Temporal quality assessment for mobile videos

Chan, An; Pande, Amit; Baik, Eilwoo; Mohapatra, Prasant

doi:10.1145/2348543.2348572

Cited by 25 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We therefore, use no-reference model, which is oblivious of the original video signal, to evaluate the quality of video telephony. In our model we use no-reference spatial metrics -Blocking & Blurring [27] to evaluate the spatial component, and use no-reference temporal metric -Temporal Variation Metric (TVM) [2] to evaluate the temporal component of the video.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Temporal information is the measure of the motion of objects in a video or movement of background including scene changes. We use the recently proposed metric TVM [2], to measure the temporal information of the video conversations. Due to the specific scenarios and video content, i.e.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…video telephony, are studied in this paper, we modified TVM so that it can measure the temporal impairment. According to [2], TVM is for temporal information measurement due to its high correlation with optical information. Numerically, TVM is calculated as log of mean square value of difference between two consecutive frames (F p−1 and F p ) of the video (measured in dB).…”

Section: Evaluation Metricsmentioning

confidence: 99%

See 2 more Smart Citations

QoE prediction model for mobile video telephony

Jana

Chan

Pande

et al. 2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Interactive online video applications, such as video telephony, are known for their vulnerability to network condition. With the increasing usage of hand-held wireless mobile devices, which are capable of capturing and processing good quality videos, combined with the flexibility in an end-user movements have added new challenging factors for application providers and network operators. These factors affect the perceived video quality of mobile video telephony applications, unlike conventional video telephony over desktop computers. We investigate this impact on video quality of mobile video telephony in varying network conditions and end-users movement scenarios. Based on 312 live traces, we quantitatively derive the correlation between the perceived video quality and the network Quality of Service (QoS) and user mobility. With the results, we develop a Quality of Experience (QoE) prediction model for mobile video telephony using Support Vector Regression techniques. The prediction models display ≈ 0.8 pearson correlation with experimental Multimed Tools Appl data. Our methodology and findings can be used to guide the video telephony application providers and network operators to work towards satisfying end-user experience.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

QoE prediction model for mobile video telephony

Jana

Chan

Pande

et al. 2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this case, a logarithmic function is first applied on all 26 features to cater for the non-linearity of the HVS and suprathreshold effects [7], [12], [13], [19], such that a feature X becomes log(1+X). The resultant features are then passed through a SVR module to yield the Natural Video Statistical Model.…”

Section: Poolingmentioning

confidence: 99%

“…However, recent research has demonstrated that the exploitation of temporal information is necessary if the performance of VQA metrics is to be made robust [1], [4], [7], [9], [17], [18]. State-of-the-art metrics designed specifically for VQA that consider temporal and/or motion information include the full-reference MOtion-based Video Integrity Evaluation (MOVIE) algorithm [1], which is primarily based on Gabor coefficients obtained via linear decomposition.…”

Section: Introductionmentioning

confidence: 99%

A no-reference video quality metric using a Natural Video Statistical Model

Galea

Farrugia

2015

IEEE EUROCON 2015 - International Conference on Computer as a Tool (EUROCON)

View full text Add to dashboard Cite

Abstract-The demand for high quality multimedia content is increasing rapidly, which has resulted in service providers employing Quality of Service (QoS) strategies to monitor the quality of delivered content. However, the QoS parameters commonly used do not correlate well with the actual quality perceived by the end-users. Numerous objective video quality assessment (VQA) metrics have been proposed to address this problem. However, most of these metrics rely on the availability of additional information from the original undistorted video to perform adequately, which will increase the bandwidth required. This paper presents a No-Reference (NR) VQA algorithm, which extracts a Natural Video Statistical Model using both spatial and temporal features to model the quality experienced by the endusers without needing additional information from the transmitter. These features are based on the observation that the statistics of natural scenes are regular on pristine content but are significantly altered in the presence of distortion. The proposed method achieves a Spearman Rank Order Correlation Coefficient (SROCC) of 0.8161 with subjective data, which is statistically identical and sometimes superior to existing state-ofthe-art full and reduced reference VQA metrics.

show abstract