基于图像特征分析的物体轮廓提取

王田; 邹子龙; 乔美娜

doi:10.13700/j.bh.1001-5965.2015.0491

基于图像特征分析的物体轮廓提取

doi: 10.13700/j.bh.1001-5965.2015.0491

北京航空航天大学自动化科学与电气工程学院, 北京 100083

基金项目: 国家自然科学基金（U1435220,61503017）；中央高校基本科研业务费专项资金（YWF-14-RSC-102）

详细信息

作者简介:
王田,男,博士,讲师。主要研究方向为:计算机视觉与模式识别。Tel.:010-82339358。E-mail:wangtian@buaa.edu.cn

通讯作者:
王田,Tel.:010-82339358,E-mail:wangtian@buaa.edu.cn

中图分类号: TP391.4
计量
- 文章访问数: 787
- HTML全文浏览量: 10
- PDF下载量: 1258
- 被引次数: 0
出版历程
- 收稿日期: 2015-07-22
- 刊出日期: 2016-08-20

Object contour extraction based on image feature analysis

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

摘要

摘要: 对物体的轮廓进行分析提取，是计算机视觉方向的基础问题之一，对其进行研究对于复杂场景的分析理解至关重要。本文对室内场景图像进行研究，基于图像特征进行图像分割，提取物体轮廓。在彩色场景图像全局轮廓后验边界概率（gPb）提取算法的基础上，加入深度图像信息，对室内场景的彩色、深度（RGB-D）图像中的物体轮廓进行分析。通过多尺度信息融合，计算得到多尺度轮廓后验概率（mPb）和谱后验概率（sPb）,两后验概率加权综合得到gPb。而后结合超度量轮廓图与分水岭算法，对基于方向特征变化的gPb图像融合处理，最终得到清晰的物体轮廓。本文所提方法在通用的RGB-D数据库基础上进行实验。实验结果表明，本文所提出的方法能提取出清晰的室内物体轮廓图。
- RGB-D /
- 尺度次信息融合 /
- 全局轮廓后验边界概率(gPb) /
- 分水岭算法 /
- 超度量轮廓
Abstract: Contour analysis and extraction is the fundamental problem in computer vision, and the research about it plays an important part in complex scene analysis and comprehension. In this paper, an algorithm for analyzing indoor scene images is studied. Based on the image features extracted from the images, the objects in the indoor scenes are segmented, and further the contours of the objects are extracted. Based on the globalized posterior probability of a boundary (gPb) method for the contour extraction on the RGB image, we introduce the depth information to enhance the performance of contour extraction on RGB-D data of indoor scenes. By combining multi-scale cues, the multi-scale posterior probability (mPb) and spectral posterior probability (sPb) are obtained. The mPb and sPb results are summed and weighted to get the gPb information. Then, the gPb information is processed by ultrametric contour and watershed algorithm, and the contours of the indoor scene objects are gained. The experiments presented in this paper are run on the general RGB-D dataset. The experimental results show that our method can extract the distinct contours of indoor objects.
- RGB-D /
- multi-scale cues fusion /
- globalized posterior probability of a boundary (gPb) /
- watershed algorithm /
- ultrametric contour

HTML全文

参考文献(15)

[1]	ROBERTS L G.Machine perception of three-dimensional solids[J].Optical and Electro-optical Information Processing,1963,20:31-39.
[2]	DUDA R O,HART P E.Pattern classification and scene analysis[M].New York:Wiley-Interscience Publication,1973:10-12.
[3]	PREWITT J.Object enhancement and extraction[J].Picture Processing and Psychopictorics,1970,10(1):15-19.
[4]	MARR D,HILDRETH E.Theory of edge detection[J].Royal Society of London Proceedings,1980,207(1167):187-217.
[5]	PERONA P,MALIK J.Detecting and localizing edges composed of steps,peaks and roofs[C]//Proceedings 3rd IEEE International Conference on Computer Vision (ICCV 1990).Piscataway,NJ:IEEE Press,1990:52-57.
[6]	MORRONE M C,OWENS R A.Feature detection from local energy[J].Pattern Recognition Letters,2014,6(5):303-313.
[7]	MARTIN D R,FOWLKES C C,MALIK J.Learning to detect natural image boundaries using local brightness,color,and texture cues[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(5):530-549.
[8]	GUPTA S,ARBELÁEZ P,MALIK J.Perceptual organization and recognition of indoor scenes from RGB-D images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013).Piscataway,NJ:IEEE Press,2013:564-571.
[9]	DOLLAR P,TU Z,BELONGIE S.Supervised learning of edges and object boundaries[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2006).Piscataway,NJ:IEEE Press,2006:1964-1971.
[10]	TU Z W.Probabilistic boosting-tree:Learning discriminative models for classification,recognition,and clustering[C]//Proceedings 10 th IEEE International Conference on Computer Vision (ICCV 2005).Piscataway,NJ:IEEE Press,2005:1589-1596.
[11]	FELZENSZWALB P F,HUTTENLOCHER D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.
[12]	SILBERMAN N,HOIEM D,KOHLI P,et al.Indoor segmentation and support inference from RGBD images[C]//Proceedings of the 12th European Conference on Computer Vision (ECCV 2012).Heidelberg:Springer-Verlag,2012,Part 5:746-760.
[13]	ARBELAEZ P,MAIRE M,FOWLKES C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(5):898-916.
[14]	NAJMAN L,SCHMITT M.Geodesic saliency of watershed contours and hierarchical segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1996,18(12):1163-1173.
[15]	AEBELAEZ P.Boundary extraction in natural images using ultrametric contour maps[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshop.Piscataway,NJ:IEEE Press,2006:182-189.