基于視頻自然統(tǒng)計(jì)特性的無參考移動(dòng)終端視頻質(zhì)量評(píng)價(jià)

施文娟; 孫彥景; 左海維; 曹起

doi:10.11999/JEIT170165

基于視頻自然統(tǒng)計(jì)特性的無參考移動(dòng)終端視頻質(zhì)量評(píng)價(jià)

doi: 10.11999/JEIT170165

2.
(中國(guó)礦業(yè)大學(xué)信息與控制工程學(xué)院徐州 221008)

基金項(xiàng)目:

國(guó)家自然科學(xué)基金項(xiàng)目(51504214, 61771417)，江蘇省自然科學(xué)基金(BK20150204)，國(guó)家重點(diǎn)研發(fā)計(jì)劃(2016YFC0801403)，江蘇省重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(BE2015040)，中國(guó)博士后基金(2015M 581884)

計(jì)量
- 文章訪問數(shù): 1228
- HTML全文瀏覽量: 237
- PDF下載量: 172
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-02-27
- 修回日期: 2017-10-23
- 刊出日期: 2018-01-19

No-reference Mobile Video Quality Assessment Based on Video Natural Statistics

2.
(School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, China)

Funds:

The National Natural Science Foundation of China (51504214, 61771417), The Natural Science Foundation of Jiangsu Province (BK20150204), The National Key Research and Development Program (2016YFC0801403), The Fundamental Research and Development Foundation of Jiangsu Province (BE2015040), China Postdoctoral Science Foundation (2015M 581884)

摘要

摘要: 針對(duì)無線網(wǎng)絡(luò)中壓縮編碼及無線丟包等因素對(duì)移動(dòng)終端視頻的降質(zhì)影響，在分析視頻相鄰幀差信號(hào)空-時(shí)感知統(tǒng)計(jì)特性的基礎(chǔ)上，該文提出一種基于視頻自然統(tǒng)計(jì)特性的無參考移動(dòng)終端視頻質(zhì)量評(píng)價(jià)(NMVQA)算法。進(jìn)行視頻幀差空-時(shí)自然統(tǒng)計(jì)規(guī)律分析，確定移動(dòng)終端視頻失真類型對(duì)視頻相鄰幀差系數(shù)統(tǒng)計(jì)特性的影響；計(jì)算水平、垂直、主對(duì)角線和副對(duì)角線方向的幀差相鄰系數(shù)乘積分布參數(shù)的時(shí)域統(tǒng)計(jì)特性；以多尺度幀差相鄰系數(shù)的時(shí)域統(tǒng)計(jì)特性相關(guān)程度來衡量移動(dòng)終端視頻失真程度。在LIVE移動(dòng)視頻數(shù)據(jù)庫上的實(shí)驗(yàn)結(jié)果表明，該文所提算法的結(jié)果與主觀評(píng)價(jià)具有較好的一致性，能夠準(zhǔn)確反映人類對(duì)視頻失真程度的視覺感知效果，可為實(shí)時(shí)在線調(diào)節(jié)信源碼率和無線信道參數(shù)提供參考依據(jù)。
- 視頻質(zhì)量評(píng)價(jià) /
- 無參考 /
- 移動(dòng)終端視頻 /
- 自然統(tǒng)計(jì)特性 /
- 相鄰幀差
Abstract: Considering the influence of compression and wireless channel packet-loss on mobile video quality in wireless network, analyzing the space-time perceptual statistics of the differences between video adjacent frames, a No-reference Mobile Video Quality Assessment (NMVQA) algorithm is proposed based on video natural statistics. First, the influences of various video distortion type on the statistical characteristics of difference coefficients between video adjacent frames are analyzed in terms of the natural statistical regularities of video frame difference. Second, the temporal change of the distribution parameters with respect to the products of adjacent frame differences computed along horizontal, vertical and diagonal spatial orientations are calculated. Finally, the distortion degree of mobile video is measured by the correlation between the multi-scale temporal changes of statistical characteristics of difference coefficients between video adjacent frames. Experimental results in the LIVE mobile video database show that NMVQA is well consistent with subjective assessment results, and can reflect human subjective feeling well. NMVQA can evaluate the performance of real-time online adjustment of the source rate and wireless channel parameters.
- Video quality assessment /
- No-reference /
- Mobile video /
- Natural statistics /
- Adjacent frame difference

HTML全文

參考文獻(xiàn)(18)

SHAO Hua, WEN Xiangming, LU Zhaoming, et al. Reduced frame set on wireless distorted video for quality assessment[J]. The Journal of China Universities of Posts and Telecommunications, 2016, 23(4): 77-82. doi: 10.1016/S1005- 8885(16)60048-1.

LIU Yan and LEE Jack Y B. Streaming variable bitrate video over mobile networks with predictable performance[C]. IEEE Wireless Communications and Networking Conference, Doha, Qatar, 2016: 1-7. doi: 10.1109/WCNC.2016.7565108.

MOORTHY A K, CHOI L K, BOVIK A C, et al. Video quality assessment on mobile devices: Subjective, behavioral and objective studies[J]. IEEE Journal of Selected Topics in Signal Processing, 2012, 6(6): 652-671. doi: 10.1109/JSTSP. 2012.2212417.

SOUNDARARAJAN R and BOVIK A C. Video quality assessment by reduced reference spatio-temporal entropic differencing[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(4): 684-694. doi: 10.1109/ TCSVT.2012.2214933.

SAAD M A, BOVIK A C, and CHARRIER C. Blind prediction of natural video quality[J]. IEEE Transactions on Image Processing, 2014, 23(3): 1352-1365. doi: 10.1109/TIP. 2014.2299154.

MITTAL A, SAAD M A, and BOVIK A C. A completely blind video integrity oracle[J]. IEEE Transactions on Image Processing, 2016, 25(1): 289-300. doi: 10.1109/TIP.2015. 2502725.

HSIAO Yimao, LEE Jengfarn, CHEN Jaishiarng, et al. H.264 video transmissions over wireless networks: challenges and solutions[J]. Computer Communications, 2011, 34: 1661-1672. doi: 10.1016/j.comcom.2011.03.016.

YU Qingqing and SUN Songlin. Mobile video perception assessment model based on QoE[C]. 16th International Symposium on Communications and Information Technologies, Qingdao, China, 2016: 642-645. doi: 10.1109/ ISCIT.2016.7751712.

陳希宏, 金躍輝, 楊談. 3G網(wǎng)絡(luò)中移動(dòng)視頻質(zhì)量評(píng)估模型的研究[J]. 計(jì)算機(jī)科學(xué), 2015, 42(9): 86-93.

CHEN Xihong, JIN Yuehui, and YANG Tan. Study on quality assessment model for mobile videos over 3G network [J]. Computer Science, 2015, 42(9): 86-93.

SONG Wei and TJONDRONEGORO D W. Acceptablity- based QoE models for mobile video[J]. IEEE Transactions on Multimedia, 2014, 3(16): 738-750. doi: 10.1109/TMM.2014. 2298217.

OLSON S and GROSSBERG S. A neural network for the develop of simple and complex cell receptive fields within cortical maps of orientation and ocular dominance[J]. Neural Networks, 1998, 11(2): 189-208. doi: 10.1016/s0893-6080(98) 00003-3.

FREEMAN J and SIMONCELLI E P. Metamers of the ventral stream[J]. Nature Neuroscience, 2011, 14(9): 1195-1201. doi: 10.1038/nn.2889.

LASMAR N E, STITOU Y, and BERTHOUMIEU Y. Multiscale skewed heavy tailed model for texture analysis[C]. 2009 IEEE International conference on Image Processing, Cairo, Egypt, 2009: 2281-2284. doi: 10.1109/icip.2009. 5414404.

MITTAL A, MOOTHY A K, and BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12): 4695-4708. doi: 10.1109/tip.2012.2214050.

孫彥景, 楊玉芬, 劉東林, 等. 基于內(nèi)在生成機(jī)制的多尺度結(jié)構(gòu)相似性圖像質(zhì)量評(píng)價(jià)[J]. 電子與信息學(xué)報(bào), 2016, 38(1): 127-134. doi: 10.11999/JEIT150616.

SUN Yanjing, YANG Yufen, LIU Donglin, et al. Multiple- scale structural similarity image quality assessment based on internal generative mechanism[J]. Journal of Electronics Information Technology, 2016, 38(1): 127-134. doi: 10.11999 /JEIT150616.

WANG Z, LU L, and BOVIK A C. Image quality assessment: from error measurement to structural similarity[J]. IEEE Signal Process Letter, 2004, 13(4): 600-612. doi: 10.1109/tip. 2003.819861.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)