摘要
船只目标检测识别技术是现阶段遥感图像研究领域的一个重要发展方向。随着国产高分辨率卫星的快速发展,高分遥感卫星陆续发射,基于光学遥感图像的船只检测识别技术会逐步成为研究热门。主要介绍了近年来基于光学图片的船只检测识别技术发展、以及当前技术存在的问题。当前基于深度学习的船只目标检测识别技术取得了较好的检测效果,成为主流研究方向,但在光学遥感图像船只检测领域基于深度学习的方法有一些基本问题限制了检测效果,对这些问题进行了归纳总结,并对未来光学遥感图像船只检测技术的发展进行了展望。
At this stage, ship detection and recognition technology is an important development direction in the field of remote sensing image research. With the rapid development of domestic high-resolution satellites, high-resolution remote sensing satellites have been launched one after another, and ship detection and recognition technology based on optical remot e sensing images will gradually become a research hotspot. This article introduces the development of ship detection and recognition technology based on optical images in recent years, and the problems of current technology. The current deep learning-based ship target detection technology has achieved good detection results and has become the mainstream research direction. However, in the field of optical remote sensing image ship detection, deep learning-based methods have some basic problems which limit the detection effect. This article summarizes some of the problems that currently limit the deep learning-based optical remote sensing image ship detection technology, and looks forward to the future development of optical remote sensing image ship detection technology.
作者
陈昱文
熊建林
刘斌
刘颖
张永倩
CHEN Yuwen;XIONG Jianlin;LIU Bin;LIU Ying;ZHANG Yongqian(Beijing Research Institute of Telemetry,Beijing 100076,China)
出处
《遥测遥控》
2021年第3期57-66,共10页
Journal of Telemetry,Tracking and Command
关键词
光学遥感图像
船只目标识别
深度学习
Optical remote sensing image
Ship detection technology
Deep learning
