基于中心点和语义信息的多方向遥感舰船检测

doi:10.12305/j.issn.1001-506X.2022.06.02

摘要/Abstract

摘要：

在高分辨率遥感影像解译中, 舰船目标的检测一直是研究热点。针对遥感影像中近岸舰船排列密集、方向各异以及背景复杂等问题, 本文提出一种基于旋转中心点网络和语义信息(rotated CenterNet using semantic information, RSI-CenterNet)的多方向遥感舰船目标检测方法。首先, 基于关键点检测网络, 在检测阶段添加目标角度回归分支, 以预测目标方向; 其次, 添加语义分割分支, 并将其输出的特征与检测部分的输入特征进行融合以强化目标区域的特征信息; 最后, 引入注意力模块, 以强化目标显著区域与通道的特征, 提升检测精度。实验结果表明, 与其他多种先进方法相比, 本文方法具有更高的检测精度与检测速度, 在高分辨率船舶数据集(High Resolution Ship Collections 2016, HRSC2016)上的平均精度达到88.31%, 检测速度达到17.8 FPS。

关键词: 高分辨率遥感图像, 舰船目标, 关键点检测, 语义信息, 多方向检测

Abstract:

Ship detection is a hotspot in the field of high-resolution remote sensing image interpretation. Aiming at the challenges of dense arrangement, different directions, and complex background of ships in remote sensing images, a rotated CenterNet using semantec information (RSI-CenterNet) multidirectional ship target detection method is proposed. First, we add a branch to predict the angle of objects in CenterNet. Second, a semantic segmentation branch is added, and the feature of semantic segmentation branch is used to guide the detection head to locate the center point more accurately. Finally, an attention module is introduced to enhance the feature of the significant areas and channels. Experimental results show that compared with other advanced methods, the proposed method has higher detection accuracy and detection speed, with an average accuracy of 88.31% and detection speed of 17.8 FPS in HRSC2016 dataset.

Key words: high-resolution remote sensing images, ship target, key-point detection, semantic information, multi-direction detection

中图分类号:

TN957

李润林, 邹焕新, 曹旭, 成飞, 贺诗甜, 李美霖. 基于中心点和语义信息的多方向遥感舰船检测[J]. 系统工程与电子技术, 2022, 44(6): 1772-1781.

Runlin LI, Huanxin ZOU, Xu CAO, Fei CHENG, Shitian HE, Meilin LI. Multi-direction remote sensing ship detection based on center point and semantic information[J]. Systems Engineering and Electronics, 2022, 44(6): 1772-1781.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

图11

表2

图12

参考文献 32

1	王伦文, 冯彦卿, 张孟伯. 光学遥感图像目标检测方法[J]. 系统工程与电子技术, 2019, 41 (10): 2163- 2169. doi: 10.3969/j.issn.1001-506X.2019.10.02
	WANG L W , FENG Y Q , ZHANG M B . Target detection method for optical remote sensing imagery[J]. Systems Engineering and Electronics, 2019, 41 (10): 2163- 2169. doi: 10.3969/j.issn.1001-506X.2019.10.02
2	MA L, GUO J, WANG Y, et al. Ship detection by salient convex boundaries[C]//Proc. of the 3rd International Congress on Image and Signal Processing, 2010: 202-205.
3	储昭亮, 王庆华, 陈海林, 等. 基于极小误差阈值分割的舰船自动检测方法[J]. 计算机工程, 2007, (11): 239- 241.239-241, 269 doi: 10.3969/j.issn.1000-3428.2007.11.086
	CHU Z L , WANG Q H , CHEN H L , et al. Ship auto detection method based on minimum error threshold segmentation[J]. Computer Engineering, 2007, (11): 239- 241.239-241, 269 doi: 10.3969/j.issn.1000-3428.2007.11.086
4	胡俊华, 徐守时, 陈海林, 等. 基于局部自相似性的遥感图像港口舰船检测[J]. 中国图象图形学报, 2009, 14 (4): 591- 597.
	HU J H , XU S S , CHEN H L , et al. Detection of ships in harbor in remote sensing image based on local self-similarity[J]. Journal of Image and Graphics, 2009, 14 (4): 591- 597.
5	尤晓建, 徐守时, 侯蕾. 基于特征融合的可见光图像舰船检测新方法[J]. 计算机工程与应用, 2005, (19): 199- 202. doi: 10.3321/j.issn:1002-8331.2005.19.058
	YOU X J , XU S S , HOU L . A new method for ship detection based on feature fusion in optical image[J]. Computer Engineering and Applications, 2005, (19): 199- 202. doi: 10.3321/j.issn:1002-8331.2005.19.058
6	GAO L N , BI F K , YANG J . Visual attention based model for target detection in large-field images[J]. Journal of Systems Engineering and Electronics, 2011, 22 (1): 150- 156. doi: 10.3969/j.issn.1004-4132.2011.01.020
7	肖利平, 曹炬, 高晓颖. 复杂海地背景下的舰船目标检测[J]. 光电工程, 2007, (6): 6- 10.
	XIAO L P , CAO J , GAO X Y . Detection for ship targets in complicated background of sea and land[J]. Opto-E1ectronic Engineering, 2007, (6): 6- 10.
8	蒋李兵. 基于高分辨光学遥感图像的舰船目标检测方法研究[D]. 长沙: 国防科学技术大学, 2007.
	JIANG L B. Research on the ship target detection in high spatial resolution optical remote sensing image[D]. Changsha: National University of Defense Technology, 2007.
9	JING Y Y, ZHU X Y, WANG X B, et al. R2CNN: rotational region CNN for orientation robust scene text detection[J]. arXiv preprint arXiv: 1706.09579, 2017.
10	LIU Z K, HU J G, WENG L B, et al. Rotated region based CNN for ship detection[C]//Proc. of the IEEE International Conference on Image Processing, 2017: 900-904.
11	MA J Q , SHAO W Y , YE H , et al. Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Trans.on Multimedia, 2018, 20 (11): 3111- 3122. doi: 10.1109/TMM.2018.2818020
12	DING J, XUE N, LONG Y, et al. Learning RoI transformer for oriented target detection in aerial images[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 2849-2858.
13	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015, 28, 91- 99.
14	孙嘉赤, 邹焕新, 邓志鹏, 等. 基于级联卷积神经网络的港口多方向舰船检测与分类[J]. 系统工程与电子技术, 2020, 42 (9): 1903- 1910.
	SUN J C , ZOU H X , DENG Z P , et al. Oriented inshore ship detection and classification based on cascade RCNN[J]. Systems Engineering and Electronics, 2020, 42 (9): 1903- 1910.
15	CAI Z, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 6154-6162.
16	YANG X, LIU Q Q, YAN J C, et al. R3det: refined single-stage detector with feature refinement for rotating object[EB/OL]. [2021-06-25]. https://arxiv.org/abs/1908.05612.
17	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proc. of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
18	LIAO M H, ZHU Z, SHI B G, et al. Rotation-sensitive regression for oriented scene text detection[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recog-nition, 2018: 5909-5918.
19	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proc. of the European Conference on Computer Vision, 2016: 21-37.
20	张筱晗, 姚力波, 吕亚飞, 等. 基于中心点的遥感图像多方向舰船目标检测[J]. 光子学报, 2020, 49 (4): 210- 218.
	ZHANG X H , YAO L B , LYU Y F , et al. Center based model for arbitrary-oriented ship detection in remote sensing images[J]. Acta Photonica Sinica, 2020, 49 (4): 0410005.
21	LI L H , ZHOU Z Q , WANG B , et al. A novel CNN-based method for accurate ship detection in HR optical remote sensing images via rotated bounding box[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 59 (1): 689- 699.
22	LIU Q W , XIANG X Q , YANG Z , et al. Arbitrary direction ship detection in remote-sensing images based on multitask learning and multiregion feature fusion[J]. IEEE Trans.on Geoscience and Remote Sensing, 2021, 59 (2): 1553- 1564. doi: 10.1109/TGRS.2020.3002850
23	LI H , DENG L B , YANG C , et al. Enhanced YOLO v3 tiny network for real-time ship detection from visual image[J]. IEEE Access, 2021, 9, 16692- 16706. doi: 10.1109/ACCESS.2021.3053956
24	WU Y F , ZHAO W , ZHANG R F , et al. AMR-Net: arbitrary-oriented ship detection using attention module, multi-scale feature fusion and rotation pseudo-label[J]. IEEE Access, 2021, 9, 68208- 68222. doi: 10.1109/ACCESS.2021.3075857
25	CHEN J J , XIE F Y , LU Y Y , et al. Finding arbitrary-oriented ships from remote sensing images using corner detection[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 17 (10): 1712- 1716.
26	LAW H, DENG J. CornerNet: detecting objects as paired keypoints[C]//Proc. of the European Conference on Computer Vision, 2018: 734-750.
27	ZHOU X, WANG D, KRAHENBUHL P. Objects as points[EB/OL]. [2021-06-25]. https://arxiv.org/abs/1904.07850.
28	ZHOU L , WEI H R , LI H , et al. Arbitrary-oriented object detection in remote sensing images based on polar coordinates[J]. IEEE Access, 2020, 8, 223373- 223384. doi: 10.1109/ACCESS.2020.3041025
29	LIU Z K, YUAN L, WENG L B, et al. A high resolution optical satellite image dataset for ship recognition and some new baselines[C]//Proc. of the International Conference on Pattern Recognition Applications and Methods, 2017, 2: 324-331.
30	EVERINGHAM M , WINN J . The pascal visual object classes challenge 2012 (voc2012) development kit[J]. Pattern Analysis, Statistical Modelling and Computational Learning, 2011, 8, 5.
31	CHEN K, PANG J M, WANG J Q, et al. Hybrid task cascade for instance segmentation[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4974-4983.
32	WOO S, PARK J, LEE J Y, et al. Cbam: convolutional block attention module[C]//Proc. of the European Conference on Computer Vision, 2018: 3-19.

性能参数	舰船目标检测方法
性能参数	R2CNN	RR-CNN	RRPN	RNet-H	RRD	RoI-T	RSI-C
骨干网络	R101	VGG16	R101	R101	VGG16	R101	R101
输入尺寸	800×800	-	800×800	800×800	384×384	512×800	512×512
检测速度/FPS	5	-	1.5	14	-	6	17.8
AP/%	73.07	75.7	79.08	82.89	84.3	86.2	88.31

网络模型	CBAM	语义信息	AP/%	检测速度/FPS	参数量/M
R-C	-	-	80.05	24.63	121.0
R-C+改进	√	-	85.27	22.73	121.1
	-	√	87.43	22.00	129.1
	√	√	87.81	21.16	129.2

[1]	潘超凡, 李润生, 许岩, 胡庆, 牛朝阳, 刘伟. 基于感知向量的光学遥感图像舰船检测[J]. 系统工程与电子技术, 2022, 44(12): 3631-3640.
[2]	雷禹, 冷祥光, 周晓艳, 孙忠镇, 计科峰. 基于改进ResNet网络的复数SAR图像舰船目标识别方法[J]. 系统工程与电子技术, 2022, 44(12): 3652-3660.
[3]	贾晓雅, 汪洪桥, 杨亚聃, 崔忠马, 熊斌. 基于YOLO框架的无锚框SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(12): 3703-3709.
[4]	李永刚, 朱卫纲, 黄琼男, 李云涛, 何永华. 复杂背景下SAR图像近岸舰船目标检测[J]. 系统工程与电子技术, 2022, 44(10): 3096-3103.
[5]	曹旭, 邹焕新, 成飞, 李润林, 贺诗甜. 基于RHTC网络的飞机目标检测与精细识别[J]. 系统工程与电子技术, 2021, 43(12): 3439-3451.
[6]	李晨瑄, 钱坤, 胥辉旗. 基于深浅层特征融合的舰船要害关键点检测算法[J]. 系统工程与电子技术, 2021, 43(11): 3239-3249.
[7]	季玙璠, 王伦文, 张孟伯. 通信辐射源运动轨迹相似性分析[J]. 系统工程与电子技术, 2020, 42(9): 1920-1926.
[8]	杨龙, 苏娟, 李响. 基于深度卷积神经网络的SAR舰船目标检测[J]. 系统工程与电子技术, 2019, 41(9): 1990-1997.
[9]	杨青青, 樊桂花. 基于改进模糊综合评判法的建筑物毁伤效果评估[J]. 系统工程与电子技术, 2018, 40(9): 2026-2031.
[10]	罗畅, 王洁, 王世强, 史通, 任卫华. 基于泛化深度迁移特征的高分遥感场景分类[J]. 系统工程与电子技术, 2018, 40(3): 682-691.
[11]	赵志国，陈建文，鲍拯. 一种改进的OTHR自适应海杂波抑制方法[J]. Journal of Systems Engineering and Electronics, 2012, 34(5): 909-914.
[12]	余定峰，陈谦，姚菁晶，何思远，朱国强，胡卫东. 海上舰船目标HRRP特性仿真[J]. Journal of Systems Engineering and Electronics, 2010, 32(12): 2552-2556.