首页 > 论文 > 红外与毫米波学报 > 38卷 > 3期(pp:290-295)

CCNet:面向多光谱图像的高速船只检测级联卷积神经网络

cnCCNet: A high-speed cascaded convolutional neural network for ship detection with multispectral images

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对实现遥感图像中船只目标的快速检测, 提出了一个采用多光谱图像、基于级联的卷积神经网络(CNN)船只检测方法CCNet.该方法所采用两级级联的CNN依次实现感兴趣区域(ROI)的快速搜索、基于感兴趣区域的船只目标定位和分割.同时, 采用含有更多细节信息的多光谱图像作为CCNet的输入, 能够提升网络提取特征鲁棒性, 从而使得检测更加精确.基于SPOT 6卫星多光谱图像的实验表明, 与当前主流的深度学习船只检测方法相比, 该方法能够在实现高检测精准度的基础上将检测速度提高5倍以上.

Abstract

The CCNet employs two cascaded convolutional neural networks (CNN) for extracting regions of interest (ROIs), locating and segmenting ship objects sequentially. Benefit from the abundant details of the multispectral image, CCNet can extract more robust feature for achieving more accurate detection. The efficiency of CCNet has been validated by the experiments on the SPOT 6 satellite multispectral images. Compared with the state-of-the-art deep-learning-based ship detection algorithms, the proposed ship detection algorithm accelerates the processing by more than 5 times with a higher detection accuracy.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751

DOI:10.11972/j.issn.1001-9014.2019.03.006

基金项目:This work is supported by The National Key Research and Development Program of China (Grant No. 2016YFA0202200), National Natural Science Foundation of China (Grant Nos. 61434004, 61234003), National Natural Science Foundation for the Youth of China (61504141, 61704167), National Key R&D Program of Beijing (Z181100008918009) and Youth Innovation Promotion Association Program, Chinese Academy of Sciences (No. 2016107)

收稿日期:2018-12-01

修改稿日期:2019-02-11

网络出版日期:--

作者单位    点击查看

张忠星:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
李鸿龙:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
张广乾:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
朱文平:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
刘力源:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
刘 剑:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049
吴南健:中国科学院半导体研究所 超晶格国家重点实验室, 北京 100083中国科学院脑科学与智能技术卓越创新中心, 北京 100083中国科学院大学 材料与光电研究中心, 北京 100049

联系人作者:张忠星(zhangzhongxing@semi.ac.cn)

备注:ZHANG Zhong-Xing (1990-), male, Liaocheng, doctor. Research area involves Image processing and digital integrated circuits.

【1】Jubelin G, Khenchaf A. Multiscale algorithm for ship detection in mid, high and very high resolution optical imagery[C]//Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International. IEEE, 2014: 2289-2292.

【2】L Liu G, Zhang Y, Zheng X, et al. A new method on inshore ship detection in high-resolution satellite images using shape and context information[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(3): 617-621.

【3】Bi F, Zhu B, Gao L, et al. A visual search inspired computational model for ship detection in optical satellite images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4): 749-753.

【4】Zhang R, Yao J, Zhang K, et al. S-CNN-BASED ship detection from high-resolution remote sensing images[J]. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 2016, 41.

【5】He H, Lin Y, Chen F, et al. Inshore ship detection in remote sensing images via weighted pose voting[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(6): 3091-3107.

【6】Shi Z, Yu X, Jiang Z, et al. Ship detection in high-resolution optical imagery based on anomaly detector and local shape feature[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(8): 4511-4523.

【7】Zhu C, Zhou H, Wang R, et al. A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features[J]. IEEE Transactions on geoscience and remote sensing, 2010, 48(9): 3446-3456.

【8】Liu Z, Hu J, Weng L, et al. Rotated region based CNN for ship detection[C]//Image Processing (ICIP), 2017 IEEE International Conference on. IEEE, 2017: 900-904.

【9】Yao Y, Jiang Z, Zhang H, et al. Ship detection in optical remote sensing images based on deep convolutional neural networks[J]. Journal of Applied Remote Sensing, 2017, 11(4): 042611.

【10】Zou Z, Shi Z. Ship detection in spaceborne optical image with SVD networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10): 5832-5845.

【11】Zhou M, Jing M, Liu D, et al. Multi-resolution Networks for Ship Detection in Infrared Remote Sensing Images[J]. Infrared Physics & Technology, 2018.

【12】Brauchle J, Bayer S, Berger R. Automatic ship detection on multispectral and thermal infrared aerial images using MACS-Mar remote sensing platform[C]//Pacific-Rim Symposium on Image and Video Technology. Springer, Cham, 2017: 382-395.

【13】Lin T Y, Maire M, Belongie S, et al. Microsoft coco: Common objects in context[C]//European conference on computer vision. Springer, Cham, 2014: 740-755.

【14】He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Computer Vision (ICCV), 2017 IEEE International Conference on. IEEE, 2017: 2980-2988.

【15】Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//European conference on computer vision. Springer, Cham, 2016: 21-37.

【16】Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

【17】Lin T Y, Dollár P, Girshick R B, et al. Feature Pyramid Networks for Object Detection[C]//CVPR. 2017, 1(2): 4.

【18】Airbus dataset [OL]. 2018. https://www.kaggle.com/c/airbus-ship-detection/data.

【19】Zhang Z, Guo W, Zhu S, et al. Toward Arbitrary-Oriented Ship Detection With Rotated Region Proposal and Discrimination Networks[J]. IEEE Geoscience and Remote Sensing Letters, 2018, (99): 1-5.

引用该论文

ZHANG Zhong-Xing,LI Hong-Long,ZHANG Guang-Qian,ZHU Wen-Ping,LIU Li-Yuan,LIU Jian,WU Nan-Jian. cnCCNet: A high-speed cascaded convolutional neural network for ship detection with multispectral images[J]. Journal of Infrared and Millimeter Waves, 2019, 38(3): 290-295

张忠星,李鸿龙,张广乾,朱文平,刘力源,刘 剑,吴南健. CCNet:面向多光谱图像的高速船只检测级联卷积神经网络[J]. 红外与毫米波学报, 2019, 38(3): 290-295

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF