基于稀疏点云的多平面场景稠密重建

缪君; 储珺; 张桂梅; 王璐

doi:10.16383/j.aas.2015.c140279

基于稀疏点云的多平面场景稠密重建

doi: 10.16383/j.aas.2015.c140279

缪君^1,2,
储珺^2, ,,
张桂梅²,
王璐²

1.
南昌大学机电工程学院南昌 330031;
2.
南昌航空大学计算机视觉研究所南昌 330063

基金项目:

国家自然科学基金(61263046,61462065),江西省自然科学基金(20122BAB201037)资助

详细信息

作者简介:
缪君南昌大学机电工程学院博士研究生.南昌航空大学航空制造工程学院讲师.主要研究方向为计算机视觉与图像处理.E-mail:miaojun@nchu.edu.cn

通讯作者:
储珺南昌航空大学软件学院教授.主要研究方向为图像处理与计算机视觉.本文通信作者.E-mail:chuj@nchu.edu.cn

计量
- 文章访问数: 3919
- HTML全文浏览量: 353
- PDF下载量: 2662
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-22
- 修回日期: 2014-10-13
- 刊出日期: 2015-04-20

Dense Multi-planar Scene Reconstruction from Sparse Point Cloud

MIAO Jun^1,2,
CHU Jun^{2
, ,},
ZHANG Gui-Mei²,
WANG Lu²

1.
School of Mechanical and Electrical Engineering, Nanchang University, Nanchang 330031;
2.
Institute of Computer Vision, Nanchang Hangkong University, Nanchang 330063

Funds:

Supported by National Natural Science Foundation of China(61263046, 61462065) and Natural Science Foundation of Jiangxi Province(20122BAB201037)

摘要

摘要: 多平面场景是生活中常见的一种场景,然而由于该类场景中常常存在物体表面纹理缺乏和纹理重复的现象,导致从多视图像重建获得的三维点云数据中存在点云过于稀疏甚至孔洞等问题,进而导致以微面片拟合三维点云所得到的重建表面出现平面颠簸现象.针对这些问题,本文提出了一种基于稀疏点云的分段平面场景重建方法.首先,利用分层抽样代替随机抽样,改进了J-Linkage多模型估计算法;然后,利用该方法对稀疏点云进行多平面拟合,来获得场景的多平面模型;最后,将多平面模型和无监督的图像分割相结合,提取并重建场景中的平面区域.场景中的非平面部分用CMVS/PMVS(Clustering views for multi-view stereo/patch-based multi-view stereo)算法重建.多平面模型估计的实验表明,改进的J-Linkage算法提高了模型估计的准确度.三维重建的实验证实,提出的重建方法在有效地克服孔洞和平面颠簸问题的同时,还能重建出完整平面区域.
- 多视重建 /
- 三维重建 /
- 多模型估计 /
- 图像分割
Abstract: There are multi-planar scenes everywhere in our daily life. However, given its lack and self-repeat of the texture, there would be problems of over scarcity and holes on the reconstructed point cloud by the method of multi-view reconstruction. Further, there would be vacillation over the reconstructed facades using the method of fitting the reconstructed point cloud with miniature facets. To address these problems, we propose a method of piecewise reconstruction of each plane from the sparse point cloud. The proposed method first improves the J-linkage algorithm, with the stratified sampling instead of the random sampling. We then fit the point cloud with planes using the improved J-linkage algorithm, to obtain the multi-planar model of the scene. Finally, we extract and reconstruct the planar regions with the multi-planar model as well as an unsupervised segmentation algorithm. Besides, the non-planar areas are reconstructed by using the clustering views for multi-view stereo/patch-based multi-view stereo(CMVS/PMVS) algorithm. Experimental results of the multi-planar model demonstrate that the improved J-linkage algorithm can enhance the accuracy of the multi-planar model. Also, the experimental results of 3D reconstruction show that our method not only can effectively overcome holes and jaggies problems, but also can model the complete planar regions.
- Multi-view reconstruction /
- 3D reconstruction /
- multiple structures estimation /
- image segmentation

HTML全文

参考文献(26)

[1]	Vanegas C A, Aliaga D G, Wonka P, Mller P, Waddell P, Watson B. Modelling the appearance and behaviour of urban spaces. Computer Graphics Forum, 2010, 29(1):25-42
[2]	[2] Sheppard S R J, Cizek P. The ethics of Google Earth:crossing thresholds from spatial data to landscape visualisation. Journal of Environmental Management, 2009, 90(6):2012-2117
[3]	Shi Li-Min, Guo Fu-Sheng, Hu Zhan-Yi. An improved PMVS through scene geometric information. Acta Automatica Sinica, 2011, 37(5):560-568(史利民, 郭复胜, 胡占义. 利用空间几何信息的改进PMVS算法. 自动化学报, 2011, 37(5):560-568)
[4]	[4] Simon L, Teboul O, Koutsourakis P, Van Gool L, Paragios N. Parameter-free/Pareto-driven procedural 3D reconstruction of buildings from ground-level sequences. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Rhode Island, USA:IEEE, 2012. 518-525
[5]	[5] Vanegas C A, Aliaga D G, Benes B. Automatic extraction of manhattan-world building masses from 3D laser range scans. IEEE Transactions on Visualization and Computer Graphics, 2012, 18(10):1627-1637
[6]	[6] Agarwal S, Furukawa Y, Snavely N, Simon I, Curless B, Seitz S M, Szeliski R. Building rome in a day. In:Proceedings of the 12th International Conference on Computer Vision. Kyoto, Japan:IEEE, 2009. 72-79
[7]	[7] Mičuk B, Koeck J. Multi-view superpixel stereo in urban environments. International Journal of Computer Vision, 2010, 89(1):106-119
[8]	[8] Snavely N, Simon I, Goesele M, Szeliski R, Seitz S M. Scene reconstruction and visualization from community photo collections. Proceedings of the IEEE, 2010, 98(8):1370-1390
[9]	[9] Bartoli A, Sturm P. Constrained structure and motion from multiple uncalibrated views of a piecewise planar scene. International Journal of Computer Vision, 2003, 52(1):45-64
[10]	Zhou Z H, Jin H L, Ma Y. Robust plane-based structure from motion. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Rhode Island, USA:IEEE, 2012. 1482-1489
[11]	Goesele M, Snavely N, Curless B, Hoppe H, Seitz S M. Multi-view stereo for community photo collections. In:Proceedings of the 11th International Conference on Computer Vision. Rio de Janeiro, Brazil:IEEE, 2007. 1-8
[12]	Seitz S M, Curless B, Diebel J, Scharstein D, Szeliski R. A comparison and evaluation of multi-view stereo reconstruction algorithms. In:Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA:IEEE, 2006. 519-528
[13]	Furukawa Y, Ponce J. Accurate, dense, and robust multiview stereopsis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(8):1362-1376
[14]	Musialski P, Wonka P, Aliaga D G, Wimmer M, Gool L, Purgathofer W. A survey of urban reconstruction. In Computer Graphics Forum, 2013, 32(6):146-177
[15]	Bartoli A. A random sampling strategy for piecewise planar scene segmentation. Computer Vision and Image Understanding, 2007, 105(1):42-59
[16]	Yu W C, Kai L Y, Chung P C. 3D reconstruction of piecewise planar models from multiple views utilizing coplanar and region constraints. Journal of Information Science and Engineering, 2013, 29(2):361-378
[17]	Micusik B, Kosecka J. Piecewise planar city 3D modeling from street view panoramic sequences. In:Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA:IEEE, 2009. 2906-2912
[18]	Sinha S N, Steedly D, Szeliski R. Piecewise planar stereo for image-based rendering. In:Proceedings of the 12th IEEE Conference on Computer Vision. Rio de Kyoto, Japan:IEEE, 2009. 1881-1888
[19]	Gallup D, Frahm J M, Pollefeys M. Piecewise planar and non-planar stereo for urban scene reconstruction. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA:IEEE, 2010. 1418-1425
[20]	Hane C, Zach C, Cohen A, Angst R, Pollefeys M. Joint 3D scene reconstruction and class segmentation. In:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA:IEEE, 2013. 97-104
[21]	Toldo R, Fusiello A. Photo-consistent planar patches from unstructured cloud of points. In:Proceedings of the 2010 European Conference on Computer Vision. Crete, Greece:Springer, 2010. 589-602
[22]	Toldo R, Fusiello A. Robust multiple structures estimation with J-linkage. In:Proceedings of the 2008 European Conference on Computer Vision. Marseille, France:Springer, 2008. 537-547
[23]	Zuliani M, Kenney C S, Manjunath B S. The multiransac algorithm and its application to detect planar homographies. In:Proceedings of the 2005 IEEE Conference on Image Processing. Genoa, Italy:IEEE, 2005. 153-156
[24]	Veksler O. Star shape prior for graph-cut image segmentation. In:Proceedings of the 2008 European Conference on Computer Vision. Marseille, France:Springer, 2008. 454-467
[25]	Gulshan V, Rother C, Criminisi A, Blake A, Zisserman A. Geodesic star convexity for interactive image segmentation. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA:IEEE, 2010. 3129-3136
[26]	Farenzena M, Fusiello A, Gherardi R. Structure-and-motion pipeline on a hierarchical cluster tree. In:Proceedings of the 12th IEEE Conference on Computer Vision Workshops. Miami, USA:IEEE, 2009. 1489-1496