Show simple item record

dc.contributor.advisor曹刘娟
dc.contributor.author罗峰
dc.date.accessioned2018-12-05T01:48:15Z
dc.date.available2018-12-05T01:48:15Z
dc.date.issued2018-01-02
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/170655
dc.description.abstract遥感成像技术的迅猛发展催生了大量的遥感图像的产生。以车辆检测为代表的遥感图像目标检测在公共安全、智能交通、城市规划等领域具有研究价值。大规模卫星图像中的标注信息不足、表观特征不明显、噪声干扰等因素严重影响了对于当前计算机视觉主流车辆检测算法的直接应用,导致了直接训练鲁棒的卫星图像车辆检测器面临监督信息不足的挑战。本文主要研究基于高分辨率航摄图像进行高效自动的车辆目标检测,并将分类器迁移应用于低分辨率的卫星图像实现车辆检测。研究的主要内容包括以下三个方面: (1)针对卫星图像表观特征不明显的问题,本文引入基于随机森林的超分辨率重建算法对卫星图像进行特征增强、表观重构。对于背景复杂的卫星图像,基...
dc.description.abstractA large number of remote sensing images have been produced with the rapid development of remote sensing imaging technology. Object detection in remote sensing images such as vehicle detection has been an important research topic in many applications, such as public security, intelligent transportation and urban planning. The lack of annotation information, apparent features, noise interference and...
dc.language.isozh_CN
dc.relation.urihttps://catalog.xmu.edu.cn/opac/openlink.php?strText=58812&doctype=ALL&strSearchType=callno
dc.source.urihttps://etd.xmu.edu.cn/detail.asp?serial=60665
dc.subject遥感图像
dc.subject车辆检测
dc.subject超分辨率重建
dc.subject迁移学习
dc.subject深度学习
dc.subjectRemote Sensing
dc.subjectVehicle Detection
dc.subjectSuper-resolution Representation
dc.subjectTransfer Learning
dc.subjectDeep Learning
dc.title基于超分辨率迁移学习的遥感图像车辆检测
dc.title.alternativeVehicle Detection in Remote Sensing Imagery Based on Super-Resolution Transfer Learning
dc.typethesis
dc.date.replied2017-05-20
dc.description.note学位:工程硕士
dc.description.note院系专业:信息科学与技术学院_工程硕士(计算机技术)
dc.description.note学号:23020141153187


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record