IEEE Transactions on Image Processing, 2021, 30:1232-1244. doi: 10.1109/TIP.2020.3043113 pmid: 33315561
[4]	张永梅, 赖裕平, 马健喆, 等. 基于视频的装甲车和飞机检测跟踪及轨迹预测算法[J]. 兵工学报, 2021, 42(3):545-554. doi: 10.3969/j.issn.1000-1093.2021.03.010
	ZHANG Y M, LAI Y P, MA J Z, et al. A video-based prediction algorithm for armored vehicle andaircraft detection/tracking and trajectory[J]. Acta Armamentarii, 2021, 42(3):545-554. (in Chinese)
[5]	梁杰, 李磊, 任君, 等. 基于深度学习的红外图像遮挡干扰检测方法[J]. 兵工学报, 2019, 40(7):1401-1410. doi: 10.3969/j.issn.1000-1093.2019.07.009
	LIANG J, LI L, REN J, et al. Infrared image occlusion interferencedetection method based on deep learning[J]. Acta Armamentarii, 2019, 40(7):1401-1410. (in Chinese) doi: 10.3969/j.issn.1000-1093.2019.07.009
[6]	DANELLJAN M, BHAT G, SHAHBAZ KHAN F, et al. ECO: Efficient convolution operators for tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US:IEEE, 2017:6638-6646.
[7]	BIBI A, MUELLER M, GHANEM B. Target response adaptation for correlation filter tracking[C]//Proceedings of the 2016 IEEE European Conference on Computer Vision Workshop. Amsterdam, the Nethland: IEEE, 2016:419-433.
[8]	ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami. FL, US:IEEE, 2009:1597-1604.
[9]	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 and Remote Sensing, 2013, 52(1):574-581. doi: 10.1109/TGRS.2013.2242477 URL
[10]	SINGH N, THILAGAVATHY T, LAKSHMIPRIYA R T, et al. Some studies on detection and filtering algorithms for the removal of random valued impulse noise[J]. Iet Image Processing, 2017, 11(11):953-963. doi: 10.1049/ipr2.v11.11 URL
[11]	吴一全, 罗子娟. 基于最小二乘支持向量机时域背景预测的红外弱小目标检测[J]. 兵工学报, 2010, 31(6):678-684.
	WU Y Q, LUO Z J. Small infrared target detection based on least squares supportvector machine temporal background prediction[J]. Acta Armamentarii, 2010, 31(6):678-684. (in Chinese)
[12]	刘德鹏, 李正周, 曾靖杰, 等. 基于多尺度局部对比度和多尺度梯度一致性的红外小弱目标检测算法[J]. 兵工学报, 2018, 39(8):1526-1535. doi: 10.3969/j.issn.1000-1093.2018.08.009
	LIU D P, LI Z Z, ZENG J J, et al. Infrared dim small target detection based on Multi-scale Local Contrast and Multi-scale Gradient coherence[J]. Acta Armamentarii, 2018, 39(8):1526-1535. (in Chinese)
[13]	HAN J H, LIU C Y, LIU Y C, et al. Infrared small target detection utilizing the enhanced closest-mean background estimation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14: 645-662. doi: 10.1109/JSTARS.4609443 URL
[14]	于劲松, 万九卿, 高秀林. 红外图像弱小点目标检测技术研究[J]. 兵工学报, 2008, 29(12):1518-1521.
	YU J S, WAN J Q, GAO X L. Research on dim point moving target detection in infrared image[J]. Acta Armamentarii, 2008, 29(12):1518-1521. (in Chinese)
[15]	WANG H X, PENG J G, ZHENG X Q, et al. A robust visual system for small target motion detection against cluttered moving backgrounds[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(3):839-853. doi: 10.1109/TNNLS.5962385 URL
[16]	WANG H X, PENG J G, YUE S G. A directionally selective small target motion detecting visual neural network in cluttered backgrounds[J]. IEEE Transactions on Cybernetics, 2018, 50(4):1541-1555. doi: 10.1109/TCYB.6221036 URL
[17]	WIEDERMANN S D, O'CARROLL D C. Biologically inspired feature detection using cascaded correlations of off and on channels[J]. Journal of Artificial Intelligence and Soft Computing Research, 2013, 3:5-14. doi: 10.2478/jaiscr-2014-0001 URL
[18]	吴青青, 许廷发, 闫辉, 等. 复杂背景下的颜色分离背景差分目标检测方法[J]. 兵工学报, 2013, 193(4):501-506.
	WU Q Q, XU T F, YAN H, et al. An improved color separation method for object detection in complex background[J]. Acta Armamentarii, 2013, 193(4):501-506. (in Chinese)
[19]	ZHANG W, CONG M Y, WANG L P. Algorithms for optical weak small targets detection and tracking[C]//Proceedings of International Conference on Neural Networks and Signal Processing. Nanjing, China:IEEE, 2003, 1: 643-647.
[20]	王荔豪, 杨凯, 马菲, 等. 基于捷联导引头的制导信息解耦及滤波方法[J]. 计算机测量与控制, 2020, 28(4):142-145.
	WANG L H, YANG K, MA F, et al. Decoupling and filter algorithm for guidance information based on strap-down seeker[J]. Computer Measurement & Control, 2020, 28(4):142-145. (in Chinese)