The TUM high definition video datasets

Keimel, Christian; Redl, Arne; Diepold, Klaus

doi:10.1109/qomex.2012.6263865

Cited by 40 publications

(28 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus we have in total 20 data points, each representing a combination of coding condition and content for the TUM1080p50 data set. The data set is available at [317] and for more information I refer to [136,266].…”

Section: Tum1080p50mentioning

confidence: 99%

See 1 more Smart Citation

Design of Video Quality Metrics with Multi-Way Data Analysis

Keimel¹

2016

T-Labs Series in Telecommunication Services

Self Cite

View full text Add to dashboard Cite

Video quality metrics determine the visual quality of distorted video sequences by using prediction models based on objectively measurable features and are therefore an alternative to the time-consuming and costly subjective video quality assessment. In the conventional design approach to video quality metrics, however, the temporal nature of video is often considered only inadequately due to the use of temporal pooling in the prediction process. Moreover, this approach also often requires knowledge about the human visual system that is not readily or only partly available. In this thesis, I therefore propose a data driven design methodology using multi-way data analysis for the design of video quality metrics. This data driven design approach not only requires no detailed knowledge of the human visual system, but also allows for a proper consideration of the temporal nature of video by using a three-way prediction model, corresponding to the three-way structure of video. Using two simple example metrics, I demonstrate that this purely data driven approach not only outperforms video quality metrics in the state-of-the-art that are often highly optimised towards specific properties of the human visual system, but also that multi-way data analysis methods outperform the combination of two-way data analysis methods and temporal pooling.iii

show abstract

Section: Tum1080p50mentioning

confidence: 99%

“…In the end, however, only the data points relating to the H.264/AVC encoded video sequences can be used and thus only a subset of 32 data points will be used in the performance comparison in this thesis. The data set is available at [317] and for more information I refer to [136,139]. …”

Section: Tum1080p25mentioning

confidence: 99%

Design of Video Quality Metrics with Multi-Way Data Analysis

Keimel¹

2016

T-Labs Series in Telecommunication Services

Self Cite

View full text Add to dashboard Cite

show abstract

“…We gratefully acknowledge the work of TU München and their high-definition video dataset [7] as well as the JIKU video dataset [8] which provided different datasets of high-quality video. In addition we have recorded 349 own video sequences during a musical festival and a football match.…”

Section: Evaluated Videosmentioning

confidence: 99%

“…The JIKU dataset allows us to have a valid and realistic set of recordings of a live event that show quite well realistic degradations, such as shakes or occlusions. But as our as well as the JIKU dataset do not show all degradations and according parameters in the required fine granularity, we decided to artificially impair videos from the TU München dataset [7]. The traces of potential shaking or occurrence of occlusions were retrieved from the JIKU dataset [8] and our own videos using video analysis and applied them to the TU München dataset using frame manipulation methods.…”

Section: Evaluated Videosmentioning

confidence: 99%

The influence of camera shakes, harmful occlusions and camera misalignment on the perceived quality in user generated video

Wilk

Effelsberg

2014

2014 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Video sharing sites such as Youtube are prominent examples for the increasing demand of private camera owners to record, save and share their real life experiences as videos. Whereas professional video productions use advanced camera equipment in a controlled environment with skilled cameramen, User-Generated Video (UGV) differs significantly in regard of equipment, skill and thus in video quality. In this work we focus on a detailed analysis of the effects of camera shakes, harmful occlusions as well as a possible misalignment between the recording camera and the scene, on the resulting video quality. In contrast, most of the video quality discussion in the literature has focused on encoding artifacts and other compression problems. Our data was systematically gathered using large crowdsourcing experiments over three genres of video, and it was validated in a controlled lab setting. Our results show that even minimal camera shaking as well as occlusions lead to a significant reduction in the perceived video quality.

show abstract

“…All in all, we have 20 different sequences with corresponding subjective visual quality as mean opinion scores (MOS) based on a discrete voting scale from 0 to 10. For more information we refer to [11] and the results of this dataset are also discussed in detail in [12]. …”

Section: Data Setmentioning

confidence: 99%

Saliency based video quality prediction using multi-way data analysis

Redl

Keimel

Diepold

2013

2013 Fifth International Workshop on Quality of Multimedia Experience (QoMEX)

Self Cite

View full text Add to dashboard Cite

Saliency information allows us to determine which parts of an image or video frame attracts the focus of the observer and thus where distortions will be more obvious. Using this knowledge and saliency thresholds, we therefore combine the saliency information generated by a computational model and the features extracted from the H.264/AVC bitstream, and use the resulting saliency-weighted features in the design of a video quality metric with multi-way data analysis. We used two different multi-way methods, the two dimensional principal component regression (2D-PCR) and multi-way partial least squares regression (PLSR) in the design of a no-reference video quality metric, where the different saliency levels are considered as an additional direction. Our results show that the consideration of the the saliency information leads to more stable models with less parameters in the model and thus the prediction performance increases compared to metrics without saliency information for the same number of parameters.

show abstract

The TUM high definition video datasets

Cited by 40 publications

References 10 publications

Design of Video Quality Metrics with Multi-Way Data Analysis

Design of Video Quality Metrics with Multi-Way Data Analysis

The influence of camera shakes, harmful occlusions and camera misalignment on the perceived quality in user generated video

Saliency based video quality prediction using multi-way data analysis

Contact Info

Product

Resources

About