基于任务对齐学习的红外船舶目标检测方法

doi:10.12305/j.issn.1001-506X.2025.01.04

摘要/Abstract

摘要：

针对红外船舶检测过程中, 在不同场景下对多尺度、小目标、有遮挡等问题检测效果不佳、实时性难以满足任务需要的情况, 提出一种基于任务对齐学习的红外船舶目标检测方法。首先, 为提升检测速度采用无锚框设计降低计算量。然后, 为提升检测精度采用任务对齐学习(task alignment learning, TAL)进行标签分配和对齐。最后, 根据特定场景有针对性地设计检测头以提升网络检测性能。通过实验对比验证, 结果表明所提方法可有效提升对不同场景下船舶目标的检测性能, 在检测精度及实时性上优于其他同类方法。

关键词: 红外船舶, 目标检测, 无锚框, 任务对齐学习

Abstract:

A task alignment learning (TAL) based infrared ship target detection method is proposed to address the issues of poor detection performance and difficulty in meeting task requirements for multi-scale, small targets, and occlusion in different scenarios during the infrared ship detection process. Firstly, to improve detection speed, an anchor free design is adopted to reduce computational complexity. Then, to improve detection accuracy, TAL is used for label allocation and alignment. Finally, design detection heads tailored to specific scenarios to improve network detection performance. Through experimental comparison and verification, the results show that the proposed method effectively improves the detection performance of ship targets in different scenarios, and outperforms other similar methods in terms of detection accuracy and real-time performance.

Key words: infrared vessel, object detection, anchor-free, task alignment learning (TAL)

中图分类号:

TP391.4

姜杰, 张立民, 刘凯, 闫文君, 王萌. 基于任务对齐学习的红外船舶目标检测方法[J]. 系统工程与电子技术, 2025, 47(1): 34-40.

Jie JIANG, Limin ZHANG, Kai LIU, Wenjun YAN, Meng WANG. Infrared ship target detection method based on task alignment learning[J]. Systems Engineering and Electronics, 2025, 47(1): 34-40.

图/表 11

图1

图2

图3

图4

图5

表1

表2

表3

图6

表4

图7

参考文献 30

1	陈钱, 隋修宝. 红外图像处理理论与技术[M]. 北京: 电子工业出版社, 2018.
	CHEN Q , SUI X B . Infrared image processing theory and technology[M]. Beijing: Publishing House of Electronics Industry, 2018.
2	REKAVANDI A M, RASHIDI S, BOUSSAID F, et al. Transformers in small object detection: a benchmark and survey of state-of-the-art[EB/OL]. [2023-09-01], https://arxiv.org/abs/2309.04902.
3	HASSAN S A, RAHIM T, SHIN S Y. Real-time UAV detection based on deep learning network[C]//Proc. of the International Conference on Information and Communication Technology Convergence, 2019.
4	OPROMALLA R , FASANO G , ACCARDO D . A vision-based approach to UAV detection and tracking in cooperative applications[J]. Sensors, 2018, 18 (10):3391. doi: 10.3390/s18103391
5	KOU R , WANG C P , PENG Z M , et al. Infrared small target segmentation networks: a survey[J]. Pattern Recognition, 2023, 143, 109788. doi: 10.1016/j.patcog.2023.109788
6	BAI X Z , CHEN Z G , ZHANG Y , et al. Infrared ship target segmentation based on spatial information improved FCM[J]. IEEE Trans. on Cybernetics, 2015, 46 (12): 3259-3271.
7	LIU Z Y , ZHOU F , CHEN X W , et al. Iterative infrared ship target segmentation based on multiple features[J]. Pattern Recognition, 2014, 47 (9): 2839- 2852. doi: 10.1016/j.patcog.2014.03.005
8	DAI Y M , WU Y Q , ZHOU F , et al. Attentional local contrast networks for infrared small target detection[J]. IEEE Trans. on Geoscience and Remote Sensing, 2021, 59 (11): 9813- 9824. doi: 10.1109/TGRS.2020.3044958
9	甘春生. 星载遥感图像舰船检测方法研究[D]. 辽宁: 沈阳航空航天大学, 2016.
	GAN C S. Research on ship detection methods in spaceborne remote sensing images[D]. Liaoning: Shenyang University of Aeronautics and Astronautics, 2016.
10	LEI S , ZOU Z X , LIU D G , et al. Sea-land segmentation for infrared remote sensing images based on superpixels and multi-scale features[J]. Infrared Physics & Technology, 2018, 91, 12- 17.
11	BAI X Z , ZHOU F G . Analysis of new top-hat transformation and the application for infrared dim small target detection[J]. Pattern Recognition, 2010, 43 (6): 2145- 2156. doi: 10.1016/j.patcog.2009.12.023
12	LIU R M , LU Y H , GONG C L , et al. Infrared point target detection with improved template matching[J]. Infrared Phy-sics & Technology, 2012, 55 (4): 380- 387.
13	李海军, 孔繁程, 林云. 基于改进YOLOv5s的红外舰船检测算法[J]. 系统工程与电子技术, 2023, 45 (8): 2415- 2422.
	LI H J , KONG F C , LIN Y . Infrared ship detection algorithm based on improved YOLOv5s[J]. Systems Engineering and Electronics, 2023, 45 (8): 2415- 2422.
14	潘为年. 基于深度学习的红外成像舰船目标检测方法研究[D]. 成都: 电子科技大学, 2021.
	PAN W N. Research on infrared imaging ship target detection method based on deep learning[D]. Chengdu: University of Electronic Science and Technology of China, 2021.
15	FENG C J, ZHONG Y J, GAO Y, et al. Tood: task-aligned one-stage object detection[C]//Proc. of the IEEE/CVF International Conference on Computer Vision, 2021: 3490-3499.
16	THECKEDATH D , SEDAMKAR R R . Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks[J]. SN Computer Science, 2020, 1 (2): 79. doi: 10.1007/s42979-020-0114-9
17	TIAN Z , CHEN C H , CHEN H , et al. FCOS: a simple and strong anchor-free object detector[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2020, 44 (4): 1922- 1933.
18	ZHANG Y C , ZHANG W B , YU J Y , et al. Complete and accurate holly fruits counting using YOLOX object detection[J]. Computers and Electronics in Agriculture, 2022, 198, 107062. doi: 10.1016/j.compag.2022.107062
19	WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
20	JU C , GUAN C T . Tensor-CSPNet: a novel geometric deep learning framework for motor imagery classification[J]. IEEE Trans. on Neural Networks and Learning Systems, 2022, 9, 4512- 4516.
21	XU W J, LONG C J, WANG R S, et al. DRB-GAN: a dyna-mic resblock generative adversarial network for artistic style transfer[C]//Proc. of the IEEE/CVF International Conference on Computer Vision, 2021: 6383-6392.
22	WANG Y J , LEE J G , MOON U C , et al. SSD-TSEFFM: new SSD using trident feature and squeeze and extraction feature fusion[J]. Sensors, 2020, 20 (13): 3630. doi: 10.3390/s20133630
23	DELIANG X , XU Y H , CHENG J D , et al. An agorithm based on a feature interaction-based keypoint detector and sim-CSPNet for SAR image registration[J]. Journal of Radars, 2022, 11 (6): 1081- 1097.
24	ZHANG Y C , ZHANG W B , JI Y Y , et al. Complete and accurate holly fruits counting using YOLOX object detection[J]. Computers and Electronics in Agriculture, 2022, 198, 107062. doi: 10.1016/j.compag.2022.107062
25	DEVER W G . The chronology of Syria-Palestine in the second millennium BCE: a review of current issues[J]. Bulletin of the American Schools of Oriental Research, 1992, 288 (1): 1- 25.
26	SONG G L, LIU Y, WANG X G. Revisiting the sibling head in object detector[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 11563-11572.
27	FU A M , ZHANG X L , XIONG N X , et al. VFL: a verifiable federated learning with privacy-preserving for big data in industrial IOT[J]. IEEE Trans. on Industrial Informatics, 2020, 18 (5): 3316- 3326.
28	WANG Z H , LIU H , XU S X , et al. A diffraction measurement model and particle filter tracking method for RSS-based DFL[J]. IEEE Journal on Selected Areas in Communications, 2015, 33 (11): 2391- 2403.
29	LI X , WANG W H , WU L J , et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[J]. Advances in Neural Information Processing Systems, 2020, 33, 21002- 21012.
30	RAZAQ A , HAYAT T , KHAN S A , et al. ATSS model based upon applications of Cattaneo-Christov thermal analysis for entropy optimized ternary nanomaterial flow with homogeneous-heterogeneous chemical reactions[J]. Alexandria Engineering Journal, 2023, 79, 390- 401.

模型	平均准确率均值/%	参数量	运算量	时延/ms	每秒处理帧数
基线模型	48.3	55.58	115.77	15.3	70.3
增加Anchor-free	48.0(-0.3)	53.68	114.78	14.1	70.2
增加CSPResNet	48.7(+0.7)	47.63	101.87	11.9	85.6
增加TAL	49.6(+0.9)	48.42	104.75	12.2	84.1
增加ET-head	50.1(+0.5)	52.31	110.07	13.1	78.3

方法	mAP
ATSS	43.1
SimOTA	44.3
TAL	45.2

算法	mAP1/%	mAP2/%	FPS
YOLOX	80.3	58.9	70.3
YOLOv7	79.9	57.4	65.1
可拓展高效目标检测网络	75.1	52.1	66.7
单发多盒检测网络	81.2	55.6	72.3
区域卷积神经网络	78.1	51.4	62.2
级联卷积神经网络	75.2	52.3	59.8
视网膜网络	74.8	49.8	65.4
全卷积单阶段目标检测	76.6	53.1	76.1
本文网络	82.6	62.3	78.0

训练集与测试集比例	mAP
9∶1	91.7
8∶2	92.3
7∶3	91.5
6∶4	91.2

[1]	韩子硕, 范喜全, 付强, 马传焱, 张冬冬. 面向无人机视角的多源信息融合目标检测[J]. 系统工程与电子技术, 2025, 47(1): 52-61.
[2]	任晓昱, 林瑞奇, 邓云开, 田卫明, 胡程. 基于模态分解的地基雷达慢速弱目标检测方法[J]. 系统工程与电子技术, 2025, 47(1): 70-80.
[3]	蔡伟, 王鑫, 蒋昕昊, 杨志勇, 陈栋. 基于解耦的小样本目标检测方法研究[J]. 系统工程与电子技术, 2024, 46(9): 2941-2950.
[4]	颜上取, 付耀文, 张文鹏, 杨威, 余若峰, 张法桐. 视频合成孔径雷达技术发展现状综述[J]. 系统工程与电子技术, 2024, 46(8): 2650-2666.
[5]	周利, 胡杰民, 付连庆, 凌三力. 基于MDCFT与水平集的高海情弹载雷达成像检测方法[J]. 系统工程与电子技术, 2024, 46(4): 1247-1254.
[6]	黄思佳, 宋纯锋, 李璇. 基于可变尺度先验框的声呐图像目标检测[J]. 系统工程与电子技术, 2024, 46(3): 771-778.
[7]	扈琪, 胡绍海, 刘帅奇. 基于多层显著性模型的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2024, 46(2): 478-487.
[8]	龚峻扬, 付卫红, 刘乃安. SAR图像目标轮廓增强预处理模块设计[J]. 系统工程与电子技术, 2024, 46(12): 4010-4017.
[9]	薛峰涛, 孙天宇, 杨益民, 杨健. 基于全局特征融合的SAR图像旋转舰船目标检测算法[J]. 系统工程与电子技术, 2024, 46(12): 4044-4053.
[10]	关键, 姜星宇, 刘宁波, 丁昊, 黄勇. 海杂波背景下的双极化最大特征值目标检测[J]. 系统工程与电子技术, 2024, 46(11): 3715-3725.
[11]	宋存利, 柴伟琴, 张雪松. 基于改进YOLO v5算法的道路小目标检测[J]. 系统工程与电子技术, 2024, 46(10): 3271-3278.
[12]	黄广佳, 程旭, 饶彬, 王伟. 基于广义Rao检验的单/多比特MIMO雷达运动目标检测方法[J]. 系统工程与电子技术, 2024, 46(1): 105-112.
[13]	施端阳, 林强, 胡冰, 杜小帅. 基于YOLO的航管一次雷达目标检测方法[J]. 系统工程与电子技术, 2024, 46(1): 143-151.
[14]	汪萌, 诸兵. 不确定性建模在2D和3D目标检测中的应用[J]. 系统工程与电子技术, 2023, 45(8): 2370-2376.
[15]	成倩, 李佳, 杜娟. 基于YOLOv5的光学遥感图像舰船目标检测算法[J]. 系统工程与电子技术, 2023, 45(5): 1270-1276.