基于YOLO框架的无锚框SAR图像舰船目标检测

doi:10.12305/j.issn.1001-506X.2022.12.14

系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (12): 3703-3709.doi: 10.12305/j.issn.1001-506X.2022.12.14

基于YOLO框架的无锚框SAR图像舰船目标检测

贾晓雅^1,², 汪洪桥^1,*, 杨亚聃³, 崔忠马², 熊斌²

1. 火箭军工程大学作战保障学院, 陕西西安 710025
2. 北京遥感设备研究所, 北京 100854
3. 中国航天科工集团有限公司科研生产部, 北京 100048

收稿日期:2021-07-08 出版日期:2022-11-14 发布日期:2022-11-24
通讯作者: 汪洪桥
作者简介:贾晓雅(1993—), 女, 硕士研究生, 主要研究方向为SAR图像目标检测|汪洪桥(1979—), 男, 副教授, 博士, 主要研究方向为人工智能、机器学习、遥感图像处理|杨亚聃(1983—), 男, 高级工程师, 硕士, 主要研究方向为电子对抗|崔忠马(1978—), 男, 研究员, 硕士, 主要研究方向为雷达系统|熊斌(1982—), 男, 高级工程师, 博士, 主要研究方向为雷达系统
基金资助:
陕西省自然科学基础研究计划(2020JM-358)

Anchor free SAR image ship target detection method based on the YOLO framework

Xiaoya JIA^1,², Hongqiao WANG^1,*, Yadan YANG³, Zhongma CUI², Bin XIONG²

1. Department of Information Engineering, Rocket Force University of Engineering, Xi'an 710025, China
2. Beijing Institute of Remote Sensing Equipment, Beijing 100854, China
3. Scientific Research and Production Department, China Aerospace Science and Industry Corporation, Beijing 100048, China

Received:2021-07-08 Online:2022-11-14 Published:2022-11-24
Contact: Hongqiao WANG

摘要/Abstract

摘要：

面向合成孔径雷达(synthetic aperture radar, SAR)多目标检测应用, 提出了一种基于YOLO (you only look once) 框架的无锚框SAR图像舰船目标检测方法。该方法针对YOLOv3锚框需要预先设定且无法完美契合的弊端, 通过采用无锚框方法更好适应所检测目标的大小, 便于多尺度目标使用。在此基础上, 给CSPDarknet53网络增加了注意力机制作为特征提取网络, 然后经过能够增大感受野的改进特征金字塔网络(feature pyramid network, FPN)后, 把特征图传给无锚框检测头, 有效提升了目标类别和位置的预测精度。实验证明, 所提算法在公开SAR舰船数据集上平均精度比YOLOv3提高3.8%，达到了94.8%, 虚警率降低4.8%。

关键词: 合成孔径雷达图像, YOLO, 无锚框, 舰船目标检测

Abstract:

For synthetic aperture radar (SAR) multi-target detection applications, this paper proposes an anchor free SAR image ship target detection method based on the you only look once (YOLO) framework. This method is aimed at the disadvantage that the YOLOv3 anchor needs to be preset and cannot fit perfectly. By adopting the anchor free method, it can better adapt to the size of the detected target and facilitate the use of multi-scale targets. On this basis, the attention mechanism is added to the CSPDarknet53 network as a feature extraction network, and then after an improved feature pyramid network (FPN) that can increases the receptive field, the feature map is transmitted to the anchor free detection head, which effectively improves the prediction precision of the target category and location. Experiments show that the improved algorithm has an average precision of 3.8% higher than YOLOv3 on the public SAR ship data set, reaching 94.8%, and the false alarm rate is reduced by 4.8%.

Key words: synthetic aperture radar (SAR) image, YOLO, anchor free, ship target detection

中图分类号:

TP751

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.

Xiaoya JIA, Hongqiao WANG, Yadan YANG, Zhongma CUI, Bin XIONG. Anchor free SAR image ship target detection method based on the YOLO framework[J]. Systems Engineering and Electronics, 2022, 44(12): 3703-3709.

图/表 8

图1

图2

图3

表1

表2

图4

图5

图6

参考文献 38

1	ROBEY F C , FUHRMANN D R , KELLY E J , et al. A CFAR adaptive matched filter detector[J]. IEEE Trans.on Aerospace & Electronic Systems, 1992, 28 (1): 208- 216.
2	LIM H , CHAE D , YOO J H , et al. Template matching-based target recognition algorithm development and verification using SAR images[J]. Journal of the Korea Institute of Military Science and Technology, 2014, 17 (3): 364- 377. doi: 10.9766/KIMST.2014.17.3.364
3	GROSSO E, GUIDA R. A new automatic ship wake detection for Sentinel-1 imagery[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2020: 1259-1262.
4	何耀民, 何华锋, 徐永壮, 等. 基于改进小波变换的海上目标检测[J]. 系统工程与电子技术, 2020, 42 (1): 83- 89.
	HE Y M , HE H F , XU Y Z , et al. Marine target detection based on improved wavelet transform[J]. Systems Engineering and Electronics, 2020, 42 (1): 83- 89.
5	魏松杰, 张泽栋, 徐臻, 等. 基于多尺寸特征叠加的SAR舰船目标检测方法[J]. 湖南大学学报(自然科学版), 2021, 48 (4): 80- 89.
	WEI S J , ZHANG Z D , XU Z , et al. Method of vessel target detection in SAR images based on multi-scale feature superposition[J]. Journal of Hunan University (Natural Sciences), 2021, 48 (4): 80- 89.
6	YANG M, SHI X B. A deep learning model S-Darknet suitable for small target detection[C]//Proc. of the 6th International Symposium on Advances in Electrical, Electronics and Computer Engineering, 2021.
7	ZHANG R H, XU M, SHI Y X, et al. Infrared target detection using intensity saliency and self-attention[C]//Proc. of the IEEE International Conference on Image Processing, 2020: 1991-1995.
8	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.
9	HE K M , ZHANG X Y , REN S Q , et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
10	GIRSHICK R. Fast R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
11	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans. Pattern Analysis & Machine Intelligence, 2017, 39 (6): 1137- 1149.
12	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.
13	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.
14	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proc. of the Computer Vision and Pattern Recognition, 2017: 6517-6525.
15	REDMON J, FARHADI A. YOLOv3: an incre-mental improvement[EB/OL]. [2020-07-16]. http://arxiv.org/abs/1804.02767.
16	BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2020-04-23]. https://arx-iv.org/abs/2004.10934.
17	SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014, 770- 778.
18	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.
19	XIE S N, 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.
20	NEWELL A, YANG K Y, DENG J. Stacked hourglass networks for human pose estimation[C]//Proc. of the European Conference on Computer Vision, 2016: 483-499.
21	HOWARD A G, ZHU M L, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. [2017-04-17]. https://arxiv.org/abs/1704.04861.
22	TAN M X, LE Q V. EfficientNet: rethinking model scaling for convolutional neural networks[C]//Proc. of the International Conference on Machine Learning, 2019: 6105-6114.
23	SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 5686-5696.
24	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
25	GHIASI G, LIN T, LE Q V. NAS-FPN: learning scalable feature pyramid architecture for object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 7029-7038.
26	PANG J M, CHEN K, SHI J P, et al. Libra R-CNN: towards balanced learning for object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 821-830.
27	LAW H , DENG J . CornerNet: detecting objects as paired keypoints[J]. International Journal of Computer Vision, 2020, 128 (3): 642- 656. doi: 10.1007/s11263-019-01204-1
28	ZHOU X Y, ZHUO J C, KRÄHENBVHL P. Bottom-up object detection by grouping extreme and center points[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 850-859.
29	ZHOU X Y, WANG D Q, KRÄHENBVHL P. Objects as points[EB/OL]. [2019-04-16]. http://arxiv.org/abs/1904.07850.
30	ZHU C C, HE Y H, SAVVIDES M. Feature selective anchor-free module for single-shot object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 840-849.
31	TIAN Z, SHEN C H, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proc. of the IEEE International Conference on Computer Vision, 2019, 27: 9626-9635.
32	KONG T , SUN F C , LIU H P , et al. FoveaBox: beyound anchor-based object detection[J]. IEEE Trans.on Image Processing, 2020, 29, 7389- 7398. doi: 10.1109/TIP.2020.3002345
33	CAO Y, XU J R, LIN S, et al. GCNet: non-local networks meet squeeze-excitation networks and beyond[C]//Proc. of the International Conference on Computer Vision Workshop, 2019: 1971-1980.
34	LIU S T, HUANG D, WANG Y H. Receptive field block net for accurate and fast object detection[C]//Proc. of the European Conference on Computer Vision, 2018: 404-419.
35	WANG X L, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognitiion, 2018: 7794-7803.
36	HU J , SHEN L , ALBANIE S , et al. Squeeze-and-excitation networks[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2017, 42 (8): 2011- 2023.
37	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 IEEE SAR in Big Data Era: Models, Methods and Applications, 2017.
38	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.

实验序号	Backbone	Neck	Head	AP/%	Recall/%	FA/%	大小/MB
1	Darknet53	YOLOv3Neck	YOLOv3Head	91.0	93.3	14.8	246.0
2	Darknet53	FPN	FoveaBox	94.7	96.0	16.6	208.6
3	CSPDarknet53	FPN	FoveaBox	94.4	95.6	14.5	152.7
4	CSPDarknet53	FPN+RFB	FoveaBox	93.8	95.0	12.8	155.7
5	CSPDarknet53+GC	FPN	FoveaBox	94.1	95.4	9.3	152.9
6	CSPDarknet53+GC	FPN+RFB	FoveaBox	94.8	96.0	10.0	155.9

网络	AP/%	Recall/%	FA/%	检测速度task/s
YOLOv3	91.0	93.3	14.8	30.1
FoveaBox	91.2	95.0	46.7	30.5
本文方法	94.8	96.0	10.0	23.7

[1]	汤寓麟, 李厚朴, 张卫东, 边少锋, 翟国君, 刘敏, 张晓平. 侧扫声纳检测沉船目标的轻量化DETR-YOLO法[J]. 系统工程与电子技术, 2022, 44(8): 2427-2436.
[2]	钱坤, 李晨瑄, 陈美杉, 王瑶. 基于YOLOv5的舰船目标及关键部位检测算法[J]. 系统工程与电子技术, 2022, 44(6): 1823-1832.
[3]	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.
[4]	宋子壮, 杨嘉伟, 张东方, 王诗强, 张硕. 基于无锚框的红外多类别多目标实时跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 401-409.
[5]	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.
[6]	王彬, 王国宇. 基于改进的深度学习网络的SAR图像瞬时海岸线自动提取算法[J]. 系统工程与电子技术, 2021, 43(8): 2108-2115.
[7]	马倩, 邹焕新, 李美霖, 成飞, 贺诗甜. 基于SNIC的双时相SAR图像超像素协同分割算法[J]. 系统工程与电子技术, 2021, 43(5): 1198-1209.
[8]	李广帅, 苏娟, 李义红, 李响. 基于卷积神经网络与注意力机制的SAR图像飞机检测[J]. 系统工程与电子技术, 2021, 43(11): 3202-3210.
[9]	刘书君, 宋健, 沈晓东, 曹建鑫. 基于非凸加权范数约束的SAR图像降斑[J]. 系统工程与电子技术, 2020, 42(4): 813-818.
[10]	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.
[11]	周龙, 韦素媛, 崔忠马, 房嘉奇, 杨小婷, 杨龙. 基于深度学习的复杂背景雷达图像多目标检测#br#[J]. 系统工程与电子技术, 2019, 41(6): 1258-1264.
[12]	韩萍, 贾锟, 卢晓光, 韩宾宾. PolSAR图像的改进非局部均值滤波算法[J]. 系统工程与电子技术, 2019, 41(5): 992-999.
[13]	彭书娟, 曲长文, 李健伟, 邵嘉琦, 骆卉子. 基于ROEWA算子局部活动轮廓的SAR图像分割算法[J]. 系统工程与电子技术, 2019, 41(2): 280-290.
[14]	邱洪彬, 王雪梅, 许哲, 张钧, 宿常鹏. 基于二维能量检测的舰船SAR图像阈值分割[J]. 系统工程与电子技术, 2019, 41(12): 2747-2753.
[15]	黄晨霞, 殷君君, 杨健. 基于l1范数主成分分析的极化SAR图像变化检测[J]. 系统工程与电子技术, 2019, 41(10): 2214-2220.

基于YOLO框架的无锚框SAR图像舰船目标检测

Anchor free SAR image ship target detection method based on the YOLO framework

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 38

相关文章 15

编辑推荐

Metrics

本文评价