论文:2021,Vol:39,Issue(1):135-140
引用本文:
宋征玺, 吴淇, 王雪, 王庆. 基于三维霍夫变换的环形光场三维重建[J]. 西北工业大学学报
SONG Zhengxi, WU Qi, WANG Xue, WANG Qing. 3D Reconstruction with circular light field by using 3D hough transformation[J]. Northwestern polytechnical university

基于三维霍夫变换的环形光场三维重建
宋征玺, 吴淇, 王雪, 王庆
西北工业大学 计算机学院, 陕西 西安 710072
摘要:
针对环形光场的二维对极几何图特征轨迹不完整问题,提出了一种基于三维霍夫变换的环形光场三维重建方法。将三维重建参数求解转化为高维图像体特征轨迹参数的解算。通过分析环形光场图像体中特征轨迹三维分布,提取图像体中的轨迹曲线,并采用三维结构张量分析曲线的局部方向。构建了面向三维曲线检测的三维霍夫空间,并设计霍夫参数筛选方法。通过曲线参数恢复每个视点下的三维点云并根据环形光场视点关系融合形成重建结果。消除了二维霍夫变换求解三维特征轨迹参数的歧义性,并在环形光场仿真与真实数据集上进行了三维重建实验。实验结果表明,该方法能够提高环形光场三维重建的精度与效果。
关键词:    环形光场    对极几何图    三维霍夫变换    三维重建    张量分析    点云    特征轨迹   
3D Reconstruction with circular light field by using 3D hough transformation
SONG Zhengxi, WU Qi, WANG Xue, WANG Qing
School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
Aiming at the issue of incomplete trajectories in the 2D epipolar image of circular light field, this paper proposes a 3D reconstruction method by using 3D Hough transformation. This method computes 3D point clouds by computing the parameters of feature trajectories in 3D image volume. By analyzing the 3D distribution of circular light field trajectories, binary curves in image volume are extracted, and their local orientation are further estimated by the 3D structure tensor. The 3D Hough space generation and the parameter selection method are proposed to the 3D curves detection. The parameters of these curves are converted to 3D point clouds on each view and then merged to final 3D reconstruction. The ambiguity of Hough transformation solution on 2D epipolar image is overcome by the 3D analyzing method. The experiments are carried out on both synthetic and real datasets. The experiment results show that this method can improve the reconstruction performance compared with the state-of-the-art in circular light field.
Key words:    circular light field    epipolar image    3D Hough transformation    3D reconstruction    tensor analysis    point clouds    feature trajectory   
收稿日期: 2020-06-12     修回日期:
DOI: 10.1051/jnwpu/20213910135
基金项目: 国家自然科学基金(61531014,61801396)资助
通讯作者:     Email:
作者简介: 宋征玺(1990-),女,西北工业大学博士研究生,主要从事计算机视觉,情报数据分析研究。
相关功能
PDF(2457KB) Free
打印本文
把本文推荐给朋友
作者相关文章
宋征玺  在本刊中的所有文章
吴淇  在本刊中的所有文章
王雪  在本刊中的所有文章
王庆  在本刊中的所有文章

参考文献:
[1] SCHONBERGER J L, FRAHM J M. Structure-from-motion revisited[C]//IEEE Conference on Computer Vision and Pattern Recognition, Seattle, United States, 2016: 4104-4113
[2] ENGEL J, SCHOPS T and CREMERS D. LSD-SLAM: large-scale direct monocular SLAM[C]//13th European Conference on Computer Vision, Lecture Notes in Computer Science, Zurich, Switzerland, 2014, 8690: 834-849
[3] MUR-ARTAL R, MONTIEL J, TARDOS, J. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Trans on Robotics, 2015, 31(5): 1147-1163
[4] LEVOY M, HANRAHAN P. Light field rendering[C]//Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, Siggraph, New Orleans, United States 1996: 31-42
[5] WANNER S. Orientation Analysis in 4D Light Fields[D]. Heidelberg: Heidelberg University, 2014
[6] KIM C, ZIMMER H, PRITCH Y, SORKINE-HORNUNG A, GROSS M. Scene reconstruction from high spatio-angular resolution light fields[J]. ACM Transactions on Graphics, 2013, 32(4): 1-12
[7] FELDMANN I, KAUFF P, EISERT P. Detection strategies for image cube trajectory analysis[C]//2007 IEEE International Conference on Image Processing, San Antonio, United States, 2007: 533-536
[8] FELDMANN I, EISER P, KAUFF P. Extension of epipolar image analysis to circular camera movements[C]//Proceedings 2003 International Conference on Image Processing, Barcelona, Spain, 2003: 697
[9] FELDMANN I, KAUFF P, EISER P. Optimized space sampling for circular image cube trajectory analysis[C]//2004 International Conference on Image Processing, Singapore, 2004: 1947-1950
[10] YÜCER K, SORKINE-HORNUNG A, WANG O, SORKINE-HORNUNG O. Efficient 3D object segmentation from densely sampled light fields with applications to 3D reconstruction[J]. ACM Trans on Graphics 2016, 35(3): 22
[11] VIANELLO A, ACKERMANN J, DIEBOLD M, JAHNE B. Robust hough transform based 3D reconstruction from circular light fields[C]//IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, United States, 2018: 7327-7335
[12] VIANELLO A. Robust 3D surface reconstruction from light fields[D]. Heidelberg: Heidelberg University, 2017
[13] GOESELE M, SNAVELY N, CURLESS B, HOPPE H, SEITZ S. Multi-view stereo for community photo collections[C]//Proceedings of the IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, 2007: 825-832
[14] FOUNDATION B. Blender[EB/OL]. (2015-07-28)[2020-12-25]. http://www.blender.org, 2016
[15] SCHARSTEIN D,SZELISKI R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1/2/3): 7-42
[16] FURUKAWA Y, PONCE J. Accurate, dense, and robust multiview stereopsis[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 32(8): 1362-1376