基于三维光场的静态场景前景分割

魏巍; 老松杨; 康来; 白亮

doi:10.13700/j.bh.1001-5965.2014.0477

基于三维光场的静态场景前景分割

doi: 10.13700/j.bh.1001-5965.2014.0477

国防科学技术大学信息系统与管理学院, 长沙 410073

基金项目: 国家自然科学基金(61201339)

详细信息

作者简介:
魏巍(1991—),男,河南开封人,硕士研究生,ww91911@163.com

通讯作者:
老松杨(1968—),男,广东南海人,教授,laosongyang@vip.sina.com,主要研究方向为多媒体信息系统.

中图分类号: TP391.41
计量
- 文章访问数: 965
- HTML全文浏览量: 143
- PDF下载量: 593
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-28
- 修回日期: 2014-11-27
- 网络出版日期: 2015-07-20

3D light fields based foreground segmentation in static scenes

Collage of Information System and Management, National University of Defense Technology, Changsha 410073, China

摘要

摘要: 为解决复杂场景中的前景提取问题提出一种基于三维光场分析的静态场景前景分割方法.首先,通过在一条直线等间距的不同视点上拍摄场景的序列图像构建密集采样的三维光场.其次,用线段检测(LSD)直线检测算法从对极平面图(EPI)中分析提取出场景边缘及其深度信息.借助分段三次Hermite多项式(PCHIP)快速插值算法恢复整个场景的深度信息.最终,通过阈值法实现对不同深度的前景物体的分割.初步实验结果表明,本方法能够较准确地恢复场景中多个物体之间的空间关系,前景分割结果较好地克服了现有基于区域聚类和数学形态学等方法在复杂场景应用中存在的过分割问题.
- 三维光场 /
- 对极平面图(EPI) /
- 深度图 /
- 静态场景 /
- 前景分割
Abstract: To address the problem of extracting foreground objects from complex scenes, a 3D light field based method for foreground segmentation of static scenes was presented. Firstly, the method relies on densely sampled 3D light field formed by stacking a sequence of images captured at different viewpoints. These viewpoints were equally spaced along a linear path so that object trace was smooth in epipolar plan image (EPI). Secondly, line segment detection (LSD) method was performed to extract edges and compute the corresponding depth in EPI, based on which a depth map of the scene was obtained through a fast local depth interpolation algorithm. Piecewise cubic Hermite interpolating polynomial (PCHIP) algorithm proved to have desirable results in this phase. Finally, the recovered dense depth information was exploited to facilitate foreground segmentation. A threshold approach was used to separate different objects in scenes. Preliminary experimental results show that our method is able to estimate the correct relative spatial relation of multiple objects and our proposed foreground segmentation method reduces over-segmentation effects existed in traditional methods based on region clustering and mathematical morphology.
- 3D light fields /
- epipolar plan image (EPI) /
- depth map /
- static scene /
- foreground segmentation

HTML全文

参考文献(17)

[1]	Bhattacharyya S. A brief survey of color image preprocessing and segmentation techniques[J].Journal of Pattern Recognition Research, 2011, 6(1): 120-129.
[2]	Arbelaez P, Maire M, Fowlkes C, et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898-916.
[3]	Bolles R C, Baker H H, Marimont D V.Epipolar-plane image analysis: An approach to determining structure from motion[J].International Journal of Computer Vision, 1987, 1(1): 7-55.
[4]	Levoy M, Hanrahan P.Light field rendering[J].Annual Conference on Computer Graphics, 1996: 31-42.
[5]	Wanner S, Goldluecke B.Globally consistent depth labeling of 4D light fields[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2012: 41-48.
[6]	Kim C, Zimmer H, Pritch Y, et al.Scene reconstruction from high spatio-angular resolution light fields[J].ACM Transactions on Graphics, 2013, 32(4): 1-12.
[7]	Vincent L, Soille P.Watersheds in digital spaces: An efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598.
[8]	Felzenszwalb P F, Huttenlocher D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision, 2004, 59(2): 167-181.
[9]	Chan T F, Vese L A.Active contours without edges[J].IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
[10]	皮志明, 汪增福.融合深度和颜色信息的图像物体分割算法[J].模式识别与人工智能, 2013, 26(2): 151-158. Pi Z M, Wang Z F.Image object segmentation algorithm by combining depth discontinuities and color information[J].Pattern Recognition and Artificial Intelligence, 2013, 26(2): 151-158(in Chinese).
[11]	范忠良, 蒋刚毅, 郁梅.多视点图像的前景对象自动分割方法[J].计算机辅助设计与图形学报, 2009, 21(9): 1316-1320. Fan Z L, Jiang G Y, Yu M.Automatic foreground object segmentation from multi-view images[J].Journal of Computer-aided Design & Computer Graphics, 2009, 21(9): 1316-1320(in Chinese).
[12]	Yu Y Z, Ferencz A, Malik J.Extracting objects from range and radiance images[J].IEEE Transactions on Visualization and Computer Graphics, 2001, 7(4): 351-364.
[13]	von Gioi R G, Jakubowicz J, Morel J M, et al.LSD: A fast line segment detector with a false detection control[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.
[14]	Desolneux A, Moisan L, Morel J-M.Meaningful alignments[J].International Journal of Computer Vision, 2000, 40(1): 7-23.
[15]	Fritsch F N, Carlson R E.Monotone piecewise cubic interpolation[J].SIAM Journal on Numerical Analysis, 1980, 17(2): 238-246.
[16]	Maddalena L, Petrosino A.A self-organizing approach to background subtraction for visual surveillance applications[J].IEEE Transactions on Image Processing, 2008, 17(7): 1168-1177.
[17]	Hartigan J A, Wong M A.Algorithm AS 136: A K-means clustering algorithm[J].Journal of the Royal Statistical Society.Series C(Applied Statistics), 1979, 28(1): 100-108.