Distributed Grayscale Stereo Image Coding with Unsupervised Learning of Disparity

Authors:
David Varodayan;Aditya Mavlankar;Markus Flierl;Bernd Girod
Affiliations:
Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA
Venue:
DCC '07 Proceedings of the 2007 Data Compression Conference
Year:
2007

Citing 0
Cited 7

Wyner-Ziv coding of video with unsupervised motion vector learning

Image Communication
A channel coding approach for human authentication from gait sequences

IEEE Transactions on Information Forensics and Security
Distributed source coding authentication of images with contrast and brightness adjustment and affine warping

PCS'09 Proceedings of the 27th conference on Picture Coding Symposium
Successive refinement based Wyner-Ziv video compression

Image Communication
Biometric template protection in multimodal authentication systems based on error correcting codes

Journal of Computer Security - EU-Funded ICT Research on Trust and Security
Robust distributed multiview video compression for wireless camera networks

IEEE Transactions on Image Processing
Secure image authentication by distibuted source coding using LDPC encoding

Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Distributed compression is particularly attractive for stereo images since it avoids communication between cameras. Since compression performance depends on exploiting the redundancy between images, knowing the disparity is important at the decoder. Unfortunately, distributed encoders cannot calculate this disparity and communicate it. We consider the compression of grayscale stereo images, and develop an Expectation Maximization algorithm to perform unsupervised learning of disparity during the decoding procedure. Towards this, we devise a novel method for joint bitplane distributed source coding of grayscale images. Our experiments with both natural and synthetic 8-bit images show that the unsupervised disparity learning algorithm outperforms a system which does no disparity compensation by between 1 and more than 3 bits/pixel and performs nearly as well as a system which knows the disparity through an oracle.