Technology for fast 3D-scene reconstruction from stereo images
A.P. Kotov, V.A. Fursov, Ye.V. Goshin

 

Image Processing Systems Institute, Russian Academy of Sciences,

Samara State Aerospace University

Full text of article: Russian language.

 PDF

Abstract:
We propose a fast algorithm for disparity maps construction from stereo images. It is known that the main problem in 3D-reconstruction is to find the corresponding points on different views of the scene. The search area greatly extends when shifts and scale differences in stereo images are great. To improve the performance we offer to use initial image matching by using an affine transform. The reliability and efficiency of image matching in subsequent steps is achieved by using epipolar constraints and an image pyramid. The developed method was implemented on a parallel computing platform CUDA. The results of experimental studies show high performance of the proposed approach, while maintaining the high-quality reconstruction of 3D-scenes.

Keywords:
digital image processing, 3D-scene reconstruction, image matching, affine transform, CUDA.

Citation:
Kotov AP, Fursov VA, Goshin YeV. Technology for fast 3d-scene reconstruction from stereo images. Computer Optics 2015; 39(4): 600-5. DOI: 10.18287/0134-2452-2015-39-4-600-605.

References:

  1. Reznik AL, Efimov VM, Torgov AV. Effective methods on speed of digital processing dynamic sequences of images [In Russian]. Vestnik Novosibirskogo Gosudarstvennogo Universiteta 2008; 3(3): 95-103.
  2. Baillard C, Ma?tre H. 3-D reconstruction of urban scenes from aerial stereo imagery: a focusing strategy. Computer Vision and Image Understanding 1999;76(3): 244-58.
  3. Hartley RI. Theory and Practice of Projective Rectification. International Journal of Computer Vision 1999; 35: 115-27.
  4. Fursov VA, Goshin YeV, Bibikov SA. 3D-scene stereo reconstruction on sheaves of epipolar planes [In Russian]. Mechatronics Automation Control 2013; 9(150): 19-24.
  5. Fursov VA, Goshin YeV. Information technology for digital terrain model reconstruction from stereo images [In Russian]. Computer Optics 2014; 38(2): 335-42. – ISSN 0134-2452.
  6. Lowe DG. Object recognition from local scale-invariant features. Computer Vision, 1999. The proceedings of the seventh IEEE international conference on 1999; 2: 1150-7.
  7. Bay H, Ess A, Tuytelaars T, Van Gool L. Speeded-up robust features (SURF). Computer Vision and Image Understanding 2008: 110(3): 346-59.
  8. Fursov VA, Goshin YeV. Conformed identification in corresponding points detection problem. Computer Optics 2012; 36(1): 131-5.
  9. Fursov VA, Goshin YeV. Solving a camera autocalib­ration problem with a conformed identification method. Computer Optics 2014; 36(4): 605-10. – ISSN 0134-2452.
  10. Harris C, Stephens M. A combined corner and edge detector. Alvey Vision Conference 1988; 15: 50.
  11. Tao M, Bai J, Kohli P, Paris S. SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm. Computer Graphics Forum 2012; 31(2): 345-53.
  12. Forsyth D, Ponce J. Computer Vision: A Modern Approach [In Russian]. – Moscow: “Williams” Publisher; 2004. 928 p.
  13. Gruzman IS et al. Digital image processing in information systems [In Russian]. Novosibirsk: “NGTU” Publisher; 2002. 352 p.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail:journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20