Content-based selective enhancement for streaming video

Schaar, Mihaela van der; Lin, Yun-Ting

doi:10.1109/icip.2001.958659

Cited by 17 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in a video conference case, the human face is of more significance for the attendees. So, in the contentbased transmission model, face detection is performed first to find out the enhancement focus and combined with SE to give a content-based encoding [23]. The term "content-based" is defined from the viewpoint of the content-provider.…”

Section: Evolution Of Transmission Modelmentioning

confidence: 99%

See 1 more Smart Citation

Interactive Content-aware Video Streaming System with Fine Granularity Scalability

Chang

Hsu

Chao

et al. 2006

J VLSI Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

Abstract. Video streaming with varying transmission bandwidth is becoming increasingly important. In this paper, an interactive video streaming system is proposed. Fine Granularity Scalability (FGS) is applied to be the streaming video format. The computational complexity of FGS coding is analyzed to explore an efficient FGS implementation. A new transmission model is proposed for the realization of a content-aware video streaming. At encoder side, the current MPEG-4 FGS coding flow is reordered such that the picture-level maximum can be acquired in advance and bit-plane data can be dynamically adapted. With these proposed hardware-oriented optimization approaches, a hardwired FGS block-level processing core is proposed to achieve a cost-effective solution to FGS implementation. The streaming server can adaptively decide quality-enhanced region by selective enhancement according to both object information from encoding side and user-defined region from receiver side. From the simulation results, it's demonstrated that the proposed approach can provide better quality in users' interest regions with no bit-rate or complexity overhead.

show abstract

Section: Evolution Of Transmission Modelmentioning

confidence: 99%

“…The application for FGS in wireless video streaming is discussed in [21] and [22]. In [23] and [24], the content-aware feature for FGS is proposed and experimented. However, the FGS performance is improved with the penalty of much higher complexity.…”

Section: Introductionmentioning

confidence: 99%

Interactive Content-aware Video Streaming System with Fine Granularity Scalability

Chang

Hsu

Chao

et al. 2006

J VLSI Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

show abstract

“…For tracking complex nonrigid shaped objects, contour representation is used [10]. The most popular pixel domain tracing techniques apply object segmentation and tracking by utilising the object models and ontologies [11], colour information [12], texture features [13], optical flow [14], semantic and probabilistic decomposition of the video frames with learning capabilities [15], temporal comparisons between consecutive frames [16] or a combination of the previous techniques. These techniques imply a high computational burden, due to requirement to initially decode every frame in the sequence and perform pixel domain analysis.…”

Section: Pixel Domain Algorithmsmentioning

confidence: 99%

Object tracking in surveillance videos using compressed domain features from scalable bit-streams

Mehmood

Mrak

Calic

et al. 2009

Signal Processing: Image Communication

View full text Add to dashboard Cite

“…MPEG-4 selective enhancement [5] is employed in the Enhancement Layer of MPEG-4 FGS in order to stream higher quality video within selected image regions. However, MPEG-4 selective enhancement does not provide quality improvement for the Base Layer.…”

Section: Introductionmentioning

confidence: 99%

FMOE-MR: content-driven multiresolution MPEG-4 fine grained scalable layered video encoding

Chattopadhyay¹,

Luo²,

Bhandarkar³

et al. 2007

SPIE Proceedings

View full text Add to dashboard Cite

The MPEG-4 Fine Grained Scalability (FGS) profile aims at scalable layered video encoding, in order to ensure efficient video streaming in networks with fluctuating bandwidths. In this paper, we propose a novel technique, termed as FMOE-MR, which delivers significantly improved rate distortion performance compared to existing MPEG-4 Base Layer encoding techniques. The video frames are re-encoded at high resolution at semantically and visually important regions of the video (termed as Features, Motion and Objects) that are defined using a mask (FMO-Mask) and at low resolution in the remaining regions. The multiple-resolution re-rendering step is implemented such that further MPEG-4 compression leads to low bit rate Base Layer video encoding. The Features, Motion and Objects Encoded-MultiResolution (FMOE-MR) scheme is an integrated approach that requires only encoder-side modifications, and is transparent to the decoder. Further, since the FMOE-MR scheme incorporates "smart" video preprocessing, it requires no change in existing MPEG-4 codecs. As a result, it is straightforward to use the proposed FMOE-MR scheme with any existing MPEG codec, thus allowing great flexibility in implementation. In this paper, we have described, and implemented, unsupervised and semi-supervised algorithms to create the FMO-Mask from a given video sequence, using state-of-the-art computer vision algorithms.

show abstract

Content-based selective enhancement for streaming video

Cited by 17 publications

References 12 publications

Interactive Content-aware Video Streaming System with Fine Granularity Scalability

Interactive Content-aware Video Streaming System with Fine Granularity Scalability

Object tracking in surveillance videos using compressed domain features from scalable bit-streams

FMOE-MR: content-driven multiresolution MPEG-4 fine grained scalable layered video encoding

Contact Info

Product

Resources

About