基于无人艇的导航雷达目标检测跟踪算法

doi:10.12305/j.issn.1001-506X.2024.05.11

摘要/Abstract

摘要：

在无人艇利用导航雷达进行环境感知的过程中, 针对雷达回波图中出现的区域破碎现象以及对运动目标进行跟踪时存在较大误差的问题, 提出了一种应用于导航雷达的目标检测跟踪方法提高无人艇对水面目标的检测能力。首先, 对雷达原始回波图像解析并进行预处理操作; 其次, 在图像连通的基础上, 设计自适应阈值分割Hausdorff匹配算法对回波图和地图进行匹配, 区分属于目标和陆地的回波; 然后, 对连续两帧的雷达回波图进行目标匹配; 最后, 通过加入预测序列模型的经验模态分解算法优化检测跟踪结果, 提高获取目标信息的准确性。实验验证结果表明: 对1 km内相对运动速度低于30节的水面目标, 所提方法目标检测概率提升了6.5%, 距离误差低于2%, 航速误差低于6%, 航向误差低于6°, 整体性能优于工程中常用的检测跟踪方法。

关键词: 环境感知, 导航雷达, 连通算法, 地图匹配, 经验模态分解算法

Abstract:

A target detection and tracking method for navigation radar is proposed to improve the detection ability of unmanned surface vessel for surface targets. This method addresses the problems of fragmented regions in the radar echo map and large errors in tracking moving targets during the process of environmental perception using navigation radar. Firstly, the original echo image of the radar is analyzed and corrected to obtain the required echo image. Secondly, based on image connectivity, a self-adaptive threshold segmentation Hausdorff matching algorithm is designed to match the echo map and the map, distinguishing the echoes belonging to the target and the land. Thirdly, the target matching is performed on the continuous two frames of radar echoes. Finally, the empirical model decomposition (EMD) algorithm of the predictive sequence model is added to optimize the detection and tracking results, and improve the accuracy of obtaining target information. The results of experimental verification show that for surface targets with a relative motion speed of less than 30 knots within 1 km, the distance error is less than 2%, the target detection probability increases by 6.5%, the speed error is less than 6%, and the heading error is less than 6° using this method. The overall performance is better than that of the detection and tracking methods commonly used in engineering.

Key words: environmental perception, navigation radar, connectivity algorithm, map matching, empirical model decomposition (EMD) algorithm

中图分类号:

TN953

王伟, 杜旭洋, 杨志伟, 吴凡. 基于无人艇的导航雷达目标检测跟踪算法[J]. 系统工程与电子技术, 2024, 46(5): 1561-1572.

Wei WANG, Xuyang DU, Zhiwei YANG, Fan WU. Navigation radar target detection and tracking algorithm based on USV[J]. Systems Engineering and Electronics, 2024, 46(5): 1561-1572.

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

表1

参考文献 31

1	ZHOU Z G , HU X X , LI Z M , et al. A fusion algorithm of object detection and tracking for unmanned surface vehicles[J]. Front Neurorobot, 2022, 16, 808147. doi: 10.3389/fnbot.2022.808147
2	ZHANG W , GAO X Z , YANG C F , et al. A object detection and tracking method for security in intelligence of unmanned surface vehicles[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 13 (3): 1279- 1291.
3	KIM H , KIM D , LEE S M . Marine object segmentation and tracking by learning marine radar images for autonomous surface vehicles[J]. IEEE Sensors Journal, 2023, 23 (9): 10062- 10070. doi: 10.1109/JSEN.2023.3259471
4	YU Q Z , WANG B , SU Y M . Object detection-tracking algorithm for unmanned surface vehicles based on a radar-photoelectric system[J]. IEEE Access, 2021, 9, 57529- 57541. doi: 10.1109/ACCESS.2021.3072897
5	DENG L H, GUO T T, WANG H J, et al. Obstacle detection of unmanned surface vehicle based on lidar point cloud data[C]//Proc. of the Oceans, 2022.
6	陈任飞, 彭勇, 李忠文. 基于持续无监督域适应策略的水面漂浮物目标检测方法[J/OL]. [2023-06-19]. http://kns.cnki.net/kcms/detail/11.2422.TN.20230220.1441.018.html.
	CHEN R F, PENG Y, LI Z W. Based on adaptive strategy for unsupervised domain floats on the surface of the target detection method[J/OL]. [2023-06-19]. http://kns.cnki.net/kcms/detail/11.2422.TN.20230220.1441.018.html.
7	WANG W M , DU J L , TAO Y H . A dynamic collision avoidance solution scheme of unmanned surface vessels based on proactive velocity obstacle and set-based guidance[J]. Ocean Engineering, 2022, 248 (15) doi: 10.1016/j.oceaneng.2022.110794.14
8	WU Y , CHU X M , DENG L , et al. A new multi-sensor fusion approach for integrated ship motion perception in inland waterways[J]. Measurement, 2022, 200, 111630. doi: 10.1016/j.measurement.2022.111630
9	NAUS K , WAZ M , SZYMAK P , et al. Assessment of ship position estimation accuracy based on radar navigation mark echoes identified in an electronic navigational chart[J]. Measurement, 2021, 169, 108630. doi: 10.1016/j.measurement.2020.108630
10	张大恒, 张英俊, 张闯. 基于Faster R-CNN的电子海图和雷达图像的数据融合[J]. 系统工程与电子技术, 2020, 42 (6): 1267- 1273. doi: 10.3969/j.issn.1001-506X.2020.06.09
	ZHANG D H , ZHANG Y J , ZHANG C . Based on a faster R-CNN electronic chart and radar image data fusion[J]. Systems Engineering and Electronics, 2020, 42 (6): 1267- 1273. doi: 10.3969/j.issn.1001-506X.2020.06.09
11	DAGDILELIS D , BLANKE M , ANDERSEN R H , et al. Cyber-resilience for marine navigation by information fusion and change detection[J]. Ocean Engineering, 2022, 266, 112605. doi: 10.1016/j.oceaneng.2022.112605
12	XU J , JIA B Z , PAN X X , et al. Hydrographic data inspection and disaster monitoring using shipborne radar small range images with electronic navigation chart[J]. PeerJ Computer Science, 2020, doi: 10.7717/peerj-CS.290
13	DI H B , SHAFIQ M , ALREGIB G . Multi-attribute k-means clustering for salt-boundary delineation from three-dimensional seismic data[J]. Geophysical Journal International, 2018, 215 (3): 1999- 2007. doi: 10.1093/gji/ggy376
14	ADHAMI M H , GHAZIZADEH R . Secure multiple target tracking based on clustering intersection points of measurement circles in wireless sensor networks[J]. Wireless Networks, 2021, 27, 1233- 1249. doi: 10.1007/s11276-020-02510-0
15	XU Y , JIA T , CAO D , et al. Adaptive clustering-based marine radar sea clutter normalization[J]. Journal of Sensors, 2021, 2021 (7): 1- 11.
16	李立刚, 李勃然, 金久才, 等. 基于图像轮廓特征的无人水面艇航海雷达目标检测修正方法[J]. 水下无人系统学报, 2022, 30 (2): 190- 196.
	LI L G , LI B R , JIN J C , et al. Target detection and correction method of marine radar for unmanned surface craft based on image contour features[J]. Journal of Unmanned Undersea Systems, 2022, 30 (2): 190- 196.
17	刘宁波, 董云龙, 王国庆, 等. X波段雷达对海探测试验与数据获取[J]. 雷达学报, 2019, 8 (5): 656- 667.
	LIU N B , DONG Y L , WANG G Q , et al. X-band radar sea detection test and data acquisition[J]. Journal of Radars, 2019, 8 (5): 656- 667.
18	BAIRD Z , MCDONALD M K , RAJAN S , et al. A CNN-LSTM network for augmenting target detection in real maritime wide area surveillance radar data[J]. IEEE Access, 2020, 8, 179281- 179294. doi: 10.1109/ACCESS.2020.3025144
19	SU N Y , CHEN X L , GUAN J , et al. Maritime target detection based on radar graph data and graph convolutional network[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 1- 5.
20	WILLIAMS J, ROSENBERG L, STAMATESCU V, et al. Maritime radar target detection using convolutional neural networks[C]//Proc. of the IEEE Radar Conference, 2022.
21	CHEN X L , MU X Q , GUAN J , et al. Marine target detection based on marine-faster R-CNN for navigation radar plane position indicator images[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23 (4): 630- 643.
22	苏宁远, 陈小龙, 关键, 等. 基于卷积神经网络的海上微动目标检测与分类方法[J]. 雷达学报, 2018, 7 (5): 565- 574.
	SU N Y , CHEN X L , GUAN J , et al. Detection and classification of marine fretting targets based on convolutional neural networks[J]. Journal of Radars, 2018, 7 (5): 565- 574.
23	FAN Y S , QIAO S H , WANG G F , et al. A modified adaptive kalman filtering method for maneuvering target tracking of unmanned surface vehicles[J]. Ocean Engineering, 2022, 266, 112890. doi: 10.1016/j.oceaneng.2022.112890
24	COLE B , SCHAMBERG G . Unscented Kalman filter for long-distance vessel tracking in geodetic coordinates[J]. Applied Ocean Research, 2022, 124, 103205. doi: 10.1016/j.apor.2022.103205
25	王志达, 薛林, 陈阳阳, 等. 引入测速信息的雷达导引头无偏转换跟踪方法[J]. 系统工程与电子技术, 2020, 42 (8): 1695- 1702. doi: 10.3969/j.issn.1001-506X.2020.08.08
	WANG Z D , XUE L , CHEN Y Y , et al. Unbiased conversion tracking method of radar seeker with velocity measurement information[J]. Systems Engineering and Electronics, 2020, 42 (8): 1695- 1702. doi: 10.3969/j.issn.1001-506X.2020.08.08
26	EBRAHIMI M , ARDESHIRI M , KHANGHAH S A . Bearing-only 2D maneuvering target tracking using smart interacting multiple model filter[J]. Digital Signal Processing, 2022, 126, 103497. doi: 10.1016/j.dsp.2022.103497
27	XIAO Z , FU X J , ZHANG L Y , et al. Big data driven vessel trajectory and navigating state prediction with adaptive learning, motion modeling and particle filtering techniques[J]. IEEE Trans.on Intelligent Transportation Systems, 2022, 23 (4): 3696- 3709. doi: 10.1109/TITS.2020.3040268
28	BREKKE E F , HEM A G , TOKLE L N . Multitarget tracking with multiple models and visibility: derivation and verification on maritime radar data[J]. IEEE Journal of Oceanic Engineering, 2021, 46 (4): 1272- 1287. doi: 10.1109/JOE.2021.3081174
29	ZEMSKOV Y , KOPTSEVA E , PANKRATOVA A , et al. Universal prediction algorithm in maneuvering target tracking[J]. Journal of Physics: Conference Series, 2022, 2176 (1): 012074. doi: 10.1088/1742-6596/2176/1/012074
30	MA F , ZHANG F , XIANG D L , et al. Fast task-specific region merging for SAR image segmentation[J]. IEEE Trans.on Geoscience and Remote Sensing, 2022, 60, 5222316.
31	BLINDHEIM S , JOHANSEN T A . Electronic navigational charts for visualization, simulation, and autonomous ship control[J]. IEEE Access, 2022, 10, 3716- 3737. doi: 10.1109/ACCESS.2021.3139767

场景	距离/m			航向/(°)		航速/(m/s)
	相对距离	RMSE		RMSE		目标速度	RMSE
	均值	A算法	B算法	A算法	B算法	均值	A算法	B算法
1	494.71	11.32	5.70	7.37	5.15	6.17	0.69	0.33
2	627.09	6.83	3.57	12.08	5.27	5.15	0.44	0.17
3	658.87	8.22	3.61	-	-	0.16	0.38	0.16

[1]	郑建拥, 魏光辉. 基于多分辨率动态模态分解的电磁信号时频-能量分析[J]. 系统工程与电子技术, 2022, 44(5): 1468-1474.
[2]	张丹娜, 钱锋, 冯辉, 闻年成. Walsh码软扩频信号降噪算法[J]. 系统工程与电子技术, 2020, 42(4): 773-780.
[3]	吴德伟，周阳，杜佳，李伟龙. UCAV环境感知中路标选取及定位方法[J]. 系统工程与电子技术, 2014, 36(10): 2048-2052.