Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263879
S. Verstockt, P. D. Potter, W. D. Neve, P. Lambert, R. Walle
This paper proposes a generic framework for no-reference quality evaluation of video testimonials. The global quality of the video testimonials is estimated by fusing the individual scores of a selection of spatial, temporal, audio and content-related metrics. Based on the global quality score, feedback is given to the user and the video/audio quality improver can be activated. Experiments on a large set of video testimonials show that the proposed objective evaluation closely matches the perception of users.
{"title":"VITEQ: A generic framework for no-reference quality evaluation of video testimonials","authors":"S. Verstockt, P. D. Potter, W. D. Neve, P. Lambert, R. Walle","doi":"10.1109/QoMEX.2012.6263879","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263879","url":null,"abstract":"This paper proposes a generic framework for no-reference quality evaluation of video testimonials. The global quality of the video testimonials is estimated by fusing the individual scores of a selection of spatial, temporal, audio and content-related metrics. Based on the global quality score, feedback is given to the user and the video/audio quality improver can be activated. Experiments on a large set of video testimonials show that the proposed objective evaluation closely matches the perception of users.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87912670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263839
J. Korhonen, Nino Burini, Junyong You, Ehsan Nadernejad
The typical procedure for evaluating the performance of different objective quality metrics and indices involves comparisons between subjective quality ratings and the quality indices obtained using the objective metrics in question on the known video sequences. Several correlation indicators can be employed to assess how well the subjective ratings can be predicted from the objective values. In this paper, we give an overview of the potential sources for uncertainties and inaccuracies in such studies, related both to the method of comparison, possible inaccuracies in the subjective data, as well as processing of subjective data. We also suggest some general guidelines for researchers to make comparison studies of objective video quality metrics more reliable and useful for the practitioners in the field.
{"title":"How to evaluate objective video quality metrics reliably","authors":"J. Korhonen, Nino Burini, Junyong You, Ehsan Nadernejad","doi":"10.1109/QoMEX.2012.6263839","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263839","url":null,"abstract":"The typical procedure for evaluating the performance of different objective quality metrics and indices involves comparisons between subjective quality ratings and the quality indices obtained using the objective metrics in question on the known video sequences. Several correlation indicators can be employed to assess how well the subjective ratings can be predicted from the objective values. In this paper, we give an overview of the potential sources for uncertainties and inaccuracies in such studies, related both to the method of comparison, possible inaccuracies in the subjective data, as well as processing of subjective data. We also suggest some general guidelines for researchers to make comparison studies of objective video quality metrics more reliable and useful for the practitioners in the field.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77617606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263855
S. Werner, Judith Liebetrau, T. Sporer
Human audio perception is influenced by vision and vice versa. The effect and thresholds of perceptual fusion, for example the ventriloquism-effect, are well investigated for natural listening conditions in the horizontal plane. Modern reproduction approaches for realistic spatial audio, e.g. binaural reproduction, promise more realistic sound reproduction, though, including proper perception of direction, distance, and elevation. This raises the question if the thresholds of perceptual fusion in audio reproduction systems that consider elevation are the same as in natural listening conditions. To estimate the influence of audiovisual discrepancy on vertical sound source localization via binaural headphones, two experiments were conducted. Results show an effect of similar magnitude for the vertical and horizontal plane.
{"title":"Audio-visual discrepancy and the influence on vertical sound source localization","authors":"S. Werner, Judith Liebetrau, T. Sporer","doi":"10.1109/QoMEX.2012.6263855","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263855","url":null,"abstract":"Human audio perception is influenced by vision and vice versa. The effect and thresholds of perceptual fusion, for example the ventriloquism-effect, are well investigated for natural listening conditions in the horizontal plane. Modern reproduction approaches for realistic spatial audio, e.g. binaural reproduction, promise more realistic sound reproduction, though, including proper perception of direction, distance, and elevation. This raises the question if the thresholds of perceptual fusion in audio reproduction systems that consider elevation are the same as in natural listening conditions. To estimate the influence of audiovisual discrepancy on vertical sound source localization via binaural headphones, two experiments were conducted. Results show an effect of similar magnitude for the vertical and horizontal plane.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76900117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263868
M. Quintero, A. Raake
This paper provides the results of a speech quality listening test on Wideband (WB, 500-7000 Hz) and narrowband (NB; 300-3400 Hz) codecs for new wideband-based, so-called “high-definition” (HD Voice) telephony services. Aside of error-free coding, the experiment also evaluated the effects of packet loss and external noise. Unlike “expert vs non-expert differentiation” typical of speech quality research, users are classified into six groups according to demographic characteristics, their attitude towards adopting new technologies and socio-economic information. With this experiment, we want to present how factors beyond the level of prior knowledge of the users affect their perception of quality.
{"title":"Is taking into account the subjects degree of knowledge and expertise enough when rating quality?","authors":"M. Quintero, A. Raake","doi":"10.1109/QoMEX.2012.6263868","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263868","url":null,"abstract":"This paper provides the results of a speech quality listening test on Wideband (WB, 500-7000 Hz) and narrowband (NB; 300-3400 Hz) codecs for new wideband-based, so-called “high-definition” (HD Voice) telephony services. Aside of error-free coding, the experiment also evaluated the effects of packet loss and external noise. Unlike “expert vs non-expert differentiation” typical of speech quality research, users are classified into six groups according to demographic characteristics, their attitude towards adopting new technologies and socio-economic information. With this experiment, we want to present how factors beyond the level of prior knowledge of the users affect their perception of quality.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77898092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263867
B. Goossens, H. Luong, L. Platisa, W. Philips
Objective image quality assessment (QA) is crucial in order to improve imaging systems and image processing techniques. In medical imaging, model observers that estimate signal detectability, have become widespread and promising as a means to avoid costly human observer experiments. However, signal detectability alone does not give the complete picture: one may also be interested in optimizing several independent quality factors (e.g. contrast, spatial resolution, noise). In recent work, we have proposed the channelized joint observer (CJO), to jointly detect and estimate random parametric signals in images, a so-called signal-known-statistically (SKS) detection task. In this paper, we show how the estimation capabilities of the CJO can be exploited to estimate several image quality factors in degraded images, through signal insertion. By fixing the signal detectability, we illustrate how to benefit from the trade-offs that exist between the different quality factors. Our method is in the first place intended to aid medical image reconstruction techniques and medical display design, although the technique can also be useful in a much wider context.
{"title":"Optimizing image quality using test signals: Trading off blur, noise and contrast","authors":"B. Goossens, H. Luong, L. Platisa, W. Philips","doi":"10.1109/QoMEX.2012.6263867","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263867","url":null,"abstract":"Objective image quality assessment (QA) is crucial in order to improve imaging systems and image processing techniques. In medical imaging, model observers that estimate signal detectability, have become widespread and promising as a means to avoid costly human observer experiments. However, signal detectability alone does not give the complete picture: one may also be interested in optimizing several independent quality factors (e.g. contrast, spatial resolution, noise). In recent work, we have proposed the channelized joint observer (CJO), to jointly detect and estimate random parametric signals in images, a so-called signal-known-statistically (SKS) detection task. In this paper, we show how the estimation capabilities of the CJO can be exploited to estimate several image quality factors in degraded images, through signal insertion. By fixing the signal detectability, we illustrate how to benefit from the trade-offs that exist between the different quality factors. Our method is in the first place intended to aid medical image reconstruction techniques and medical display design, although the technique can also be useful in a much wider context.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79980020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263866
Christian Keimel, Julian Habigt, K. Diepold
Video quality evaluation with subjective testing is both time consuming and expensive. A promising new approach to traditional testing is the so-called crowdsourcing, moving the testing effort into the Internet. The advantages of this approach are not only the access to a larger and more diverse pool of test subjects, but also the significant reduction of the financial burden. Recent contributions have also shown that crowd-based video quality assessment can deliver results comparable to traditional testing in some cases. In general, however, new problems arise, as no longer every test detail can be controlled, resulting in less reliable results. Therefore we will discuss in this contribution the conceptual, technical, motivational and reliability challenges that need to be addressed, before this promising approach to subjective testing can become a valid alternative to the testing in standardized environments.
{"title":"Challenges in crowd-based video quality assessment","authors":"Christian Keimel, Julian Habigt, K. Diepold","doi":"10.1109/QoMEX.2012.6263866","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263866","url":null,"abstract":"Video quality evaluation with subjective testing is both time consuming and expensive. A promising new approach to traditional testing is the so-called crowdsourcing, moving the testing effort into the Internet. The advantages of this approach are not only the access to a larger and more diverse pool of test subjects, but also the significant reduction of the financial burden. Recent contributions have also shown that crowd-based video quality assessment can deliver results comparable to traditional testing in some cases. In general, however, new problems arise, as no longer every test detail can be controlled, resulting in less reliable results. Therefore we will discuss in this contribution the conceptual, technical, motivational and reliability challenges that need to be addressed, before this promising approach to subjective testing can become a valid alternative to the testing in standardized environments.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76351897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263876
S. Paris
This short paper presents a perspective plan to build a null reference image quality assessment. Its main goal is to deliver both the objective score and the distortion map for a given distorted image without the knowledge of its reference image.
{"title":"A proposal project for a blind image quality assessment by learning distortions from the full reference image quality assessments","authors":"S. Paris","doi":"10.1109/QoMEX.2012.6263876","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263876","url":null,"abstract":"This short paper presents a perspective plan to build a null reference image quality assessment. Its main goal is to deliver both the objective score and the distortion map for a given distorted image without the knowledge of its reference image.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84490137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263865
Christian Keimel, A. Redl, K. Diepold
The research on video quality metrics depends on the results from subjective testing for both the design and development of metrics, but also for their verification. As it is often too cumbersome to conduct subjective tests, freely available data sets that include both mean opinion scores and the distorted videos are becoming ever more important. While many datasets are already widely available, the majority of these data sets focus on smaller resolutions. We therefore present in this contribution the TUM high definition datasets that include videos in both 1080p25 and 1080p50, encoded with different coding technologies and settings, H.264/AVC and Dirac, but also different presentation devices from reference monitors to home-cinema projectors. Additionally a soundtrack is provided for the home-cinema scenario. The datasets are made freely available for download under a creative commons license.
{"title":"The TUM high definition video datasets","authors":"Christian Keimel, A. Redl, K. Diepold","doi":"10.1109/QoMEX.2012.6263865","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263865","url":null,"abstract":"The research on video quality metrics depends on the results from subjective testing for both the design and development of metrics, but also for their verification. As it is often too cumbersome to conduct subjective tests, freely available data sets that include both mean opinion scores and the distorted videos are becoming ever more important. While many datasets are already widely available, the majority of these data sets focus on smaller resolutions. We therefore present in this contribution the TUM high definition datasets that include videos in both 1080p25 and 1080p50, encoded with different coding technologies and settings, H.264/AVC and Dirac, but also different presentation devices from reference monitors to home-cinema projectors. Additionally a soundtrack is provided for the home-cinema scenario. The datasets are made freely available for download under a creative commons license.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83562566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263882
A. Sackl, Kathrin Masuch, S. Egger, R. Schatz
Within QoE research it has become a generally acknowledged fact that user expectations can have considerable impact on subjective quality perception. In order to empirically quantify this influence we conducted a user study on expectations caused by the type of access network used. Study participants were asked to rate the QoE of various broadband services accessed via Internet connections labeled either as `wireless' or `wireline'. Our results show that for certain applications such as web-browsing, a considerable share of users rated differently in the wireless context than when (supposedly) using wireline, despite otherwise identical underlying technical network conditions. These and other findings demonstrate that dedicated studies on expectations can provide valuable information regarding the nature and impact of hitherto neglected QoE influence factors.
{"title":"Wireless vs. wireline shootout: Howuser expectations influence quality of experience","authors":"A. Sackl, Kathrin Masuch, S. Egger, R. Schatz","doi":"10.1109/QoMEX.2012.6263882","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263882","url":null,"abstract":"Within QoE research it has become a generally acknowledged fact that user expectations can have considerable impact on subjective quality perception. In order to empirically quantify this influence we conducted a user study on expectations caused by the type of access network used. Study participants were asked to rate the QoE of various broadband services accessed via Internet connections labeled either as `wireless' or `wireline'. Our results show that for certain applications such as web-browsing, a considerable share of users rated differently in the wireless context than when (supposedly) using wireline, despite otherwise identical underlying technical network conditions. These and other findings demonstrate that dedicated studies on expectations can provide valuable information regarding the nature and impact of hitherto neglected QoE influence factors.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90133081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-07-05DOI: 10.1109/QoMEX.2012.6263837
N. Staelens, Arnaud Boussaer, N. Vercammen, G. V. hoogenbemt, B. Vermeulen, P. Demeester
Thanks to the availability of 3D-capable televisions and bluray players, 3D content is made accessible in the home. Recently, an extension of the H.264/AVC video coding standard has been defined for encoding 3D video content. This extension, called Multiview Video Coding, allows inter-view prediction resulting in a better compression efficiency. However, due to these inter-view dependencies impairments in one view caused by e.g. packet losses can lead to degradations in other views. Research has already been conducted towards estimating packet loss visibility in H.264/AVC encoded sequences. In this paper, we investigate the possibility of using an existing decision tree-based classifier for estimating impairment visibility in 3D MVC encoded sequences. Our results show that, in the case of losing entire pictures, it is possible to estimate packet loss visibility in 3D MVC encoded sequences with a high accuracy by only taking into account a limited number of parameters.
{"title":"Comparing objective visual quality impairment detection in 2D and 3D video sequences","authors":"N. Staelens, Arnaud Boussaer, N. Vercammen, G. V. hoogenbemt, B. Vermeulen, P. Demeester","doi":"10.1109/QoMEX.2012.6263837","DOIUrl":"https://doi.org/10.1109/QoMEX.2012.6263837","url":null,"abstract":"Thanks to the availability of 3D-capable televisions and bluray players, 3D content is made accessible in the home. Recently, an extension of the H.264/AVC video coding standard has been defined for encoding 3D video content. This extension, called Multiview Video Coding, allows inter-view prediction resulting in a better compression efficiency. However, due to these inter-view dependencies impairments in one view caused by e.g. packet losses can lead to degradations in other views. Research has already been conducted towards estimating packet loss visibility in H.264/AVC encoded sequences. In this paper, we investigate the possibility of using an existing decision tree-based classifier for estimating impairment visibility in 3D MVC encoded sequences. Our results show that, in the case of losing entire pictures, it is possible to estimate packet loss visibility in 3D MVC encoded sequences with a high accuracy by only taking into account a limited number of parameters.","PeriodicalId":6303,"journal":{"name":"2012 Fourth International Workshop on Quality of Multimedia Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85584379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：