Performance evaluation of super-resolution reconstruction from video. Caner, G, Tekalp, A., & Heinzelman, W In Vasudev, B, Hsing, T., Tescher, A., & Ebrahimi, T, editors, IMAGE AND VIDEO COMMUNICATIONS AND PROCESSING 2003, PTS 1 AND 2, volume 5022, of PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE), pages 177-185, 2003. Soc Imaging Sci & Technol; SPIE. Conference on Image and Video Communications and Processing, SANTA CLARA, CA, JAN 21-24, 2003
doi  abstract   bibtex   
Several algorithms have been proposed to enhance the resolution of a reference image from multiplestill images or video that may be captured/stored in raw or compressed format. This paper provides a thorough study of how the performance of the projections onto convex sets (POCS) method is affected by camera parameters, quantization of the pixel-values, motion estimation errors, and quantization in the DCT-domain (when compressed data is used). Experimental results are provided to evaluate the practical applicability of super-resolution reconstruction in various scenarios. It has been observed that the quality of the resolution enhancement depends on the quantization of pixel intensity values in the RGB (uncompressed) or YUV (compressed) domains by the video capture device, as well as the accuracy of the estimated motion parameters between successive frames.
@inproceedings{ ISI:000183315800019,
Author = {Caner, G and Tekalp, AM and Heinzelman, W},
Editor = {{Vasudev, B and Hsing, TR and Tescher, AG and Ebrahimi, T}},
Title = {{Performance evaluation of super-resolution reconstruction from video}},
Booktitle = {{IMAGE AND VIDEO COMMUNICATIONS AND PROCESSING 2003, PTS 1 AND 2}},
Series = {{PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
   (SPIE)}},
Year = {{2003}},
Volume = {{5022}},
Pages = {{177-185}},
Note = {{Conference on Image and Video Communications and Processing, SANTA
   CLARA, CA, JAN 21-24, 2003}},
Organization = {{Soc Imaging Sci \& Technol; SPIE}},
Abstract = {{Several algorithms have been proposed to enhance the resolution of a
   reference image from multiplestill images or video that may be
   captured/stored in raw or compressed format. This paper provides a
   thorough study of how the performance of the projections onto convex
   sets (POCS) method is affected by camera parameters, quantization of the
   pixel-values, motion estimation errors, and quantization in the
   DCT-domain (when compressed data is used). Experimental results are
   provided to evaluate the practical applicability of super-resolution
   reconstruction in various scenarios. It has been observed that the
   quality of the resolution enhancement depends on the quantization of
   pixel intensity values in the RGB (uncompressed) or YUV (compressed)
   domains by the video capture device, as well as the accuracy of the
   estimated motion parameters between successive frames.}},
DOI = {{10.1117/12.476358}},
ISSN = {{0277-786X}},
ISBN = {{0-8194-4822-2}},
Unique-ID = {{ISI:000183315800019}},
}

Downloads: 0