Abstract | ||
---|---|---|
This paper addresses the problem of processing motion-JPEG video data in the compressed domain. The operations covered are those where a pixel in the output image is an arbitrary linear combination of pixels in the input image, which includes convolution, scaling, rotation, translation, morphing, de-interlacing, image composition, and transcoding. This paper further develops an approximation technique calledcondensationto improve performance and evaluates condensations in terms of processing speed and image quality. Using condensation, motion-JPEG video can be processed at near real-time rates on current generation workstations. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1006/rtim.1996.0002 | Real-Time Imaging |
Keywords | Field | DocType |
image quality,near real time,motion jpeg | Computer vision,Video post-processing,Feature detection (computer vision),Image texture,Computer science,Image processing,Image quality,JPEG,Artificial intelligence,Image restoration,Digital image processing | Journal |
Volume | Issue | ISSN |
2 | 1 | 1077-2014 |
Citations | PageRank | References |
10 | 1.66 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Brian C. Smith | 1 | 654 | 183.66 |
Lawrence A. Rowe | 2 | 1465 | 689.61 |