计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 143-146.

• 模式识别与图像处理 • 上一篇    下一篇

基于渐进可靠点生长的散斑图快速立体匹配

张彦峰,黄向生,李杭,王梦伟   

  1. 中国测绘科学研究院 北京100830;中国科学院自动化研究所 北京100190;中国科学院自动化研究所 北京100190;中国科学院自动化研究所 北京100190;清华大学 北京100083;中国科学院自动化研究所 北京100190
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(61175034),青年基金项目(61103154)资助

Fast Stereo Matching Based on Progressive Reliable Point Growing Matching for Speckle Pattern Images

ZHANG Yan-feng,HUANG Xiang-sheng,LI Hang and WANG Meng-wei   

  • Online:2018-11-14 Published:2018-11-14

摘要: 传统的区域生长匹配结果过于依赖生长阈值,而渐进可靠点生长匹配设置由高到低的种子点选取阈值和生长阈值迭代地生长区域,有效增强了匹配结果对于生长阈值的鲁棒性。有研究将该方法用于散斑图的立体匹配,取得了较好的效果,但是计算速度慢且仍存在不少非法点。实现了一种划分格网进而筛选种子点的方法,并在生长过程中丢弃传统的四邻域生长,提出一种跳跃式生长方法,其在确保匹配质量的同时大大提高了计算速度。进一步地,将渐进可靠点生长的方法用在匹配后处理中消除了一半的非法点。

关键词: 立体匹配,散斑图,区域生长,非法点 中图法分类号TP301.6文献标识码A

Abstract: Different from the traditional region growing matching algorithm which is excessively dependent on the growing threshold,PRPGM(Progressive Reliable Points Growing Matching) sets a sequence of thresholds from high to low for both seed point selection and growing matching to implement the stereo matching in an iterative process,thus enhancing the results’ robustness on the thresholds.A research has employed this method for depth estimation for speckle projection system and achieved good results.However,it motivates us to conduct this research that the calculation is not fast enough for practical applications as well as there are still many illegal points on the disparity map.We proposed a sparse seed point selecting method that selects seed point from grid divided by certain size on the speckle pattern image in the stage of selecting seed point and a jumping growing matching method instead of the conventional connectivity constraint of 4-neighbors domain during the growth of the reliable points.Both of the above revises have been verified to improve calculation speed greatly.Meanwhile,we applied the PRPGM to handle illegal points in post-processing of stereo matching and eliminated most of illegal points consequently.

Key words: Stereo matching,Speckle pattern image,Region growing,Invalid point

[1] Javier G.Three-dimensional mapping and range measurement by means of projected speckle patterns [J].Applied Optics,2008,47(16):3032-3040
[2] Freedman B,Shpunt A,Machline M,et al.Depth mapping using projected patterns:US,20100118123[P].2010-05-13
[3] 亚历山大·施庞特,泽夫·扎勒夫斯基.利用散斑图案的三维传感:中国,200780016625[P].2009-07-29
[4] 亚历山大· 施庞特,泽夫·扎勒夫斯基.三维传感的深度变化光场:中国,200780009053[P].2009-08-05
[5] 泽夫·扎勒夫斯基,亚历山大· 施庞特,雅维尔·加西亚,等.用于物体重现的方法和系统:中国,200680038004[P].2008-10-15
[6] Wang G J,Yin X W,Pei X K,et al.Depth estimation for speckle projection system using progressive reliable points growing matching [J].Applied Optics,2013,52(3):516-524
[7] Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J].International Journal of Computer Vision,2002,47(3):7-42
[8] El-Hakim S F,Beraldin J A,Blais F.A comparative evaluation of the performance of passive and active 3-d vision system [C]∥Proc.SPIE.Canada,NRC 39160,1995:14-25
[9] Szeliski R.Computer Vision:Alogorithms and Applications [M].New York:Springer,2010
[10] Zhang L.Automatic Digital Surface Model(DSM) Generationfrom Linear Array Images [D].Switzerland:Swiss Federal Institute of Technology Zurich,2005
[11] Marr D,Poggio T.A computational theory of human stereo vision [C]∥Proc of the Royal Society of London.London,Royal Society,1979:301-328
[12] 石春琴.随机光照双目立体测量系统中的若干关键问题研究[D].南京:南京航空航天大学,2011
[13] Hirschmüller H,Scharstein D.Evaluation of stereo matchingcosts on im-ages with radiometric differences [J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2008,31(9):1582-1599
[14] 舒志龙,阮秋琦.一种二维均值滤波快速算法及应用[J].北方交通大学学报,2001,25(2):22-24

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!