Video Data Compression Using Multilayer Perceptrons
In this paper, we present a neural network-based approach to the problem of video compression. In particular, an MPEG-like encoder is proposed, in which a novel scheme is proposed for a very low cost motion compensation of the frames which lie in between I or P frames. To code the error information of the inter coded frames, several multilayer perceptron are utilised, which operate on both two- and three-dimensional data.
Simulation results are also presented, which show the peculiar characteristics of the proposed approach.
KeywordsHide Layer Motion Vector Hide Node Image Compression Motion Compensation
Unable to display preview. Download preview PDF.
- 1.G. W. Cottrell, P. Munro, and D. Zipser, “Image compression by back propagation: an example of extensional programming,” in Models of cognition: a review of cognition science ( N. E. Sharkey, ed.), NJ: Norwood, 1989.Google Scholar
- 2.M. Mougeot, R. Azencott, and B. Angeniol, “A study of image compression with backpropagation,” in NATO ASI Series, Vol. F 68, Neurocomputing ( F. F. Soulie and J. Herault, eds.), Berlin Heidelberg: Springer-Verlag, 1990.Google Scholar
- 4.ISO/IEC, “Coding of moving pictures and associated audio.” ISO/IEC JTC 1/SC 29 WG 11, MPEG 92/No 245, July 1992.Google Scholar
- 6.J. R. Jain and A. K. Jain, “Displacement measurement and its application in interframe image coding,” IEEE Trans. Commun., vol. COM-29, pp. 1799–1806, Dec. 1981.Google Scholar
- 8.R. P. Lippmann, “An introduction to computing with neural nets,” IEEE ASSP Magazine, pp. 4–21, Apr. 1987.Google Scholar