基于三维视觉的室内设计虚拟现实方法研究Research on virtual reality method of indoor design based on 3D vision
师春艳
摘要(Abstract)：
针对传统基于辐射度算法的室内场景三维虚拟现实方法存在耗时高、建模效果差的弊端,研究基于三维视觉的室内设计虚拟现实方法,采用主动式、全方位立体视觉传感器采集室内场景的三维点云数据,基于点云数据进行室内场景内的物体几何关系以及摆放位置分布,完成室内三维场景的自主合成,对物体摆放位置分布实施训练,通过三维场景点云数据集获取相同类型支撑物中物体产生的位置,对数据实施归一化操作,采用高斯混合模型拟合这些数据,训练出三维室内场景中物件在支撑面中的位置分布模型。采用基于深度信息场景重构方法实现室内三维场景的虚拟实现。实验结果说明,所提方法重构的室内场景直观、视觉效果好,并且具有较高的重构效率和精度。
关键词(KeyWords)： 三维视觉;室内设计;虚拟现实方法;场景;点云数据;高斯混合模型
基金项目(Foundation):
作者(Author): 师春艳
DOI: 10.16652/j.issn.1004-373x.2018.05.018
参考文献(References)：
- [1]王云舒,刘建业,曾庆化,等.结构光辅助的惯性/视觉室内导航三维环境重构方法[J].中国惯性技术学报,2016,24(1):51-58.WANG Yunshu,LIU Jianye,ZENG Qinghua,et al.3D environment restructure method with structured light for indoor vision/inertial navigation[J].Chinese journal of inertial technology,2016,24(1):51-58.
- [2]吴乃亮,闫飞,卜春光.基于视觉里程计的移动机器人三维场景重构[J].华中科技大学学报(自然科学版),2015,43(z1):337-340.WU Nailiang,YAN Fei,BU Chunguang.Mobile robot 3D environment reconstruction based on visual odometer[J].Journal of Huazhong University of Science and Technology(natural science edition),2015,43(S1):337-340.
- [3]李秀智,杨爱林,秦宝岭,等.基于光流反馈的单目视觉三维重建[J].光学学报,2015,35(5):228-236.LI Xiuzhi,YANG Ailin,QIN Baoling,et al.Monocular camera three dimensional reconstruction based on optical flow feedback[J].Acta optica sinica,2015,35(5):228-236.
- [4]高如新,王俊孟.双目立体视觉求取三维坐标的方法研究[J].计算机仿真,2014,31(10):296-300.GAO Ruxin,WANG Junmeng.Study on some methods of 3D coordinate calculation of binocular vision[J].Computer simulation,2014,31(10):296-300.
- [5]廖明,周良辰,闾国年,等.基于Open GL驱动的三维场景重构[J].计算机应用研究,2015,32(4):1276-1280.LIAO Ming,ZHOU Liangchen,LüGuonian,et al.3D scene reconstruction based on Open GL[J].Computer application research,2015,32(4):1276-1280.
- [6]李辉.基于虚拟双目视觉的玉米叶片三维重建方法[J].科技通报,2016,32(5):96-101.LI Hui.3D reconstruction of maize leaves based on virtual visual technology[J].Bulletin of science and technology,2016,32(5):96-101.
- [7]朱笑笑,曹其新,杨扬,等.一种改进的Kinect Fusion三维重构算法[J].机器人,2014,36(2):129-136.ZHU Xiaoxiao,CAO Qixin,YANG Yang,et al.An improved Kinect Fusion 3D reconstruction algorithm[J].Robot,2014,36(2):129-136.
- [8]董峰,王继州.三维虚拟海洋图像仿真在舰艇视觉中的应用[J].舰船科学技术,2015,37(9):176-180.DONG Feng,WANG Jizhou.Application of 3D virtual ocean image simulation in naval ships vision[J].Ship science and technology,2015,37(9):176-180.
- [9]肖建良,张程,李阳.基于Unity3D的室内漫游系统[J].电子设计工程,2016,24(19):54-56.XIAO Jianliang,ZHANG Cheng,LI Yang.The indoor roaming system based on Unity3D[J].Electronic design engineering,2016,24(19):54-56.
- [10]韦争亮,古耀达,黄志斌,等.双目立体视觉中特征点三维坐标重构校准研究[J].计量学报,2014,35(2):102-107.WEI Zhengliang,GU Yaoda,HUANG Zhibin,et al.Research on calibration of three dimensional coordinate reconstruction of feature points in binocular stereo vision[J].Journal of metrology,2014,35(2):102-107.