Full Text:   <709>

Summary:  <465>

CLC number: TP242.6

On-line Access: 2015-07-06

Received: 2014-09-03

Revision Accepted: 2015-01-24

Crosschecked: 2015-06-09

Cited: 0

Clicked: 2310

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Qian-shan Li

http://orcid.org/0000-0003-0370-7100

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2015 Vol.16 No.7 P.594-606

http://doi.org/10.1631/FITEE.14a0260


Building a dense surface map incrementally from semi-dense point cloud and RGB images


Author(s):  Qian-shan Li, Rong Xiong, Shoudong Huang, Yi-ming Huang

Affiliation(s):  State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China; more

Corresponding email(s):   liqianshan@zju.edu.cn, rxiong@iipc.zju.edu.cn, shoudong.huang@uts.edu.au, ymhuang@zju.edu.cn

Key Words:  Bionic robot, Robotic mapping, Surface fusion


Qian-shan Li, Rong Xiong, Shoudong Huang, Yi-ming Huang. Building a dense surface map incrementally from semi-dense point cloud and RGB images[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(7): 594-606.

@article{title="Building a dense surface map incrementally from semi-dense point cloud and RGB images",
author="Qian-shan Li, Rong Xiong, Shoudong Huang, Yi-ming Huang",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="16",
number="7",
pages="594-606",
year="2015",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.14a0260"
}

%0 Journal Article
%T Building a dense surface map incrementally from semi-dense point cloud and RGB images
%A Qian-shan Li
%A Rong Xiong
%A Shoudong Huang
%A Yi-ming Huang
%J Frontiers of Information Technology & Electronic Engineering
%V 16
%N 7
%P 594-606
%@ 2095-9184
%D 2015
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.14a0260

TY - JOUR
T1 - Building a dense surface map incrementally from semi-dense point cloud and RGB images
A1 - Qian-shan Li
A1 - Rong Xiong
A1 - Shoudong Huang
A1 - Yi-ming Huang
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 16
IS - 7
SP - 594
EP - 606
%@ 2095-9184
Y1 - 2015
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.14a0260


Abstract: 
Building and using maps is a fundamental issue for bionic robots in field applications. A dense surface map, which offers rich visual and geometric information, is an ideal representation of the environment for indoor/outdoor localization, navigation, and recognition tasks of these robots. Since most bionic robots can use only small light-weight laser scanners and cameras to acquire semi-dense point cloud and RGB images, we propose a method to generate a consistent and dense surface map from this kind of semi-dense point cloud and RGB images. The method contains two main steps: (1) generate a dense surface for every single scan of point cloud and its corresponding image(s) and (2) incrementally fuse the dense surface of a new scan into the whole map. In step (1) edge-aware resampling is realized by segmenting the scan of a point cloud in advance and resampling each sub-cloud separately. Noise within the scan is reduced and a dense surface is generated. In step (2) the average surface is estimated probabilistically and the non-coincidence of different scans is eliminated. Experiments demonstrate that our method works well in both indoor and outdoor semi-structured environments where there are regularly shaped objects.

This paper introduces a method that increamentally constructs dense surface map using low cost devices. Their method has two steps: denoise and resample each scan, then incrementally fuse these scans. The research idea in the manuscript is interesting and the paper is well organized and is pleasing to read.

一种利用半稠密点云及RGB图像构建稠密表面模型地图的方法

目的:针对仅能通过轻型激光测距仪获取半稠密点云的环境地图构建问题,提出一种构建稠密表面模型的方法。该方法使机器人能够利用所构建的稠密表面模型地图完成定位、导航及目标搜索等任务。
创新点:提出一种基于点云分割的点云表面重采样方法及一种基于点云概率模型的表面模型融合方法。对半稠密点云进行保留表面结构特性的重采样来获取观测数据的稠密表面模型。并递增式地将新获得的稠密表面模型融合进已有的稠密表面地图中,从而获得几何一致性较好的环境表面模型地图。
实验效果:图6、7展示了基于本文方法所构建的稠密表面模型地图的效果。其几何结构精确且表面纹理清晰。此外,图8、9分别重点展示了表面重采样的作用以及本文提出的重采样方法的效果。图11则展示了本文方法对表面模型动态更新的较好支持。
结论:使用本文所提方法,机器人可携带轻便式激光测距仪,获取半稠密点云后再进一步处理和融合得到几何一致性较高、表面精细的稠密表面问题模型地图,更好地实现定位、导航及目标搜索等任务。

关键词:仿生机器人;地图构建;表面融合

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Amenta, N., Bern, M., 1999. Surface reconstruction by Voronoi filtering. Discr. Comput. Geom., 22(4):481-504.

[2]Amenta, N., Choi, S., Kolluri, R.K., 2001. The power crust. Proc. 6th ACM Symp. on Solid Modeling and Applications, p.249-266.

[3]Bajaj, C.L., Bernardini, F., Xu, G., 1997. Reconstructing surfaces and functions on surfaces from unorganized three-dimensional data. Algorithmica, 19(1-2):243-261.

[4]Básaca-Preciado, L.C., Sergiyenko, O.Y., Rodríguez-Quinonez, J.C., et al., 2014. Optical 3D laser measurement system for navigation of autonomous mobile robot. Opt. Lasers Eng., 54:159-169.

[5]Cole, D.M., Newman, P.M., 2006. Using laser range data for 3D SLAM in outdoor environments. Proc. IEEE Int. Conf. on Robotics and Automation, p.1556-1563.

[6]Crossno, P., Angel, E., 1999. Spiraling edge: fast surface reconstruction from partially organized sample points. Proc. Conf. on Visualization, p.317-324.

[7]Dey, T.K., Wang, L., 2013. Voronoi-based feature curves extraction for sampled singular surfaces. Comput. Graph., 37(6):659-668.

[8]Dey, T.K., Giesen, J., Hudson, J., 2001. Delaunay based shape reconstruction from large data. Proc. IEEE Symp. on Parallel and Large-Data Visualization and Graphics, p.19-146.

[9]Dey, T.K., Dyer, R., Wang, L., 2011. Localized Cocone surface reconstruction. Comput. Graph., 35(3):483-491.

[10]Dey, T.K., Ge, X., Que, Q., et al., 2012. Feature-preserving reconstruction of singular surfaces. Comput. Graph. Forum, 31(5):1787-1796.

[11]Felzenszwalb, P.F., Huttenlocher, D.P., 2004. Efficient graph-based image segmentation. Int. J. Comput. Vis., 59(2):167-181.

[12]Gopi, M., Krishnan, S., 2002. A fast and efficient projection-based approach for surface reconstruction. Proc. Brazilian Symp. on Computer Graphics and Image Processing, p.179-186.

[13]Holz, D., Behnke, S., 2013. Fast range image segmentation and smoothing using approximate surface reconstruction and region growing. Proc. 12th Int. Conf. on Intelligent Autonomous Systems, p.61-73.

[14]Huang, H., Wu, S., Gong, M., et al., 2013. Edge-aware point set resampling. ACM Trans. Graph., 32(1):Article 9.

[15]Lin, J., Jin, X., Wang, C., et al., 2008. Mesh composition on models with arbitrary boundary topology. IEEE Trans. Visual. Comput. Graph., 14(3):653-665.

[16]Lopez, M.R., Sergiyenko, O.Y., Tyrsa, V.V., et al., 2010. Optoelectronic method for structural health monitoring. Struct. Health Monit., 9(2):105-120.

[17]Lou, R., Pernot, J.P., Mikchevitch, A., et al., 2010. Merging enriched finite element triangle meshes for fast prototyping of alternate solutions in the context of industrial maintenance. Comput.-Aid. Des., 42(8):670-681.

[18]Marton, Z.C., Rusu, R.B., Beetz, M., 2009. On fast surface reconstruction methods for large and noisy point clouds. Proc. IEEE Int. Conf. on Robotics and Automation, p.3218-3223.

[19]Maurelli, F., Droeschel, D., Wisspeintner, T., et al., 2009. A 3D laser scanner system for autonomous vehicle navigation. Proc. Int. Conf. on Advanced Robotics, p.1-6.

[20]Newcombe, R.A., Izadi, S., Hilliges, O., et al., 2011. KinectFusion: real-time dense surface mapping and tracking. Proc. 10th IEEE Int. Symp. on Mixed and Augmented Reality, p.127-136.

[21]Nüchter, A., Lingemann, K., Hertzberg, J., et al., 2007. 6D SLAM—3D mapping outdoor environments. J. Field Robot., 24(8-9):699-722.

[22]Pandey, G., McBride, J., Savarese, S., et al., 2010. Extrinsic calibration of a 3D laser scanner and an omnidirectional camera. Proc. 7th IFAC Symp. on Intelligent Autonomous Vehicles.

[23]Rusu, R.B., Marton, Z.C., Blodow, N., et al., 2008. Towards 3D point cloud based object maps for household environments. Robot. Auton. Syst., 56(11):927-941.

[24]Schadler, M., Stückler, J., Behnke, S., et al., 2014. Rough terrain 3D mapping and navigation using a continuously rotating 2D laser scanner. Künstl. Intell., 28(2):93-99.

[25]Sheehan, M., Harrison, A., Newman, P., 2012. Self-calibration for a 3D laser. Int. J. Robot. Res., 31(5):675-687.

[26]Wang, Y.B., Sheng, Y.H., Lv, G.N., et al., 2007. A Delaunay-based surface reconstrution algorithm for unorganized sampling points. J. Image Graph., 12(9):1537-1543 (in Chinese).

[27]Whelan, T., Kaess, M., Fallon, M., et al., 2012. Kintinuous: Spatially Extended KinectFusion. Technical Report No. MIT-CSAIL-TR-2012-020. Massachusetts Institute of Technology, USA.

[28]Wulf, O., Wagner, B., 2003. Fast 3D scanning methods for laser measurement systems. Proc. Int. Conf. on Control Systems and Computer Science, p.2-5.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE