基于特征增强网络的SAR图像舰船目标检测

doi:10.12305/j.issn.1001-506X.2023.04.12

摘要/Abstract

摘要：

合成孔径雷达(synthetic aperture radar, SAR)图像场景复杂度高、舰船目标尺度小, 传统方法检测效率低、虚警概率大。针对以上问题, 提出一种特征增强网络用于SAR图像舰船目标检测。首先, 利用I-Darknet-53(improved Darknet-53)提取特征信息, 构建4层特征金字塔丰富低层特征。其次, 将多个特征层进行跨尺度连接, 使低层细节信息更易于向高层语义信息映射, 增强特征的传播和重用。最后, 利用多尺度注意力模型增强特征信息, 为检测器提供高质量的判断依据。试验结果表明, 所提算法在SSDD数据集上的平均检测精度为95%。相较于其他网络模型, 所提算法具有明显优势。

关键词: 合成孔径雷达图像, 目标检测, 特征增强, 多尺度融合, 多尺度注意力

Abstract:

Traditional detection methods are inefficient and have a high probability of false alarm due to the high complexity of synthetic aperture radar (SAR) image scenes and small scale of ship targets. To address these problems, this paper proposes a feature-enhanced network for SAR image ship target detection is proposed. Firstly, feature information is extracted using I-Darknet53 (improved Darknet-53), and a four-layer feature pyramid is constructed to enrich low-level features. Secondly, multiple feature layers are connected across scales to make low-level detail information easier to map to high-level semantic information, thus enhancing the propagation and reuse of features. Finally, the feature information is enhanced using a multi-scale attention model to provide a high-quality judgment basis for the detector. The experimental results show that the average detection accuracy of the proposed algorithm on the SSDD dataset is 95%. The proposed algorithm has high precision compared with other network models.

Key words: synthetic aperture radar (SAR) image, target detection, feature enhancement, multi-scale fusion, multi-scale attention

中图分类号:

TP391

张冬冬, 王春平, 付强. 基于特征增强网络的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2023, 45(4): 1032-1039.

Dongdong ZHANG, Chunping WANG, Qiang FU. Ship target detection in SAR image based on feature-enhanced network[J]. Systems Engineering and Electronics, 2023, 45(4): 1032-1039.

图/表 16

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

表2

表3

图10

表4

图11

图12

参考文献 24

1	刘洁瑜, 赵彤, 刘敏. 基于RetinaNet的SAR图像舰船目标检测[J]. 湖南大学学报(自然科学版), 2020, 47 (2): 85- 91.
	LIU J Y , ZHAO T , LIU M . Ship target detection in SAR image based on RetinaNet[J]. Journal of Hunan University (Natural Science Edition), 2020, 47 (2): 85- 91.
2	韩子硕, 王春平, 付强, 等. 基于超密集特征金字塔网络的SAR图像舰船检测[J]. 系统工程与电子技术, 2020, 42 (10): 2214- 2222. doi: 10.3969/j.issn.1001-506X.2020.10.09
	HAN Z S , WANG C P , FU Q , et al. Ship detection in SAR images based on super dense feature pyramid networks[J]. Systems Engineering and Electronics, 2020, 42 (10): 2214- 2222. doi: 10.3969/j.issn.1001-506X.2020.10.09
3	WANG C L , BI F K , ZHANG W P , et al. An intensity-space domain CFAR method for ship detection in HR SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (4): 529- 533. doi: 10.1109/LGRS.2017.2654450
4	ZHAO Z , JI K F , XING X W , et al. Ship surveillance by integration of space-borne SAR and AIS-review of current research[J]. Journal of Navigation, 2014, 67 (1): 177- 189. doi: 10.1017/S0373463313000659
5	FINGAS M F , BROWN C E . Review of ship detection from airborne platforms[J]. Canadian Journal of Remote Sensing, 2001, 27 (4): 379- 385. doi: 10.1080/07038992.2001.10854880
6	KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks[J]. Artificial Neural Network, 2017, 60 (6): 84- 90.
7	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
8	GIRSHICK R. Fast R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
9	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proc. of the 28th International Conference on Neural Information Processing Systems, 2015: 91-99.
10	HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
11	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.
12	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proc. of the IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017: 318-327.
13	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
14	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6517-6525.
15	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2021-04-10]. https://arxiv.org/abs/1804.02767.
16	LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 936-944.
17	SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]//Proc. of the 31st AAAI Conference on Artificial Intelligence, 2017: 4278-4284.
18	LI J W, QU C W, SHAO J Q. Ship detection in SAR images based on an improved faster R-CNN[C]//Proc. of the SAR in Big Data Era: Models, Methods and Applications, 2017.
19	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
20	XIE S, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 5987-5995.
21	HUANG G, LIU Z, VAN D M L, et al. Densely connected convolutional networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2261-2269.
22	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
23	刘杰平, 温竣文, 梁亚玲. 基于多尺度注意力导向网络的单目图像深度估计[J]. 华南理工大学学报(自然科学版), 2020, 48 (12): 52- 62.
	LIU J P , WEN J W , LIANG Y L . Monocular image depth estimation based on multi-scale attention oriented networl[J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48 (12): 52- 62.
24	刘元宁, 吴迪, 朱晓冬, 等. 基于YOLOv3改进的用户界面组件检测算法[J]. 吉林大学学报(工学版), 2021, 51 (3): 1026- 1033.
	LIU Y N , WU D , ZHU X D , et al. User interface components detection algorithm based on improved YOLOv3[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51 (3): 1026- 1033.

数据集	锚框
数据集	1	2	3	4	5	6	7	8	9	10	11	12
SSDD	9, 11	11, 23	19, 13	15, 29	30, 17	22, 50	30, 28	36, 65	52, 24	55, 72	59, 118	123, 39
SSDD	9, 12	12, 24	17, 12	18, 40	27, 17	30, 61	48, 24	59, 113	103, 44	-	-	-

数据集	图像数量	舰船数量
训练集	928	2 061
测试集	232	479

方法	SSDD
方法	TP	FP	FN	P	R	AP
YOLOv3	438	37	41	0.922 1	0.914 4	0.864 1
YOLOv3+I-Darknet-53	442	50	37	0.936 4	0.922 7	0.927 6
YOLOv3+4Layers	456	52	23	0.897 6	0.952 0	0.932 8
YOLOv3+MFPN	443	32	36	0.932 6	0.924 8	0.935 1
YOLOv3+MSA	450	34	29	0.929 6	0.939 5	0.902 3
YOLO-MDM	453	33	26	0.932 1	0.945 7	0.950 2

方法	主干网络	SSDD
方法	主干网络	P	R	AP
YOLOv3	Darknet-53	0.922 1	0.914 4	0.864 1
YOLOv4	Darknet-53	0.884 2	0.975 3	0.971 1
Faster R-CNN	ResNet-50	0.729 0	0.814 2	0.772 3
SSD	Mobilenet-v1	0.980 8	0.525 9	0.524 5
YOLO-MDM	I-Darknet-53	0.932 1	0.945 7	0.950 2

[1]	张昀普, 单甘霖, 黄燕, 付强. 考虑盲区的多移动传感器地面目标检测跟踪调度方法[J]. 系统工程与电子技术, 2023, 45(2): 453-464.
[2]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[3]	肖宇, 邓正宏, 张展. 基于双阶段互信息准则的多目标检测波形设计[J]. 系统工程与电子技术, 2022, 44(9): 2736-2742.
[4]	刘祥, 黄天耀, 刘一民. 频率捷变雷达的扩展目标检测[J]. 系统工程与电子技术, 2022, 44(6): 1833-1838.
[5]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[6]	魏文晓, 刘洁瑜, 沈强, 李成. 基于人眼视点图的特征融合小目标检测算法[J]. 系统工程与电子技术, 2022, 44(4): 1120-1127.
[7]	李洪瑶, 李小强, 韩心中, 谢学立, 席建祥. 基于决策融合的多无人机协同目标检测识别算法[J]. 系统工程与电子技术, 2022, 44(3): 746-754.
[8]	杨磊, 张苏, 盖明慧, 方澄. 高分辨SAR目标成像方向性结构特征增强[J]. 系统工程与电子技术, 2022, 44(3): 808-818.
[9]	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.
[10]	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.
[11]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[12]	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.
[13]	范加利, 田少兵, 黄葵, 朱兴动. 基于Faster R-CNN的航母舰面多尺度目标检测算法[J]. 系统工程与电子技术, 2022, 44(1): 40-46.
[14]	龚树凤, 龙伟军, 贲德, 潘明海. 组网雷达自适应模糊CFAR检测融合算法[J]. 系统工程与电子技术, 2022, 44(1): 100-107.
[15]	杨威, 刘永祥, 付耀文, 黎湘. 基于连续信任函数理论的鲁棒雷达目标检测方法[J]. 系统工程与电子技术, 2021, 43(9): 2463-2469.