CASIA OpenIR  > 空天信息研究中心
Rotated Region Based CNN for Ship Detection
Liu, Zikun1,2; Hu, Jingao1,2; Weng, Lubin1; Yang Yiping1
2017-10
会议名称2017 IEEE International Conference on Image Processing
会议日期17-20 September 2017
会议地点China National Convention Center in Beijing, China
摘要

The state-of-the-art object detection networks for natural images have recently demonstrated impressive performances. However the complexity of ship detection in high resolution satellite images exposes the limited capacity of these networks for strip-like rotated assembled object detection which are common in remote sensing images. In this paper, we embrace this observation and introduce the rotated region based CNN (RR-CNN), which can learn and accurately extract features of rotated regions and locate rotated objects precisely. RR-CNN has three important new components including a rotated region of interest (RRoI) pooling layer, a rotated bounding box regression model and a multi-task method for non-maximal suppression (NMS) between different classes. Experimental results on the public ship dataset HRSC2016 confirm that RR-CNN outperforms baselines by a large margin.

关键词Rotated Region Convolutional Neural Network Ship Detection
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14548
专题空天信息研究中心
通讯作者Weng, Lubin
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Liu, Zikun,Hu, Jingao,Weng, Lubin,et al. Rotated Region Based CNN for Ship Detection[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
rrcnn_final_v1.pdf(2750KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Liu, Zikun]的文章
[Hu, Jingao]的文章
[Weng, Lubin]的文章
百度学术
百度学术中相似的文章
[Liu, Zikun]的文章
[Hu, Jingao]的文章
[Weng, Lubin]的文章
必应学术
必应学术中相似的文章
[Liu, Zikun]的文章
[Hu, Jingao]的文章
[Weng, Lubin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: rrcnn_final_v1.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。