摘要: The research of traditional stereo vision is mainly based on static cameras. As PTZ (Pan-Tilt-Zoom) cameras are able to obtain multi-view-angle and multi-resolution information, they have received more concern in both real application. Stereo using dual-PTZ-camera system, compared with dual-static-camera much challenging. Dual-PTZ-camera system could extensive scope application by combining the merits PTZ-camera. However, few works about were found literature. In this paper, we propose a novel rectification method for which essential greatly increase efficiency matching. inconsistence intensities two camera images, caused camera's self-adjustment intensity under different illumination condition view fields, also challenge order deal problem, two-step matching strategy. Experimental results show that our approach well.
acm.org
elsevier.com
sci-hub.se 参考文章(25)
Sudipta Sinha, Marc Pollefeys, Towards calibrating a pan-tilt-zoom camera network ,(2004)
S Rougeaux, Alex Zelinsky, H. Truong, Samer Abdallah, A Novel Mechanism for Stereo Active Vision international conference on robotics and automation. ,(2000)
David A. Forsyth, Jean Ponce, Computer Vision: A Modern Approach ,(2002)
Marc Pollefeys, Sudipta Sinha, Iso-disparity Surfaces for General Stereo Configurations european conference on computer vision. pp. 509- 520 ,(2004) , 10.1007/978-3-540-24672-5_40
Richard I Hartley, None, Theory and Practice of Projective Rectification International Journal of Computer Vision. ,vol. 35, pp. 115- 127 ,(1999) , 10.1023/A:1008115206617
Sang-Cheol Park, Seong-Whan Lee, Fast Distance Computation with a Stereo Head-Eye System Lecture Notes in Computer Science. pp. 434- 443 ,(2000) , 10.1007/3-540-45482-9_44
Brian Scassellati, A Binocular, Foveated Active Vision System Massachusetts Institute of Technology. ,(1998) , 10.21236/ADA455741
Andrew Dankers, Nick Barnes, Alexander Zelinsky, None, Active Vision - Rectification and Depth Mapping international conference on robotics and automation. ,(2004)
S. Roy, J. Meunier, I.J. Cox, Cylindrical rectification to minimize epipolar distortion computer vision and pattern recognition. pp. 393- 399 ,(1997) , 10.1109/CVPR.1997.609355
Sang De Ma, A self-calibration technique for active vision systems international conference on robotics and automation. ,vol. 12, pp. 114- 120 ,(1996) , 10.1109/70.481755