特征图强化网络：利用特征图强化船舶检测模型训练的网络结构
FMRNet： A network structure for enhanced ship detection model training using feature maps
- 2023年27卷第12期 页码：2697-2705
纸质出版日期： 2023-12-07
DOI： 10.11834/jrs.20221656
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
随着人工智能技术的进一步发展，深度学习方法在船舶检测领域发挥着重要作用。然而，深度学习算法出现的虚警和漏检，对船舶检测领域技术的应用存在一定的阻碍。虽然经典的深度学习方法能够有效处理单一背景的海面，但是当面对复杂背景之下的数据时，经典模型很容易得出岸上的虚警。并且在常规训练中，模型常常对一些显著特征过于关注，出现特征过拟合现象，当这些显著特征发生改变时极易出现漏检。在模型对输入进行前向传播的过程中，模型中不同网络层会对输入生成对应的映射，也就是特征图。充分利用特征图的语义信息和空间信息是一种有效减少虚警和漏检的方法。与传统模型相比，我们提出的特征图强化网络可以充分利用特征图生成自适应特征图掩码与水陆分割掩码，避免模型的特征过拟合与削弱复杂背景造成的影响，最终达到减少虚警与漏检的目的。在现有公共数据集上与算法模型的对比实验结果表明，本文所提出的方法的性能更为出色，超过了其他SOTA算法。
Abstract
With the ongoing development of artificial intelligence technology
deep learning methods have become increasingly important role in the field of ship detection. However
the false alarms and missed detections that appear in deep learning algorithms hinder the application of technology in the field of ship detection. Although the classical deep learning methods can effectively deal with a single-background sea surface
the classical models can easily yield false alarms on shore when faced with data under complex backgrounds. In custom training
the model often tends to overly emphasize some salient features
which leads to feature overfitting. Detection can easily be missed when these salient features change. In the process of forward propagation of the model to the input
different network layers in the model generate corresponding mappings or feature maps from the input. Fully utilizing the semantic and spatial information of the feature maps is an effective way to reduce false alarms and missed detections. Compared with the traditional model
our proposed Feature Map Reinforcement Network (FMRNnet) can fully utilize feature maps to generate adaptive feature map masks and water–land segmentation masks. This method ultimately reduces false alarms and missed detections by avoiding feature overfitting of the model and weakening the effects caused by complex backgrounds. In FMRNnet
we design the Self Feature-map Mask Module (SFMM)
which can selectively utilize the feature map through the attention mechanism for generating an adaptive mask. The mask prevents the model from focusing on a single feature point
which prevents feature overfitting. We also propose a Feature-map Sea-Land Segmentation Module (FSSM) that is parallel to SFMM. It reduces the false alarms of ship targets appearing in the land area by introducing the fusion between the water-land segmentation mask and the feature map. The experimental results
when compared with SOTA algorithms on publicly available datasets
show that the performance of the proposed method in this study is excellent and outperforms that of other SOTA algorithms. After FMRNet is added
the 10-fold average mAP value of the detection algorithm ROI trans largely improves. This enhancement increases the mean value of baseline mAP from 86.1% to 90.8%
which surpasses that of other SOTA algorithms. Benefiting from the adaptive mask
the mAP value of the model including the SFMM module is 90.4%
which achieves a 4.2% improvement over the baseline. Owing to the priori knowledge learned from the water-land distribution
FSSM improves the precision and recall of the model
which results in a MAP value of 86.4%. For the task of ship detection
we propose a novel backbone network
that is
FMRNet based on Resnet. Our proposed SFMM module enables the model to discern the target from multiple features for avoiding the overfitting of salient features. We design the FSSM module to reduce the false alarms caused by complex backgrounds. Suppressing the non-water surface area reduces the confidence level of targets appearing in non-water surface. FSSM achieves the purpose of removing unreasonable false alarms while improving the accuracy of the model.
关键词
遥感成像人工智能船舶目标检测神经网络特征图网络强化旋转目标检测抑制过拟合
Keywords
remote sensing imagingartificial intelligenceship detectionneural networksfeature mapsnetwork reinforcementrotational object detectionoverfitting suppression
references
Bi F K, Hou J Y, Chen L, Yang Z H and Wang Y P. 2019. Ship detection for optical remote sensing images based on visual attention enhanced network. Sensors, 19(10): 2271 [DOI: 10.3390/s19102271http://dx.doi.org/10.3390/s19102271]
Ding G D, Kha S, Tang Z M and Porikli F. 2017. Let features decide for themselves: feature mask network for person re-identification. arXiv: 1711.07155
Ding J, Xue N, Long Y, Xia G S and Lu Q K. 2018. Learning RoI transformer for detecting oriented objects in aerial images. arXiv: 1812.00155
Girshick R. 2015. Fast R-CNN//2015 IEEE International Conference on Computer Vision. Santiago: IEEE: 1440-1448 [DOI: 10.1109/ICCV.2015.169http://dx.doi.org/10.1109/ICCV.2015.169]
Goetz A F H, Rock B N and Rowan L C. 1983. Remote sensing for exploration; an overview. Economic Geology, 78(4): 573-590 [DOI: 10.2113/gsecongeo.78.4.573http://dx.doi.org/10.2113/gsecongeo.78.4.573]
Gu Z Y. 2010. Research on high performance computing platform of ocean environmental information processing//2010 International Conference on Optics, Photonics and Energy Engineering. Wuhan: IEEE: 298-300 [DOI: 10.1109/OPEE.2010.5508128http://dx.doi.org/10.1109/OPEE.2010.5508128]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]
Hu J, Shen L and Sun G. 2018. Squeeze-and-excitation networks//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE: 7132-7141 [DOI: 10.1109/CVPR.2018.00745http://dx.doi.org/10.1109/CVPR.2018.00745]
Lunetta R S, Congalton R C, Fenstermaker L K, Jensen J R, McGwire K C and Tinney L R. 1991. Remote sensing and geographic information system data integration: error sources and research issues. Photogrammetric Engineering and Remote Sensing, 57(6): 677-687
Nie X, Duan M Y, Ding H X, Hu B L and Wong E K. 2020. Attention mask R-CNN for ship detection and segmentation from remote sensing images. IEEE Access, 8: 9325-9334 [DOI: 10.1109/ACCESS.2020.2964540http://dx.doi.org/10.1109/ACCESS.2020.2964540]
Qian W, Yang X, Peng S L, Guo Y and Yan J C. 2019. Learning modulated loss for rotated object detection. arXiv: 1911.08299
Redmon J, Divvala S, Girshick R and Farhadi A. 2016. You only look once: unified, real-time object detection//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 779-788 [DOI: 10.1109/CVPR.2016.91http://dx.doi.org/10.1109/CVPR.2016.91]
Redmon J and Farhadi A. 2018. YOLOv3: an incremental improvement. arXiv: 1804.02767v1
Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Xu K Y, Hu W H and Chen R. 2006. A vessel targets detection method based on Canny algorithm. Infrared Technology, 28(6): 315-318
许开宇, 胡文骅, 陈仁. 2006. 一种基于Canny算子的船舶目标检测算法. 红外技术, 28(6): 315-318 [DOI: 10.3969/j.issn.1001-8891.2006.06.002http://dx.doi.org/10.3969/j.issn.1001-8891.2006.06.002]
Xu Y C, Fu M T, Wang Q M, Wang Y K, Chen K, Xia G S and Bai X. 2021. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(4): 1452-1459 [DOI: 10.1109/TPAMI.2020.2974745http://dx.doi.org/10.1109/TPAMI.2020.2974745]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
南京大学 地理与海洋科学学院
北京师范大学 地表过程与资源生态国家重点实验室
同济大学 测绘与地理信息学院
中国科学院东北地理与农业生态研究所
中国科学院空天信息创新研究院
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部