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]重庆邮电大学计算机科学与技术学院网络智能研究所,重庆400065
出 处:《计算机工程与设计》2015年第1期227-231,共5页Computer Engineering and Design
基 金:"核高基"重大专项基金项目(2009ZX01038-002-002-2);科技部"原创动漫软件开发技术人才"计划扶持基金项目(2009-593)
摘 要:为获得增强现实系统更好的真实感,针对已有背景裁剪算法只适用于背景固定且单目摄像头深度恢复准确度不够的情况,提出一种动态变换背景帧的虚实遮挡处理方法。通过动态地变换背景帧检测运动物体,求出前景物体的轮廓;遍历图像像素来确定虚实物体之间的遮挡关系,利用模板缓存技术进行遮挡部位剔除工作。实验结果表明,该方法实现简单、支持摄像头移动、遮挡判定准确、计算量小,且能很好地处理刚性与非刚性物体。Since the existing background clipping algorithms are only applied to the fixed background and the accuracy of depth recovery using monocular cameras is not enough. To get a better sense of reality in augmented reality systems, a virtual-reality occlusion processing method was proposed based on the dynamic transformation background frame. The moving objects were de- tected by transforming the background frame dynamically, and the contour of foreground objects was gotten. Then the image pixels were traversed to determine the occlusion relation between virtual-reality objects, and the template caching technology was also used to remove the blocked parts. Experimental results demonstrate that the proposed method can be simply implemented which supports moving cameras and can accurately judge the occlusion with less calculation, moreover it is good at dealing both rigid and non-rigid objects.
关 键 词:增强现实 虚实遮挡 轮廓提取 模板测试 遮挡判定
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:216.73.216.145