Stabilizing image sequences taken by the camcorder mounted on a moving vehicle

This paper presents an image stabilization technique which can be used as a very useful on-board unit of a vehicle. The proposed technique includes three steps. First, we detect two lane markings and their corresponding vanishing point from the input image. These two lane markings and their corresponding vanishing point are then used as the bases to calculate the camera motion parameters. The proposed motion estimation process can be used to solve the difficult problems such as feature point extraction and correspondence matching. In addition, the extracted road information can be used to tackle more advanced traffic problems. In the last step of our approach, a motion smoothing process is developed to remove some unwanted motion. This step is fairly important for obtaining very stable image sequences. The experimental results have shown that our method is indeed superb for stabilizing image sequences.

[1]  Man Hyung Lee,et al.  Real-time lane detection for autonomous navigation , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[2]  G. Jiang,et al.  Lane and obstacle detection based on fast inverse perspective mapping algorithm , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[3]  Azriel Rosenfeld,et al.  Image Sequence Stabilization in Real Time , 1996, Real Time Imaging.

[4]  Behrooz Kamgar-Parsi,et al.  A Nonparametric Method for Fitting a Straight Line to a Noisy Image , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Massimo Bertozzi,et al.  Vision-Based Vehicle Guidance , 1997, Computer.

[6]  Sheng-Jyh Wang,et al.  Digital camcorder image stabilizer based on gray-coded bit-plane block matching , 2000, SPIE Photonics Taiwan.

[7]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[8]  Dinggang Shen,et al.  Lane detection using spline model , 2000, Pattern Recognit. Lett..

[9]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[10]  Guangyou Xu,et al.  A stable vision system for moving vehicles , 2000, IEEE Trans. Intell. Transp. Syst..

[11]  Atsushi Morimura,et al.  Automatic image stabilizing system by full-digital signal processing , 1990 .

[12]  Joonki Paik,et al.  An adaptive motion decision system for digital image stabilizer based on edge pattern matching , 1992 .

[13]  Henry Schneiderman,et al.  Visual processing for autonomous driving , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.