基于TransUNet的机动微弱目标智能检测前跟踪算法

doi:10.7527/S1000-6893.2023.29466

Abstract

Abstract:

The development and application of stealth technology have brought great challenges to radar target detection. As one of the important technical directions for weak target detection， the Tracking-Before-Detection （TBD） technology is often used in radar detection. However， the traditional TBD requires a large amount of computation and is limited by target motion models， making it difficult to effectively detect maneuvering targets in various motion states. To address this issue， a TransUNet based intelligent TBD algorithm for weak targets is proposed. The algorithm is not limited by any motion model and can effectively identify maneuvering targets in various motion states. Firstly， utilizing the spatio-temporal correlation characteristics of the target motion trajectory， a rough detection algorithm for maneuvering weak targets in different motion states is designed based on the TransUNet model to achieve preliminary detection of weak maneuvering targets. Then， the preliminary detection results are used to perform regional search for the target measurement， and achieve backtracking of weak maneuvering target points. Finally， to address the problem of missed detection in preliminary backtracking points at low Signal-to-Noise Ratio （SNR）， the auxiliary information of partially successfully detected points， combined with the Optimal Parabolic （OP） value function， is utilized to achieve precise detection of target points and complete backtracking of tracks. Simulation experiments have verified that this method proposed can effectively detect weak maneuvering targets in various motion states.

Key words: Tracking-Before-Detection (TBD), weak target, TransUNet network, spatio-temporal correlation characteristics, target detection, optimal parabolic value function

CLC Number:

V243.2

Xingrui WU, Ruihui PENG, Dianxing SUN, Shuncheng TAN, Yihong ZHANG, Wenbin WEI. Intelligent TBD algorithm for maneuvering weak targets based on TransUNet[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(12): 329466-329466.

Figures/Tables 21

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Table 1

Fig.11

Fig.12

Fig.13

Table 2

Fig.14

Table 3

Fig.15

Fig.16

Fig.17

Table 4

References 20

1	YANG Z， CHEN M Z， LIU X， et al. AI-driven UAV-NOMA-MEC in next generation wireless networks［C］∥ IEEE Wireless Communications. Piscataway： IEEE Press， 2021： 66- 73.
2	郭陈林. 基于Hough变换的微弱目标检测方法研究［D］. 成都：电子科技大学， 2011： 38- 50.
	GUO C L. Research on weak target detection method based on Hough transform［D］. Chengdu： University of Electronic Science and Technology of China， 2011： 38- 50 （in Chinese）.
3	包中华，卢建斌，田永华，等. 密集杂波背景下雷达微弱海面目标的修正Hough变换TBD检测新方法［J］. 电子学报， 2022， 50（ 7）： 1735- 1743.
	BAO Z H， LU J B， TIAN Y H， et al. A novel radar TBD detection approach for weak marine targets in dense clutter based on modified Hough transform［J］. Acta Electronica Sinica， 2022， 50（ 7）： 1735- 1743 （in Chinese）.
4	王国宏，李林，于洪波. 基于点集合并的修正Hough变换TBD算法［J］. 航空学报， 2017， 38（ 1）： 320009.
	WANG G H， LI L， YU H B. A modified Hough transform TBD algorithm based on point set merging［J］. Acta Aeronautica et Astronautica Sinica， 2017， 38（ 1）： 320009 （in Chinese）.
5	刘剑，赵艳丽，罗鹏飞. 基于Hough变换的低可观测海面运动目标检测［J］. 系统工程与电子技术， 2004， 26（ 3）： 393- 395.
	LIU J， ZHAO Y L， LUO P F. Detection of lowlying sea surface moving target via Hough transform［J］. Systems Engineering and Electronics， 2004， 26（ 3）： 393- 395 （in Chinese）.
6	薄钧天，王国宏，于洪波，等. 基于平行线坐标变换的检测前跟踪算法［J］. 航空学报， 2022， 43（ 8）： 325644.
	BO J T， WANG G H， YU H B， et al. Track before detect algorithm based on parallel-line-coordinate transformation［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（ 8）： 325644 （in Chinese）.
7	YI W， KONG L J， YANG J Y， et al. Student highlight： Dynamic programming-based track-before-detect approach to multitarget tracking［J］. IEEE Aerospace and Electronic Systems Magazine， 2012， 27（ 12）： 31- 33.
8	全英汇，陈侠达，阮锋，等. 一种捷变频联合Hough变换的抗密集假目标干扰算法［J］. 电子与信息学报， 2019， 41（ 11）： 2639- 2645.
	QUAN Y H， CHEN X D， RUAN F， et al. An anti-dense false target jamming algorithm based on agile frequency joint Hough transform［J］. Journal of Electronics & Information Technology， 2019， 41（ 11）： 2639- 2645 （in Chinese）.
9	李岳峰，王国宏，李林，等. 临近空间高超声速目标修正随机Hough变换TBD算法［J］. 宇航学报， 2017， 38（ 10）： 1114- 1123.
	LI Y F， WANG G H， LI L， et al. A modified randomized Hough transform TBD algorithm for hypersonic target in near space［J］. Journal of Astronautics， 2017， 38（ 10）： 1114- 1123 （in Chinese）.
10	郭云飞，郑晓枫，彭冬亮，等. 基于遍历Hough变换的弱目标检测前跟踪算法［J］. 系统仿真学报， 2015， 27（ 6）： 1316- 1323.
	GUO Y F， ZHENG X F， PENG D L， et al. Track-before-detect algorithm for weak target based on ergodic Hough transform［J］. Journal of System Simulation， 2015， 27（ 6）： 1316- 1323 （in Chinese）.
11	YI W， KONG L J， YANG J Y， et al. A tracking approach based on dynamic programming track-before-detect［C］∥ 2009 IEEE Radar Conference. Piscataway： IEEE Press， 2009： 1- 4.
12	LIU R， YI W， KONG L J， et al. An efficient multi-target track-before-detect algorithm for low PRF surveillance radars［C］∥ 2014 IEEE Radar Conference. Piscataway： IEEE Press， 2014： 1273- 1277.
13	MOYER L R， SPAK J， LAMANNA P. A multi-dimensional Hough transform-based track-before-detect technique for detecting weak targets in strong clutter backgrounds［J］. IEEE Transactions on Aerospace and Electronic Systems， 2011， 47（ 4）： 3062- 3068.
14	陈帅霖，罗丰，张林让，等. 采用动态规划的机动目标检测前跟踪算法［J］. 西安电子科技大学学报， 2017， 44（ 5）： 39- 45.
	CHEN S L， LUO F， ZHANG L R， et al. Maneuvering target track-before-detect method using dynamic programming［J］. Journal of Xidian University， 2017， 44（ 5）： 39- 45 （in Chinese）.
15	于洪波，王国宏，张仲凯. 基于抛物线随机Hough变换的机载脉冲多普勒雷达机动弱目标检测前跟踪方法［J］. 兵工学报， 2015， 36（ 10）： 1924- 1932.
	YU H B， WANG G H， ZHANG Z K. A RPHT-TBD algorithm for tracking and detecting maneuvering weak target via airborne PD radar［J］. Acta Armamentarii， 2015， 36（ 10）： 1924- 1932 （in Chinese）.
16	YI W， FANG Z C， LI W J， et al. Multi-frame track-before-detect algorithm for maneuvering target tracking［J］. IEEE Transactions on Vehicular Technology， 2020， 69（ 4）： 4104- 4118.
17	周宏仁. 机动目标跟踪［M］. 北京：国防工业出版社， 1991： 35- 39.
	ZHOU H R. Tracking of maneuvering targets［M］. Beijing： National Defense Industry Press， 1991： 35- 39 （in Chinese）.
18	杨威，付耀文，潘晓刚，等. 弱目标检测前跟踪技术研究综述［J］. 电子学报， 2014， 42（ 9）： 1786- 1793.
	YANG W， FU Y W， PAN X G， et al. Track-before-detect technique for dim targets： An overview［J］. Acta Electronica Sinica， 2014， 42（ 9）： 1786- 1793 （in Chinese）.
19	ZHOU G J， WANG L L. Pseudo-spectrum based speed square filter for track-before-detect in range-Doppler domain［J］. IEEE Transactions on Signal Processing， 2019， 67（ 21）： 5596- 5610.
20	CHEN J N， LU Y Y， YU Q H， et al. TransUNet： Transformers make strong encoders for medical image segmentation［DB/OL］. arXiv preprint：2102. 04306， 2021.

参数	数值
初始位置/ $m$	$(13 500,14 500)$
速度/（ $m ⋅ s - 1$ ）	$(520,500)$
目标累积帧数	$10 ~ 20$
信噪比/ $d B$	$0 ~ 20$
距离单元数/个	$256 × 256$
目标数量/个	$1$
测角误差/（°）	$1$
测距误差/ $m$	$100$

参数	数值
初始位置/ $m$	$(13 500,14 500)$
速度/（ $m ⋅ s - 1$ ）	$(520,500)$
目标累积帧数	$10 ~ 20$
信噪比/ $d B$	$0 ~ 20$
距离单元数/个	$256 × 256$
目标数量/个	$1$
测角误差/（°）	$1$
测距误差/ $m$	$100$

参数	数值
初始位置/ $m$	$(13 500,14 500)$
速度/（ $m ⋅ s - 1$ ）	$(520,500)$
目标累积帧数	$5 ~ 20$
信噪比/ $d B$	$0 ~ 16$
距离单元数/个	$256 × 256$
目标数量/个	$3 ~ 10$
测角误差/（°）	$1$
测距误差/ $m$	$100$

参数	数值
输入数据分辨率	256×256
初始学习率	0.001
学习率衰减步长	0.000 4
迭代轮次	100
batch_size	4
模型优化器	Adam

[1]	Qiang WANG, Letian WU, Yong WANG, Huan WANG, Wankou YANG. An infrared small target detection method based on key point [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(10): 328173-328173.
[2]	BO Juntian, WANG Guohong, YU Hongbo, PENG Zhigang. Track before detect algorithm based on parallel-line-coordinate transformation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 325644-325644.
[3]	LYU Shuaishuai, YANG Yu, WANG Binwen, YIN Chenfei. A crack identification method of aircraft structure based on improved FaceNet [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 525463-525463.
[4]	CHEN Weishi, HUANG Yifeng, CHEN Xiaolong, LU Xianfeng, ZHANG Jie. Development and applications of airport avian radar: Review [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(1): 24758-024758.
[5]	YING Tao, HUANG Gaoming, ZUO Wei, SHAN Hongchang, GAO Jun. Weak target detection method based on hypothesis test theory in non-cooperative passive detection [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2016, 37(2): 626-636.
[6]	XU Hang, ZHANG Xitao, ZHANG Junpeng. Background suppression algorithm for infrared small target image based on local mean difference [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2015, 36(9): 2869-2873.
[7]	GU Xinfeng, JIAN Tao, HE You, HAO Xiaolin. Recursive Asymptotic GLRT Detector of Range-spread Target in Compound Gaussian Clutter [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2013, 34(5): 1140-1150.
[8]	ZHAN Lixiao, TANG Ziyue, ZHU Zhenbo. Keystone Transform and MDCFT-based Detection and Parameter Estimation for Maneuvering Weak Targets [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2013, 34(4): 855-863.
[9]	LI Hai, WANG Xiaohan, WU Renbiao. Detection and Parameter Estimation of Multicomponent Air Maneuvering Targets via RELAX [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2013, 34(4): 873-881.
[10]	LONG Yunli, XU Hui, AN Wei, LIN Liangkui. Spatial-temporal Fused Filtering for Infrared Clutter Suppression Based on Restricted Sequential M-estimation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2011, 32(8): 1531-1541.
[11]	JIAN Tao, SU Feng, HE You, LI Bingrong, GU Xuefeng. Distributed Target Detection Without Secondary Data [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2011, 32(8): 1542-1547.
[12]	Jian Tao;He You;Su Feng;Qu Changwen;Gu Xinfeng. A Novel Adaptive Radar Target Detector for Non-Gaussian Clutter [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2010, 31(3): 579-586.
[13]	Hou Yingni;Li Daojing;Hong Wen. Airborn Early Warning Radar STAP Based on Thinned Array and Code Division Signal [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2009, 30(4): 732-737.
[14]	WU Hong-gang;LI Xiao-feng;LI Zai-ming. Adaptive Strong Clutter Suppression and Moving Point Target Detection [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2006, 27(5): 908-912.
[15]	HE Lin;PAN Quan;ZHAO Yong-qiang;ZHENG Ji-wei. CFAR Target Detection in Unknown Background Based on Subspace Projection in Aerial Hyperspectral Imagery [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2006, 27(4): 657-662.

Intelligent TBD algorithm for maneuvering weak targets based on TransUNet

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 21

References 20

Related Articles 15

Recommended Articles 0

Metrics

Comments