Transactions of the Korean Society of Automotive Engineers (한국자동차공학회논문집)

The Korean Society of Automotive Engineers (한국자동차공학회)
권호 표지

Intensity Gradients-based Stereo Matching of Road Images

에지정보를 이용한 도로영상의 스테레오 정합

  • 이기용 (전남대학교 산업공학과(자동차연구소)) ;
  • 이준웅 (전남대학교 산업공학과(자동차연구소))
  • Published : 2003.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new binocular stereo correspondence method by maximizing a fitness formulated by integrating two constraints of edge similarity and disparity smoothness simultaneously. The proposed stereopsis focusing to measure distances to leading vehicles on roads uses intensity gradients as matching attribute. In contrast to the previous work of area-based stereo matching, in which matching unit is a pixel, the matching unit of the proposed method becomes an area itself which is obtained by selecting a series of pixels enclosed by two pixels on the left and right boundaries of an object. This approach allows us to cope with real-time processing and to avoid window size selection problems arising from conventional area-based stereo.

Keywords

References

  1. Three-Dimensional Computer Vision A Geometric Viewpoint O. Faugeras
  2. ICCV'95 An Integrated Stereo-based Approach to Automatic Vehicle Guidance Q. Luong;J. Weber;D. Koller;J. Malik
  3. Proc. Intelligent Vehicles'95 A Forward Looking Automotive Radar Sensor P. Ganci;S. Potts;F. Okurowski
  4. IEEE Trans. PAMI v.20 no.11 Intensity and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions G.-Q. Wei;W. Brauer;G. Hirzinger https://doi.org/10.1109/34.730551
  5. Proc. Intelligent Vehicles'2001 Development of Stereo Image Recognition System for ADA K. Hanawa;Y. Sogawa
  6. Proc. Intelligent Vehicles'95 Real-Time Vision for Obstacle Detection Using Linear Cameras Y. Ruichek;J. Postaire
  7. Proc. Intelligent Vehicles'92 Disparity Analysis for Real Time Obstacle Detection by Linear Stereo Vision J.-L. Bruyelle;J.-G. Postaire
  8. Proc. Intelligent Vehicles'93 A New Edge Matching Procedure for Obstacle Detection by Linear Stereo Vision J.-C. Burie;J.-G. Postaire
  9. IEEE Trans. Image Processing v.7 no.1 GOLD : A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection M. Bertozzi;A. Broggi https://doi.org/10.1109/83.650851
  10. Proc. Intelligent Vehicles'95 A Sub-Pixel Vision System for Cost-Effective Intelligent Vehicle Application L. Kaminski;J. Allen;I. Masaki;G. Lemus
  11. Proc. Intelligent Vehicles'96 Fast Stereo Based Object Detection for Stop & Go Traffic U. Frank;I. Kutzbach
  12. Proc. Intelligent Vehicles'95 Texture and Neural Network for Road Segmentation C. Fernandez-Maloigne;W. Bonnet
  13. Journal of Korea Institute of Communication Sciences v.24 no.9B An Efficient Object Detection Algorithm Using Stereo Images J. W. Kim;C. H. Son;J. H. Yi;B. W. Jeon;K. Y. Lee
  14. IEICE TRANS. INF & SYST v.E84-D no.9 A Cumulative Distribution Function of Edge Direction for Road-Lane Detection J. W. Lee;U. K. Yi;K. R. Baek
  15. Digital Image Processing R. C. Gonzalez;R. E. Woods