检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]中国科学院自动化研究所模式识别国家重点实验室,北京100190
出 处:《中国科学:信息科学》2015年第9期1141-1156,共16页Scientia Sinica(Informationis)
基 金:国家自然科学基金(批准号:2013AA122301;61333015;61273280)资助
摘 要:在基于图像的复杂城市场景的重建中,由于弱纹理区域及曲面结构的存在,传统自动重建算法通常仅能获得不完整或者过于简单化的场景结构,而传统的交互式重建算法则因过于复杂的交互方式难以被用户操作.为了解决这些问题,本文提出一种快速交互式三维场景重建算法.基于稀疏的初始重建的空间点,本文算法可根据用户提供的交互区域及场景结构先验快速重建出比较准确的几何模型(如平面、柱面等),而交互区域的确定完全采用2D交互的方式完成,不但便于用户操作,而且便于移植于平板、手机等移动终端.标准数据集与自行拍摄数据集的实验表明,本文算法能有效克服传统重建算法过于依赖分段平面假设的缺点,可以快速重建出包括球面、柱面等结构在内的完整的场景结构.In 3D modeling of urban environments based on multiple images, traditional automated stereo methods usually generate incomplete or simplistic scene structures, owing to interference factors such as poorly textured regions and highly slanted surfaces. Furthermore, because of their complex interactive processes, interactive 3D modeling methods are difficult for general users to master. In order to address these problems, this paper proposes a rapid interactive 3D modeling method. Based on initial sparse spatial points and prior knowledge of the scene structure, our method can effectively and efficiently reconstruct accurate geometric models (e.g. planes, cylinders) for interactive regions provided by users in a complete 2D manner. Moreover, all interactions are performed in a single image, which facilitates operation by general users and eases the transition to mobile devices such as smartphones and tablet computers. Experiments on standard data sets and our own data sets show that our method can model complete scene structures more accurately than piecewise planar models commonly used in traditional stereo methods.
关 键 词:用户交互 深度图 平面拟合 能量最小化 平面扫描
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38