VHRShips
索引说明：本页内容为本站爬虫自动索引的第三方平台公开页面元信息，本平台不存储、不缓存任何资源文件。点击下方按钮将跳转至第三方网站平台访问，访问第三方资源链接需要 VIP 权限。
资源简介
This study focuses on all stages of ship classification in the optical satellite images. The proposed “Hierarchical Design (HieD)” approach, which is based on deep learning techniques, performs Detection, Localization, Recognition and Identification (DLRI) of the ships in the optical satellite images. HieD is an end-to-end approach which allows the optimization of each stage of the DLRI independently. A unique and rich ship dataset (High Resolution Ships, HRShips), which is formed by the Google Earth Pro software, is used in this study. While Xception network is used in detection, recognition and identification stages; YOLOv4 is preferred for the localization of the ships.
- 资源类型
- 软件
- 第三方域名
- github.com
- 索引时间
- 2026-08-04 01:40
开通 VIP 后访问第三方资源
访问第三方资源链接需要 VIP 权限。注册与搜索永久免费，VIP 仅用于访问第三方链接。