Low-Complexity Heterogeneous Video Transcoding Using Data Mining

Fernández–Escribano, Gerardo; Bialkowski, J.; Gámez, José A.; Kalva, Hari; Cuenca, Pedro; Orozco-Barbosa, Luis; Kaup, André

doi:10.1109/tmm.2007.911838

Cited by 28 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Support vector machines (SVM [14]) have been applied for transcoding H.264/AVC bitstreams [8]. Decision trees (DT [15]) are also widely used for transcoding [9]- [12]. More recently, the linear discriminant function has been used for transcoding a video from H.264/AVC to the high efficiency video coding (HEVC) standard [13], [16].…”

Section: Related Workmentioning

confidence: 99%

Performance analysis of machine learning for arbitrary downsizing of pre-encoded HEVC video

Van

Praeter

Wallendael

et al. 2015

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Performance analysis of machine learning for arbitrary downsizing of pre-encoded HEVC video

Van

Praeter

Wallendael

et al. 2015

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

“…The transcoding process should perform the conversion without making necessary the complete process of decoding and re-encoding [4]. Transcoding has been a hot research topic in the last years in the framework of MPEG-2 to H.264/AVC [5] or H.263 to H.264/AVC transcoders [6], also between H.264-extensions such as H.264/AVC to SVC [7] or, even, between Distributed Video Coding (DVC) and H.264/AVC [8].…”

Section: Related Workmentioning

confidence: 99%

Fast quadtree level decision algorithm for H.264/HEVC transcoder

Díaz-Honrubia

Martínez

Puerto

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…The main goal of this idea is to reduce the time taken by this mode decision process, trying to narrow down the set of MB partitions to be checked by the encoder by using a decision tree generated by data mining techniques. ML techniques have been used in some transcoding approaches [5,18], although these approaches focus on transcoding from several different standards to H.264/AVC. In this paper, ML has been used to reduce the complexity of the mode decision process in the proposed H.264/AVC-to-SVC transcoder.…”

Section: Observations and Motivationmentioning

confidence: 99%

H.264/AVC-to-SVC temporal video transcoder for video broadcasting in wireless networks

Garrido-Cantos

Cock

Martínez

et al. 2014

Multimed Tools Appl

View full text Add to dashboard Cite

Over the last few decades multimedia usage has changed dramatically, with networks and terminals of diverse bandwidths and capabilities coexisting. To ensure a good quality of experience, this diverse environment requires adaptability of the video stream. If video streams were compressed using Scalable Video Coding (SVC) schemes, they would be able to adapt to these heterogeneous networks and a wide range of terminals. However, since the majority of multimedia contents are compressed using H.264/AVC, they cannot benefit from this scalability. This paper makes some proposals for improving a temporal H.264/AVC-to-SVC video transcoder so that it can convert an H.264/AVC bitstream without scalability to scalable bitstreams with temporal scalability. The idea behind the proposed transcoder is to accelerate interprediction, focusing on reducing the coding complexity of the mode decision and motion estimation tasks of the encoder stage by using information available after the H.264/AVC decoding stage. To accelerate the mode decision task, a decision tree for narrowing down the Macroblock (MB) types to be checked by the SVC encoder has been developed. On the other hand, to accelerate the motion estimation task, a reduced area is created dynamically for every MB and sub-MB. Moreover, time savings increase considerably when both proposals are adjusted to work together, as opposed to doing so in an isolated way. The results show that when our joint proposal is applied, the complexity is reduced by 98 % while maintaining coding efficiency

show abstract

Low-Complexity Heterogeneous Video Transcoding Using Data Mining

Cited by 28 publications

References 19 publications

Performance analysis of machine learning for arbitrary downsizing of pre-encoded HEVC video

Performance analysis of machine learning for arbitrary downsizing of pre-encoded HEVC video

Fast quadtree level decision algorithm for H.264/HEVC transcoder

H.264/AVC-to-SVC temporal video transcoder for video broadcasting in wireless networks

Contact Info

Product

Resources

About