A Novel De-noising Model Based on Independent Component Analysis and Beamlet Transform

Vehicle video key frame processing as an important part of intelligent transportation systems plays a significant role. Traditional vehicle video key frame extraction often has lots of noises, it can't meet the requirements of the recognition and tracking. In this paper, a novel method which is combined independent component analysis with beamlet transform is proposed. Firstly, a random matrix was produce to separate the key frame into a separated image for estimate. Then beamlet transform was applied to optimize the coefficients. At last, the coefficients were selected for image reconstruction by inverse of the beamlet transform. By contrast, this approach could remove more noises and reserve more details, and the efficiency of our approach is better than other traditional de-noising approaches.

[1]  Xiaoming Huo,et al.  Beamlets and Multiscale Image Analysis , 2002 .

[2]  D. Donoho.  Wedgelets: nearly minimax estimation of edges , 1999 .

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  He Zhao,et al.  Video Image Vehicle Detection System for Signaled Traffic Intersection , 2009, 2009 Ninth International Conference on Hybrid Intelligent Systems.

[5]  A. Hyvarinen,et al.  Fast ICA for noisy data using Gaussian moments , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[6]  Erkki Oja,et al.  A fast algorithm for estimating overcomplete ICA bases for image windows , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[7]  P. Comon.  Independent Component Analysis , 1992 .

[8]  Ezzatollah Salari,et al.  Beamlet transform based technique for pavement image processing and classification , 2009, 2009 IEEE International Conference on Electro/Information Technology.

[9]  David L. Donoho,et al.  Fast X-Ray and Beamlet Transforms for Three-Dimensional Data , 2002 .