Semantic segmentation and description for video transcoding

Authors:
A. Cavallaro;O. Steiger;T. Ebrahimi
Affiliations:
Inst. of Signal Process., Swiss Fed. Inst. of Technol., Lausanne, Switzerland;Inst. of Signal Process., Swiss Fed. Inst. of Technol., Lausanne, Switzerland;Inst. of Signal Process., Swiss Fed. Inst. of Technol., Lausanne, Switzerland
Venue:
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 3 (ICME '03) - Volume 03
Year:
2003

Citing 0
Cited 2

Computer vision techniques for PDA accessibility of in-house video surveillance

IWVS '03 First ACM SIGMM international workshop on Video surveillance
Energy-aware video streaming with QoS control for portable computing devices

NOSSDAV '04 Proceedings of the 14th international workshop on Network and operating systems support for digital audio and video

Quantified Score

Hi-index	0.01

Visualization

Abstract

We present an automatic content-based video transcoding algorithm, which is based on how humans perceive visual information. The transcoder support multiple video objects and their description. First the video is decomposed into meaningful objects through semantic segmentation. Then the transcoder adapts its behavior to code relevant (foreground) and non-relevant objects differently. Both objects-based and frame-based encoders are combined with semantic segmentation. Experimental results show that the use of semantics and description prior to transcoding reduces the bandwidth requirements and makes it possible to adapt the video representation to limited network and terminal device capabilities still retaining the essential information.