Framework for measurement of the intensity of motion activity of video segments

Peker, Kadir A.; Divakaran, Ajay

doi:10.1016/j.jvcir.2004.04.007

Cited by 20 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Peker et al's [12] analysis of MPEG motion vectors suggests the variance of the motion vector magnitudes, similar to that provided in MPEG-7, is promising as a representative measure of visual motion. However, in our analysis the linear correlation with motion as perceived by the users is weak, only 0.51.…”

Section: Motionmentioning

confidence: 85%

“…Peker and Dviakaran [12] present a framework for comparing the performance of motion activity with respect to a "ground truth" based on subjective ratings. They focus analysis on how effective MPEG motion vectors are in representing visual motion, showing that average motion vector length is not as effective as measures that discard some motion vectors (using the largest remaining) or that compute the variance of the motion vector magnitudes (as in MPEG-7).…”

Section: Measuring Motion and Scene Complexitymentioning

confidence: 99%

See 1 more Smart Citation

Motion and scene complexity for streaming video games

Claypool

2009

Proceedings of the 4th International Conference on Foundations of Digital Games

View full text Add to dashboard Cite

This work provides detailed measurements of the motion and scene complexity for a wide variety of video games. Novel algorithms to measure motion and scene complexity are presented and then applied to over twenty-five games from a range of game genres. Direct comparisons of motion and scene complexity are made to traditional video, with differences highlighted in order to help thin client systems perform better when streaming video games. Preliminary performance measurements of current thin client systems are presented, evaluating the efficacy of streaming video games in the context of the motion and scene complexity measurements provided.

show abstract

Section: Motionmentioning

confidence: 85%

Section: Measuring Motion and Scene Complexitymentioning

confidence: 99%

Motion and scene complexity for streaming video games

Claypool

2009

Proceedings of the 4th International Conference on Foundations of Digital Games

View full text Add to dashboard Cite

show abstract

“…Various statistical analyses of the motion vector magnitude, which is available from the compressed MPEG video, have been proposed for extracting the motion level, see for instance [22], [23]. In these analyses the mean, variance, standard deviation or the maximum of the motion vector magnitudes is quantized into nonuniform ranges corresponding to each motion activity level.…”

Section: Extracting Mpeg-7 Motion Intensity Descriptormentioning

confidence: 99%

“…Hence, small motion vector magnitudes are matched with low activity level between successive frames. The extension of this procedure to implementation for video shots that contain a number of frames can be achieved by averaging these motion vector magnitudes in the entire shot [23].…”

Section: Extracting Mpeg-7 Motion Intensity Descriptormentioning

confidence: 99%

“…A number of video shots of various activity levels were displayed, accompanied by the anticipated activity levels. We followed the experimental guidelines presented in [23], [24]. Since we used a large ground truth, the assessments with human subjects were conducted in several sessions of about 20 min each over a few days.…”

Section: Extracting Mpeg-7 Motion Intensity Descriptormentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Video Transmission Schemes Using MPEG-7 Motion Intensity Descriptor

Lotfallah

Reisslein

Panchanathan

2006

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-A variety of error resilience and scalable coding techniques have recently been proposed to facilitate the delivery of video over best-effort networks; a common drawback of these techniques is reduced compression efficiency. Also, MPEG-7 descriptors have recently been developed for the purpose of indexing. In this paper, we propose to employ MPEG-7 descriptors to improve the quality of the video delivered over best-effort networks. In particular, we propose a video transmission system that uses the motion activity descriptors to ensure robust video transmission. A novel motion activity extraction technique is proposed, which relies on a neural network approach. By considering several low-level visual features, our proposed extraction approach achieves high consistency with subjective evaluations of motion activities. In order to demonstrate the benefits of the proposed transmission system, we develop a selective packet dropping scheme that can be applied in case of network congestion. Simulations demonstrate that the reconstruction quality of the proposed congestion scheme can surpass conventional schemes by 1.2 dB. The network performance of the proposed transmission system when video sequences are coded into single layer or scalable layers is presented. We also present a transcoding scheme that achieves the optimal reconstructed quality by exploiting the motion activities of the underlying video sequence.

show abstract