View Planning in Line Laser Measurement for Self-occlusion Objects

Abstract

Abstract: Focusing on measurement and 3D reconstruction of unknown self-occlusion objects, a new view planning method was proposed combining with fast reconstruction using Kinect Fusion technology and line laser precision measurement. Firstly, the surface depth information model of unknown self-occlusion object was obtained quickly with Kinect Fusion technology, and then the cross section shape of the object was analyzed. According to measuring visibility judgment of the five degrees-of-freedom line laser measurement system about left-right direction and upper-lower direction, the global view planning was carried out based on the best measurement range,the self-occlusion and point cloud holes were eliminated accurately and quickly. Finally, the 3D object surface reconstruction with high precision was obtained.The reconstruction experiments of self-occlusion object show that the method is feasibility and effective.

Key words: machine vision, view planning； self-occlusion； Kinect Fusion； line laser

摘要： 针对未知自遮挡物体的测量和三维重建问题，提出利用Kinect Fusion技术快速重建和线激光精密测量相结合的视点规划新方法。应用Kinect Fusion技术快速获取未知自遮挡物体表面的深度信息模型，研究提出轮廓表面的截面特征信息提取方法，在此基础上分析轮廓表面的截面形状特征，根据五自由度线激光测量系统的左右方向和上下方向测量可视性判断，在最佳测量范围内进行线激光测量全局视点规划，准确、快速消除自遮挡和点云孔洞，最后获得重建精度高的三维物体表面。经过自遮挡物体重建实验，验证了所提方法的可行性及有效性。

关键词: 机器视觉, 视点规划, 自遮挡, Kinect Fusion, 线激光

CLC Number:

TP391

Chen Tianfan, Gao Chenghui, He Bingwei. View Planning in Line Laser Measurement for Self-occlusion Objects[J]. China Mechanical Engineering.

陈天凡, 高诚辉, 何炳蔚. 自遮挡物体线激光测量视点规划[J]. 中国机械工程.

References

[1]Chalmoviansky P, Juttler B. Filling Holes in Point Clouds [C]// Mathematics of Surfaces: 10th IMA International Conference. Berlin: Springer,2003,2768: 196-212.

[2]Wang L C, Hung Y C. Hole Filling of Triangular Mesh Segments Using Systematic Grey Prediction [J]. Computer-Aided Design, 2012, 44(12): 1182-1189.

[3]Attenm M.A Lightweight Approach to Repairing Digitized Polygon Meshes [J].Visual Computer,2010,26(11):1393-1406.

[4]Chesi G，Hung Y S.Fast Multiple-view L2 Triangulation with Occlusion Handling[J].Computer Vision and Image Understanding，2011，115(2)：211-223.

[5]Zetu D, Akgunduz A. Shape Recovery and Viewpoint Planning for Reverse Engineering[J]. The International Journal of Advanced Manufacturing Technology，2005, 26: 1370-1378.

[6]Ju X, Siebert J P, Khambay B S，et al.Self-correction of 3D Reconstruction from Multi-view Stereo Images [C]//IEEE 12th International Conference on Computer Vision Workshops. Los Alamitos: IEEE Computer Society Press, 2009: 1606-1613.

[7]徐进,柯映林. 点云部分缺失条件下边界曲面直接拟合技术[J]. 机械工程学报, 2010,46(3):135-140.

Xu Jin, Ke Yinglin. Boundary Surface Straight Fitting Technique with the Constraints of Incomplete Point Cloud[J]. Journal of Mechanical Engineering, 2010,46(3):135-140.

[8]Banta J E, Wong L R, Dumont C, et al. A Next-best-view Dystem for Sutonomous 3-D Object Reconstruction[J]. IEEE Transactions on Systems Man and Cybernetics-Part A: Systems and Humans，2000, 30(5): 589-598.

[9]何炳蔚,陈志鹏,林东艺，等.融合SFS和主动视觉技术的未知物体重建方法[J]. 仪器仪表学报,2012,33(4):727-736.

He Bingwei, Chen Zhipeng, Lin Dongyi, et al.Research on Reconstruction Method for Unknown Objects through Incorporating SFS Algorithm and Active Vision Technology[J]. Chinese Journal of Scientific Instrument,2012,33(4):727-736.

[10]何炳蔚, 周小龙. 面向未知物体自动测量和重建的视点规划方法[J].计算机辅助设计与图形学学报，2010，22（8）：1374-1381.

He Bingwei，Zhou Xiaolong. View Planning Method for Automatic Measurement and Reconstruction of Unknown Objects[J]. Journal of Computer-Aided Design & Computer Graphics，2010，22（8）：1374-1381.

[11]Newcombe R A, Izadi S, Hilliges O，et al. Kinect Fusion: Real-time Dense Surface Mapping and Tracking[C]// 10th IEEE/ACM International Symposium on Mixed and Augmented Reality. Los Alamitos: IEEE Computer Society Press, 2011: 127-136.

[12]Raheja J L, Chaudhary A, Singal K. Tracking of Fingertips and Centers of Palm Using Kinect[C]//The 3rd International Conference on Computational Intelligence, Modelling and Simulation. Los Alamitos: IEEE Computer Society Press, 2011: 248-252.

[13]何炳蔚,周小龙.线激光三维测量仪中视觉传感器规划方法研究[J].中国激光,2010,37(6):1618-1625.

He Bingwei,Zhou Xiaolong.Research of Sensor Planning Method in Line Laser Three-dimensional Measurement System[J].Chinese Journal of Lasers,2010,37(6):1618-1625.

[14]何炳蔚，林东艺，陈志鹏，等.三维物体视觉测量重构中解决遮挡问题的方法研究[J] . 中国激光，2011，38（7）：0708001（1）–0708001（10）.

He Bingwei, Lin Dongyi，Chen Zhipeng，et al. Research of Eliminating Occlusion in Visual Construction of Three-dimensional Objects[J] . China Journal of Lasers，2011，38（7）：0708001（1）–0708001（10）.

[15]陈天凡，高诚辉，何炳蔚.基于表面贴合的不同视点传感器点云拼合方法研究[J].中国机械工程，2012，23（24）：2968-2971.

Chen Tianfan,Gao Chenghui, He Bingwei. Research on Points Cloud Registration about Sensor from Different View Points Based on Surface Fit[J]. China Mechanical Engineering,2012,23（24）：2968-2971.