《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (7): 2248-2255.DOI: 10.11772/j.issn.1001-9081.2021050831
收稿日期:
2021-05-20
修回日期:
2021-12-15
接受日期:
2021-12-29
发布日期:
2022-03-08
出版日期:
2022-07-10
通讯作者:
赵曙光
作者简介:
凡文俊(1996—),男,湖北天门人,硕士研究生,主要研究方向:人工智能、目标检测基金资助:
Wenjun FAN1, Shuguang ZHAO1(), Lizheng GUO2
Received:
2021-05-20
Revised:
2021-12-15
Accepted:
2021-12-29
Online:
2022-03-08
Published:
2022-07-10
Contact:
Shuguang ZHAO
About author:
FAN Wenjun, born in 1996, M. S. candidate. His research interests include artificial intelligence, target detection.Supported by:
摘要:
目前基于深度学习算法的目标检测技术在合成孔径雷达(SAR)图像船舶检测中取得了显著的成果,然而仍存在着小目标船舶和近岸密集排列船舶检测效果差的问题。针对上述问题,提出了基于改进RetinaNet的船舶检测算法。在传统RetinaNet算法的基础上,首先,将特征提取网络残差块中的卷积改进为分组卷积,以增加网络宽度,从而提高网络的特征提取能力;其次,在特征提取网络的后两个阶段加入注意力机制,让网络更加专注于目标区域,从而提升目标检测能力;最后,将软非极大值抑制(Soft-NMS)加入到算法中,降低算法对于近岸密集排列船舶检测的漏检率。在高分辨率SAR图像数据集(HRSID)和SAR船舶检测数据集(SSDD)上的实验结果表明,所提改进算法对于小目标船舶和近岸船舶的检测效果得到了有效提升,与当前优秀的目标检测模型Faster R-CNN、YOLOv3和CenterNet等相比,在检测精度和速度上更加优越。
中图分类号:
凡文俊, 赵曙光, 郭力争. 基于改进RetinaNet的船舶检测算法[J]. 计算机应用, 2022, 42(7): 2248-2255.
Wenjun FAN, Shuguang ZHAO, Lizheng GUO. Ship detection algorithm based on improved RetinaNet[J]. Journal of Computer Applications, 2022, 42(7): 2248-2255.
数据集 | 船舶目标数量 | 图像尺寸 | 图像数量 | 分辨率/m | |||
---|---|---|---|---|---|---|---|
小目标 | 中等目标 | 大目标 | 高/px | 宽/px | |||
SSDD | 1 529 | 935 | 76 | 190~526 | 214~668 | 1 160 | 1~10 |
HRSID | 9 242 | 7 388 | 321 | 800 | 800 | 5 604 | 0.5~3 |
表1 HRSID数据集与SSD数据集
Tab. 1 HRSID dataset and SSD dataset
数据集 | 船舶目标数量 | 图像尺寸 | 图像数量 | 分辨率/m | |||
---|---|---|---|---|---|---|---|
小目标 | 中等目标 | 大目标 | 高/px | 宽/px | |||
SSDD | 1 529 | 935 | 76 | 190~526 | 214~668 | 1 160 | 1~10 |
HRSID | 9 242 | 7 388 | 321 | 800 | 800 | 5 604 | 0.5~3 |
ResNeXt | GAM模块 | Soft-NMS | AP/% | AP50/% | AP75/% |
---|---|---|---|---|---|
✕ | ✕ | ✕ | 52.3 | 90.0 | 57.4 |
√ | ✕ | ✕ | 53.9 | 91.3 | 58.5 |
√ | √ | ✕ | 55.6 | 92.7 | 59.4 |
√ | ✕ | √ | 55.5 | 92.3 | 60.1 |
√ | √ | √ | 56.1 | 92.8 | 60.7 |
表2 改进算法各模块的消融实验结果
Tab. 2 Ablation experimental results of each module of improved algorithm
ResNeXt | GAM模块 | Soft-NMS | AP/% | AP50/% | AP75/% |
---|---|---|---|---|---|
✕ | ✕ | ✕ | 52.3 | 90.0 | 57.4 |
√ | ✕ | ✕ | 53.9 | 91.3 | 58.5 |
√ | √ | ✕ | 55.6 | 92.7 | 59.4 |
√ | ✕ | √ | 55.5 | 92.3 | 60.1 |
√ | √ | √ | 56.1 | 92.8 | 60.7 |
模型 | 测试时间/s | AP/% | AP50 /% | AP75 /% |
---|---|---|---|---|
RetinaNet | 0.082 | 59.1 | 85.2 | 65.6 |
本文改进算法 | 0.136 | 61.5 | 86.1 | 69.0 |
表3 RetinaNet算法改进前后性能对比
Tab. 3 Performance comparison of RetinaNet algorithm before and after improvement
模型 | 测试时间/s | AP/% | AP50 /% | AP75 /% |
---|---|---|---|---|
RetinaNet | 0.082 | 59.1 | 85.2 | 65.6 |
本文改进算法 | 0.136 | 61.5 | 86.1 | 69.0 |
算法 | 测试时间/s | AP/% | AP50 /% | AP75 /% |
---|---|---|---|---|
YOLOv3 | 0.025 | 46.9 | 87.9 | 46.4 |
SSD | 0.029 | 52.5 | 91.2 | 57.0 |
Faster R-CNN | 0.200 | 55.6 | 90.3 | 63.4 |
Libra R-CNN | 0.060 | 55.4 | 91.6 | 62.0 |
CenterNet | 0.055 | 55.6 | 92.0 | 60.3 |
本文算法 | 0.050 | 56.1 | 92.8 | 60.7 |
表4 不同检测算法的性能对比
Tab. 4 Performance comparison of different detection algorithms
算法 | 测试时间/s | AP/% | AP50 /% | AP75 /% |
---|---|---|---|---|
YOLOv3 | 0.025 | 46.9 | 87.9 | 46.4 |
SSD | 0.029 | 52.5 | 91.2 | 57.0 |
Faster R-CNN | 0.200 | 55.6 | 90.3 | 63.4 |
Libra R-CNN | 0.060 | 55.4 | 91.6 | 62.0 |
CenterNet | 0.055 | 55.6 | 92.0 | 60.3 |
本文算法 | 0.050 | 56.1 | 92.8 | 60.7 |
模型 | 近岸数据集 | 离岸数据集 |
---|---|---|
YOLOv3 | 27.9 | 51.3 |
SSD | 34.6 | 57.1 |
Faster R-CNN | 40.3 | 58.6 |
本文算法 | 41.9 | 59.6 |
表5 不同算法在SSDD数据集的近岸与离岸场景的检测精度对比 (%)
Tab. 5 Detection precision comparison of different algorithms innear-shore and off-shore scenarios of SSDD dataset
模型 | 近岸数据集 | 离岸数据集 |
---|---|---|
YOLOv3 | 27.9 | 51.3 |
SSD | 34.6 | 57.1 |
Faster R-CNN | 40.3 | 58.6 |
本文算法 | 41.9 | 59.6 |
1 | WACKERMAN C C, FRIEDMAN K S, PICHEL W G, et al. Automatic detection of ships in RADARSAT-1 SAR imagery [J]. Canadian Journal of Remote Sensing, 2001, 27(5): 568-577. 10.1080/07038992.2001.10854896 |
2 | 陈慧元,刘泽宇,郭炜炜,等.基于级联卷积神经网络的大场景遥感图像舰船目标快速检测方法[J].雷达学报,2019,8(3):413-424. 10.12000/JR19041 |
CHEN H Y, LIU Z Y, GUO W W, et al. Fast detection of ship targets for large-scale remote sensing image based on a cascade convolutional neural network [J]. Journal of Radars, 2019, 8(3): 413-424. 10.12000/JR19041 | |
3 | ROBEY F C, FUHRMANN D R, KELLY E J, et al. A CFAR adaptive matched filter detector [J]. IEEE Transactions on Aerospace and Electronic Systems, 1992, 28(1): 208-216. 10.1109/7.135446 |
4 | REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. 10.1109/tpami.2016.2577031 |
5 | REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788. 10.1109/cvpr.2016.91 |
6 | LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007. 10.1109/iccv.2017.324 |
7 | KANG M, JI K F, LENG X G, et al. Contextual region-based convolutional neural network with multilayer fusion for SAR ship detection [J]. Remote Sensing, 2017, 9(8): Article No.860. 10.3390/rs9080860 |
8 | JIAO J, ZHANG Y, SUN H, et al. A densely connected end-to-end neural network for multiscale and multiscene SAR ship detection [J]. IEEE Access, 2018, 6: 20881-20892. 10.1109/access.2018.2825376 |
9 | ZHANG T W, ZHANG X L. High-speed ship detection in SAR images based on a grid convolutional neural network [J]. Remote Sensing, 2019, 11(10): Article No.1206. 10.3390/rs11101206 |
10 | CUI Z Y, LI Q, CAO Z J, 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. 10.1109/tgrs.2019.2923988 |
11 | ZHAO Y, ZHAO L J, LI C Y, et al. Pyramid attention dilated network for aircraft detection in SAR images [J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(4): 662-666. 10.1109/lgrs.2020.2981255 |
12 | 袁国文,张彩霞,杨阳,等.复杂场景下深度表示的SAR船舶目标检测算法[J].计算机工程与应用,2022,58(2):289-294. 10.3778/j.issn.1002-8331.2008-0117 |
YUAN G W, ZHANG C X, YANG Y, et al. SAR target detection algorithm for depth representation in complex scenes [J]. Computer Engineering and Applications, 2022, 58(2): 289-294. 10.3778/j.issn.1002-8331.2008-0117 | |
13 | PANG J M, CHEN K, SHI J P, et al. Libra R-CNN: towards balanced learning for object detection [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 821-830. 10.1109/cvpr.2019.00091 |
14 | GUO H Y, YANG X, WANG N N, et al. A CenterNet++ model for ship detection in SAR images [J]. Pattern Recognition, 2021, 112: Article No.107787. 10.1016/j.patcog.2020.107787 |
15 | ZHOU X Y, WANG D Q, KRÄHENBÜHL P. Objects as points [EB/OL]. [2021-03-03]. . |
16 | SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1-9. 10.1109/cvpr.2015.7298594 |
17 | BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS —improving object detection with one line of code [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 5562-5570. 10.1109/iccv.2017.593 |
18 | XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5987-5995. 10.1109/cvpr.2017.634 |
19 | ZHU X Z, CHENG D Z, ZHANG Z, et al. An empirical study of spatial attention mechanisms in deep networks [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 6687-6696. 10.1109/iccv.2019.00679 |
20 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 2017 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010. 10.1016/s0262-4079(17)32358-8 |
21 | WEI S J, ZENG X F, QU Q Z, et al. HRSID: a high-resolution SAR images dataset for ship detection and instance segmentation [J]. IEEE Access, 2020, 8: 120234-120254. 10.1109/access.2020.3005861 |
22 | LI J W, QU C W, SHAO J Q. Ship detection in SAR images based on an improved faster R-CNN [C]// Proceedings of the 2017 SAR in Big Data Era: Models, Methods and Applications. Piscataway: IEEE, 2017: 1-6. 10.1109/bigsardata.2017.8124934 |
23 | REDMON J, FARHADI A. YOLOv3: an incremental improvement [EB/OL] [2021-03-03]. . |
24 | LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multiBox detector [C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9905. Cham: Springer, 2016: 21-37. |
[1] | 赵志强, 马培红, 黑新宏. 基于双重注意力机制的人群计数方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2886-2892. |
[2] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[3] | 李力铤, 华蓓, 贺若舟, 徐况. 基于解耦注意力机制的多变量时序预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2732-2738. |
[4] | 薛凯鹏, 徐涛, 廖春节. 融合自监督和多层交叉注意力的多模态情感分析网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2387-2392. |
[5] | 汪雨晴, 朱广丽, 段文杰, 李书羽, 周若彤. 基于交互注意力机制的心理咨询文本情感分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2393-2399. |
[6] | 高鹏淇, 黄鹤鸣, 樊永红. 融合坐标与多头注意力机制的交互语音情感识别[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2400-2406. |
[7] | 李钟华, 白云起, 王雪津, 黄雷雷, 林初俊, 廖诗宇. 基于图像增强的低照度人脸检测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2588-2594. |
[8] | 莫尚斌, 王文君, 董凌, 高盛祥, 余正涛. 基于多路信息聚合协同解码的单通道语音增强[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2611-2617. |
[9] | 熊武, 曹从军, 宋雪芳, 邵云龙, 王旭升. 基于多尺度混合域注意力机制的笔迹鉴别方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2225-2232. |
[10] | 李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072. |
[11] | 毛典辉, 李学博, 刘峻岭, 张登辉, 颜文婧. 基于并行异构图和序列注意力机制的中文实体关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2018-2025. |
[12] | 刘丽, 侯海金, 王安红, 张涛. 基于多尺度注意力的生成式信息隐藏算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2102-2109. |
[13] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[14] | 李大海, 王忠华, 王振东. 结合空间域和频域信息的双分支低光照图像增强网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2175-2182. |
[15] | 魏文亮, 王阳萍, 岳彪, 王安政, 张哲. 基于光照权重分配和注意力的红外与可见光图像融合深度学习模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2183-2191. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||