Improved FCOS Two-Stage SAR Ship Detection Algorithm

doi:10.3778/j.issn.1002-8331.2102-0270

Abstract

Abstract:

Recently, the anchor-free object detection algorithms have been gradually applied to SAR ship detection. Among them, the FCOS algorithm eliminates the dependence on the setting of anchor parameters, and is more robust to multi-scale and multi-modal ship detection, but there are still two problems：firstly, the algorithm directly performs pixel-by-pixel regression, and the large search space and the difficulty of target regression leads to inaccurate detection. secondly, the insufficient use of low-level features by the feature pyramid leads to amounts of small targets missed. To solve these problems, improvements are made based on FCOS. A two-stage anchor-free detection algorithm is constructed by adding a feature enhancement network. As the first stage, the network provides refined guidance for the detection process, meanwhile enhances the ship feature expression ability. It improves the feature pyramid by introducing more features and adding skip connections to improve the utilization of low-level features. Experiments on datasets SSDD and SAR-Ship-Dataset demonstrate that the mean Average Precision（mAP） is 9.5 and 3.4 percentage points higher than FCOS, and 3.6 and 1.0 percentage points higher than other popular ship detection algorithms respectively, which fully verifies the effectiveness of the proposed algorithm.

Key words: Synthetic Aperture Radar（SAR）, ship detection, Fully Convolutional One-Stage object detector（FCOS）, two-stage, feature enhancement

摘要：

近年来无锚框的目标检测算法逐渐被应用于SAR舰船检测，其中FCOS算法摆脱了对锚框参数设置的依赖，对多尺度、多形态舰船检测的鲁棒性更好，但仍存在两个问题：第一、该算法直接进行逐像素点回归，因搜索空间过大、目标回归困难导致检测不够准确；第二、其中特征金字塔对低层特征利用仍有不足导致小目标大量漏检。针对上述问题基于FCOS进行改进，通过增加特征增强网络构建了二阶段无锚框检测算法。该网络作为第一阶段对检测过程进行精细化引导，同时增强了舰船特征表达能力。通过引入更多特征并增加跳跃连接改进特征金字塔，提高了低层特征利用率。在数据集SSDD和SAR-Ship-Dataset上的实验结果表明，平均准确率（mAP）相比FCOS分别提高9.5和3.4个百分点，相比其他主流舰船检测算法分别提高3.6和1.0个百分点，充分验证了所提算法的有效性。

关键词: 合成孔径雷达, 舰船检测, FCOS算法, 二阶段, 特征增强

LIU Jingsheng, WU Xing, WANG Honggang, LI Jiangnan. Improved FCOS Two-Stage SAR Ship Detection Algorithm[J]. Computer Engineering and Applications, 2021, 57(24): 144-151.

刘竞升，伍星，王洪刚，李姜楠. 改进FCOS的二阶段SAR舰船检测算法[J]. 计算机工程与应用, 2021, 57(24): 144-151.

References

[1] WANG Y，CHEN L，SHI H，et al.Ship detection in synthetic aperture radar imagery based on discriminative dictioary learning[C]//Proceedings of the 2019 6th Asia-Pacific Conference on Synthetic Aperture Radar（APSAR），2019：1-4.
[2] 李健伟，曲长文，彭书娟，等.基于卷积神经网络的SAR图像舰船目标检测[J].系统工程与电子技术，2018，40（9）：1953-1959.
LI J W，QU C W，PENG S J，et al.Ship detection in SAR images based on convolutional neural network[J].Systems Engineering and Electronics，2018，40（9）：1953-1959.
[3] CHANG Y，ANAGAW A，CHANG L，et al.Ship detection based on YOLOv2 for SAR imagery[J].Remote Sensing，2019，11：786-790.
[4] 苏娟，杨龙，黄华，等.用于SAR图像小目标舰船检测的改进SSD算法[J].系统工程与电子技术，2020，42（5）：1026-1034.
SU J，YANG L，HUANG H，et al.Improved SSD algorithm for small-sized SAR ship detection[J].Systems Engineering and Electronics，2020，42（5）：1026-1034.
[5] WANG Y Y，CHAO W，HONG Z，et al.Automatic ship detection based on RetinaNet using multi-resolution Gaofen-3 imagery[J].Remote Sensing，2019，11（5）：531-545.
[6] 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 Sciences），2020，47（2）：85-91.
[7] 顾振辉，姜文刚.基于Mask R-CNN改进的遥感图像舰船检测[J].计算机工程与应用，2020，56（8）：171-176.
GU Z H，JIANG W G.Improved remote sensing image ship detection based on Mask R-CNN[J].Computer Engineering and Applications，2020，56（8）：171-176.
[8] PANG J M，CHEN K，SHI J，et al.Libra R-CNN：towards balanced learning for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：821-830.
[9] WEI S，SU H，MING J，et al.Precise and robust ship detection for high-resolution SAR imagery based on HR-SDNET[J].Remote Sensing，2020，12：167-196.
[10] CUI Z Y，Qi L，ZONG J C，et al.Dense attention pyramid networks for multi-scale ship detection in SAR images[J].IEEE Transactions on Geoscience and Remote Sensing，2019，57（11）：8983-8997.
[11] LIU N Y，CUI Z Y，CAO Z J，et al.Scale-transferrable pyramid network for multi-scale ship detection in sar images[C]//IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium，2019：1-4.
[12] 胡庆，李润生，许岩，等.SAR影像船舶目标检测技术研究[J].测绘科学技术学报，2020，37（5）：479-487.
HU Q，LI R S，XU Y，et al.Research on SAR ship detection[J].Journal of Geomatics Science and Technology，2020，37（5）：479-487.
[13] 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.
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.
[14] ZHAO Y，ZHAO L，XIONG B，et al.Attention receptive pyramid network for ship detection in SAR images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：2738-2756.
[15] 张筱晗，姚力波，吕亚飞，等.双向特征融合的数据自适应SAR图像舰船目标检测模型[J].中国图象图形学报，2020，25（9）：1943-1952.
ZHANG X H，YAO L B，LYU Y F，et al.Data-adaptive single-shot ship detector with a bidirectional feature fusion module for SAR images[J].Journal of Image and Graphics，2020，25（9）：1943-1952.
[16] CHEN P，LI Y，ZHOU H，et al.Detection of small ship objects using anchor boxes cluster and feature pyramid network model for SAR imagery[J].Journal of Marine Science and Engineering，2020，8（2）：112-125.
[17] KONG T，SUN F C，LIU H P，et al.Foveabox：beyond anchor-based object detector[J].IEEE Transactions on Image Processing，2020，29：7389-7398.
[18] 侯笑晗，金国栋，谭力宁.基于无锚框检测网络FCOS的SAR舰船目标检测算法[M]//国家安全地球物理丛书（十六）大数据与地球物理.西安：西安地图出版社，2020：162-166.
HOU X H，JIN G D，TAN L N.An SAR ship detection algorithm based on anchor-free FCOS[M].National security geophysics series （16） big data and geophysics.Xi’an：Xi’an Map Publishing House，2020：162-166.
[19] TIAN Z，SHEN C H，CHEN H，et al.FCOS：fully convolutional one-stage object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2019：9627-9636.
[20] YANG Z，LIU S，HU H，et al.Reppoints：point set representation for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9657-9666.
[21] MAO Y，LI X，LI Z，et al.An Anchor-free SAR ship detector with only 1.17 M parameters[C]//Proceedings of the 2020 International Conference on Aviation Safety and Information Technology，2020：182-186.
[22] GAO F，HE Y S，WANG J，et al.Anchor-free convolutional network with dense attention feature aggregation for ship detection in SAR images[J].Remote Sensing，2020，12（16）：2619-2644.
[23] GUO H，YANG X，WANG N，et al.A CenterNet++ model for ship detection in SAR images[J].Pattern Recognition，2021，112：107787-107797.
[24] CUI Z，WANG X，LIU N，et al.Ship detection in large-scale SAR images via spatial shuffle-group enhance attention[J].IEEE Transactions on Geoscience and Remote Sensing，2021，50（1）：379-391.
[25] FU J M，SUN X，WANG Z R，et al.An anchor-free method based on feature balancing and refinement network for multiscale ship detection in SAR images[J].IEEE Transactions on Geoscience and Remote Sensing，2020，59（2）：1331-1344.
[26] LIN T Y，DOLLAR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[27] REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN：towards realtime object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[28] KONG T，SUN F C，YAO A B，et al.Ron：reverse connection with objectness prior networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：5936-5944.
[29] YU J H，JIANG Y N，WANG Z Y，et al.Unitbox：an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia，2016：516-520.
[30] LIN T Y，PRIYA G，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[31] GAO F，SHI W，WANG J，et al.Enhanced feature extraction for ship detection from multi-resolution and multi-scene synthetic aperture radar（SAR） images[J].Remote Sensing，2019，11（22）：2694.
[32] WANG J P，LIN Y Q，GUO J，et al.SSS-YOLO：towards more accurate detection for small ships in SAR image[J].Remote Sensing Letters，2021，12（2）：122-131.
[33] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[34] WANG Y Y，WANG C，ZHANG H，et al.A SAR dataset of ship detection for deep learning under complex backgrounds[J].Remote Sensing，2019，11（7）：765-779.
[35] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft coco：common objects in context[C]//European Conference on Computer Vision.Cham：Springer，2014：740-755.
[36] YU F，WANG D，SHELHAMER E，et al.Deep layer aggregation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：2403-2412.