全局相机姿态优化下的快速表面重建

doi:10.13229/j.cnki.jdxbgxb20170146

摘要/Abstract

摘要： 针对传统三维重建算法存在的漂移问题,提出了一种端到端的在线大规模三维场景重建算法。首先,使用一种在线估计策略来鲁棒地确定相机的旋转姿态,同时构建层次优化框架用于融合深度数据的输入。然后,依据相机的全局估计姿态对每一帧的信息进行优化,解除了算法对目标跟踪时间的限制,完成了对帧间关系对象的实时跟踪。试验结果表明:本文算法的平均重建时间为399 ms,平均估计迭代最低点(ICP)次数为20,完成每帧变换的时间为100 ms;系统对大规模场景的重建具有鲁棒性,且实时性较好,是一种具有对应关系稀疏特性、结构信息稠密特性和相机光照一致特性的实时三维重建算法。

关键词: 计算机应用, 机器视觉, 三维重建, 实时体素融合, 姿态估计

Abstract: An end-to-end online large-scale 3D scene reconstruction method is proposed. This method uses robustness to estimate the rotation attitude of the camera and constructs a hierarchical optimization framework for the fusion of depth data input. Then, the information of each frame is optimized according to the global pose of the camera, and the algorithm limits the target tracking time and completes real-time tracking of the frame. Experimental results show that the average time to reconstruct the algorithm reaches 399 ms and the average number of estimated Iterative Closest Point (ICP) times is 20, which needs 100 ms to complete each frame transformation. The system is robust to the reconstruction of large-scale scenes and has better real-time performance. This method is a real-time three-dimensional reconstruction system with corresponding sparseness, dense structure information and camera illustration uniformity.

Key words: computer application, machine vision, 3D reconstruction, online volume fusion, pose estimation

中图分类号:

TP391

林金花, 王延杰, 王璐, 姚禹. 全局相机姿态优化下的快速表面重建[J]. 吉林大学学报(工学版), 2018, 48(3): 909-918.

LIN Jin-hua, WANG Yan-jie, WANG Lu, YAO Yu. Real-time surface reconstruction based global camera pose optimization[J]. 吉林大学学报(工学版), 2018, 48(3): 909-918.

参考文献

[1] Weise T, Wismer T, Leibe B, et al.In-hand scanning with online loop closure[C]∥IEEE International Conference on Computer Vision Workshops,Kyoto,Japan,2009:1630-1637.
[2] Henry P,Krainin M,Herbst E,et al.RGB-D mapping: using depth cameras for dense 3D modeling of indoor environments[J]. International Journal of Robotics Research,2012,31(5):647-663.
[3] Keller M, Lefloch D, Lambers M, et al.Real-time 3D reconstruction in dynamic scenes using point-based fusion[C]∥International Conference on 3D Vision-3DV,Tokyo,Japan,2013,8768(2):1-8.
[4] Whelan T,Leutenegger S,Salas-moreno R F,et al. Elastic fusion: dense SLAM without a pose graph[J/OL].[2017-02-10]. http://www.doc.ic.ac.uk/~bglocker/pdfs/whelan2015rss.pdf.
[5] Merrell P,Akbarzadeh A,Wang L,et al.Real-time visibility based fusion of depth maps[C]∥IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil,2007:1-8.
[6] Meilland M, Comport A.On unifying key-frame and voxel-based dense visual SLAM at large scales[C]∥International Conference on Intelligent Robots & Systems, Tokyo, Japan,2013:3677-3683.
[7] Gallup D, Pollefeys M, Frahm J M.3D reconstruction using an n-layer heightmap[J]. Pattern Recognition,2010,6376:1-10.
[8] Wurm K M,Hornung A,Bennewitz M,et al. Octomap:a probabilistic, flexible, and compact 3D map representation for robotic systems[J/OL].[2017-02-13]. http://ais.informatik.uni-freiburg.de/publications/papers/wurm10octomap.pdf.
[9] Curless B,Levoy M.A volumetric method for building complex models from range images[C]∥Conference on Computer Graphics and Interactive Techniques,New Orleans,LA,USA,1996:303-312.
[10] Kornuta T, Laszkowski M.Perception subsystem for object recognition and pose estimation in RGB-D images[J]. Automation, Springer International Publishing,2016,44(10):995-1003.
[11] Steinbruecker F,Sturm J,Cremers D.Volumetric 3D mapping in real-time on a CPU[C]∥IEEE International Conference on Robotics and Automation,Stockholm,Sweden,2014:2021-2028.
[12] Zollhöfer M,Thies J,Colaianni M,et al.Interactive model-based reconstruction of the human head using an RGB-D sensor[J]. Computer Animation & Virtual Worlds,2014,25(3-4):213-222.
[13] Zhou Q Y. Koltun V.Color map optimization for 3D reconstruction with consumer depth cameras[J]. ACM Transactions on Graphics,2014,33(4):1-10.
[14] Choi S,Zhou Q Y,Koltun V.Robust reconstruction of indoor scenes[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Boston,MA,USA,2015:5556-5565.
[15] Wikowski A,Kornuta T,Stefańczyk M,et al.Efficient generation of 3D surfel maps using RGB-D sensors[J]. International Journal of Applied Mathematics & Computer Science,2016,26(1):99-122.
[16] Newcombe R A, Izadi S, Hilliges O,et al.KinectFusion: real-time dense surface mapping and tracking[C]∥Conference on Computer Graphics & Interactive Techniques,New Orleans,LA,USA,1996:303-312.
[17] Whelan T,Johannsson H,Kaess M,et al.Robust real-time visual odometry for dense RGB-D mapping[C]∥IEEE International Conference on Robotics and Automation, Karlsruhe,Germany,2013:13851317.
[18] Lin J H, Wang Y J, Sun H H.A Feature-adaptive subdivision method for real-time 3D reconstruction of repeated topology surfaces[J]. 3D Research,2017,8(1):1-16.
[19] 王新华,欧阳继红,张广,等. 微扫描红外成像超分辨重建[J]. 吉林大学学报:工学版,2017,47(1):235-241.
Wang Xin-hua,Ouyang Ji-hong,Zhang Guang, et al.Super-resolution reconstruction of infrared images based on micro-scanner[J]. Journal of Jilin University(Engineering and Technology Edition),2017,47(1):235-241.
[20] 刘迎,王朝阳,高楠,等. 特征提取的点云自适应精简[J]. 光学精密工程, 2017,25(1):245-254.
Liu Ying,Wang Chao-yang,Gao Nan, et al.Point cloud adaptive simplification of feature extraction[J]. Optics and Precision Engineering,2017,25(1):245-254.
[21] 张雷,王延杰,孙宏海,等. 采用核相关滤波器的自适应尺度目标跟踪[J]. 光学精密工程,2016,24(2):448-459.
Zhang Lei,Wang Yan-jie,Sun Hong-hai,et al.Adaptive scale object tracking with kernelized correlation filters[J]. Optics and Precision Engineering,2016,24(2):448-459.
[22] 王慧利,朱明,蔺春波,等. 光学遥感图像中复杂海背景下的舰船检测[J]. 光学精密工程,2018,26(3):723-732.
Wang Hui-li,Zhu Ming,Lin Chun-bo,et al.Ship detection of complex sea background in optical remote sensing images[J]. Optics and Precision Engineering, 2018,26(3):723-732.
[23] 李湘眷,王彩玲,李宇,等.窗口融合特征对比度的光学遥感目标检测[J].光学精密工程,2016,24(8):2067-2077.
Li Xiang-juan,Wang Cai-ling,Li Yu,et al.Optical remote Sensing object detection based on fused feature Contrast of subwindows[J]. Optics and Precision Engineering,2016,24(8): 2067-2077.
[24] 徐伟,陈彦彤,朴永杰,等.基于吉林一号遥感图像的星载目标快速识别系统[J].光学精密工程,2017,25(1):255-262.
Xu Wei,Chen Yan-tong,Piao Yong-jie,et al.Target fast matching recognition of on-board system based on Jilin-1 satellite image[J]. Optics and Precision Engineering,2017,25(1):255-262.

相关文章 15

[1]	刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2]	王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3]	金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4]	赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5]	刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6]	欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[7]	刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[8]	桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[9]	刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[10]	车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12]	黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13]	傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14]	曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15]	侯永宏, 王利伟, 邢家明. 基于HTTP的动态自适应流媒体传输算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed