基于場(chǎng)景模式的立體圖像舒適度客觀評(píng)價(jià)模型
doi: 10.11999/JEIT150267
-
2.
(寧波大學(xué)信息科學(xué)與工程學(xué)院 寧波 315211) ②(寧波工程學(xué)院電子與信息工程學(xué)院 寧波 315211) ③(南京大學(xué)計(jì)算機(jī)軟件新技術(shù)國家重點(diǎn)實(shí)驗(yàn)室 南京 210093)
國家自然科學(xué)基金(U1301257, 61171163, 61271270, 61271021, 61311140262),寧波市自然科學(xué)基金(2013A610113)
Objective Visual Comfort Assessment Model of Stereo Image Based on Scene Mode
-
2.
(Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, China)
The National Natural Science Foundation of China (U1301257, 61171163, 61271270, 61271021, 61311140262), Natural Science Foundation of Ningbo (2013A610113)
-
摘要: 為了預(yù)測(cè)雙目立體圖像內(nèi)容對(duì)視覺健康可能產(chǎn)生的危害,該文提出一種基于場(chǎng)景模式的立體圖像舒適度客觀評(píng)價(jià)模型。根據(jù)場(chǎng)景中前景目標(biāo)和后景區(qū)域相對(duì)于顯示屏幕的凹凸性以及是否處于舒適觀看區(qū),將自然場(chǎng)景抽象為多種場(chǎng)景模式。在模式選擇階段,從視差圖中自適應(yīng)分割出前景目標(biāo)和后景區(qū)域,根據(jù)前、后景的視差角特征確定場(chǎng)景所屬的模式;在建模階段,采用前、后景的視差角特征結(jié)合前景的寬度角和曲折度特征對(duì)各個(gè)場(chǎng)景模式分別進(jìn)行建模,并量化了前、后景視差因素對(duì)視覺舒適度的影響。在IVY數(shù)據(jù)庫上的實(shí)驗(yàn)結(jié)果表明,所提出的模型與主觀感知存在較好的一致性,Pearson相關(guān)系數(shù)高于0.91, Spearman相關(guān)系數(shù)高于0.90, Kendall相關(guān)系數(shù)高于0.74,平均絕對(duì)值誤差低于0.24,均方根誤差低于0.32,與現(xiàn)有的方法相比,該文所提出的模型的評(píng)價(jià)效果更好,更接近于主觀測(cè)試結(jié)果。
-
關(guān)鍵詞:
- 立體圖像 /
- 舒適度評(píng)價(jià) /
- 場(chǎng)景模式 /
- 雙目視覺
Abstract: To predict the effects induced by stereo image content on visual health, a new objective Visual Comfort Assessment (VCA) method of stereo image is proposed based on scene modes. Natural scene is abstracted as multiple scene modes according to two position states of foreground object and background region. One is the convex-concave to screen, and the other is the whether locate on zone of comfortable viewing. In the process of mode selection, disparity map is utilized to segment scene into foreground object and background region adaptively. Then, the scenes mode can be determined by disparity angle features of both foreground object and background region. In the modeling stage, disparity angle features of foreground object and background region, width angle and sinuosity features of foreground object are utilized to build objective VCA models in various scene modes. The experimental results tested on IVY database show that high consistency exists between the proposed model and subjective perception that Pearson linear correlation coefficient is higher than 0.91, Spearman rank-order correlation coefficient is higher than 0.90, Kendall rank-order correlation coefficient is higher than 0.74, Mean Absolute Error (MAE) is lower than 0.24 and Root Mean Squared Error (RMSE) is lower than 0.32. Compared with other existing methods, the proposed model has the better assessment performance and is much closer to the subjective assessment scores.-
Key words:
- Stereo image /
- Visual comfort assessment /
- Scene mode /
- Binocular vision
-
HEWAGE C T E R and MARINI M G. Quality of experience for 3D video streaming[J]. IEEE Communications Magazine, 2013, 51(5): 101-107. 蔣驍辰, 李國平, 王國中, 等. 基于AVS+實(shí)時(shí)編碼的多核并行視頻編碼算法[J]. 電子與信息學(xué)報(bào), 2014, 36(4): 810-816. doi: 103724/SP.J.1146.2013.00845. JIANG Xiaochen, LI Guoping, WANG Guozhong, et al. Multi-core parallel video coding algorithm based on AVS+ real-time encoding[J]. Journal of Electronics Information Technology, 2014, 36(4): 810-816. doi: 103724/SP.J.1146.2013. 00845. KIM D and SOHN K. Visual fatigue prediction for stereoscopic image[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(2): 231-236. LI J, BARKOWSKY M, and CALLET P L. Visual discomfort of stereoscopic 3D videos: Influence of 3D motion[J]. Displays, 2014, 35(1): 49-57. UKAI K and HOWARTH P A. Visual fatigue caused by viewing stereoscopic motion images: Background, theories and observations[J]. Displays, 2008, 29(2): 106-116. PARK J, LEE S, and BOVIK A C. 3D visual discomfort prediction: Vergence, foveation, and the physiological optics of accommodation[J]. IEEE Journal of Selected Topics in Signal Processing, 2014, 8(3): 415-427. RICHARDS W and KAYE M G. Local versus global stereopsis: two mechanisms[J]. Visual Research, 1974, 14(12): 1345-1347. LEE S, JUNG Y J, SOHN H, et al. Effect of stimulus width on the perceived visual discomfort in viewing stereoscopic 3-D-TV[J]. IEEE Transactions on Broadcasting, 2013, 59(4): 580-590. SCHOR C, WOOD I, and OGAWA J. Binocular sensory fusion is limited by spatial resolution[J]. Visual Research, 1984, 24(7): 661-665. SCHOR C, HECKMANN T, and TYLER C W. Binocular fusion limits are independent of contrast, luminance gradient and component phases[J]. Visual Research, 1989, 29(7): 821-835. WOPKING M. Viewing comfort with stereoscopic pictures: an experimental study on the subjective effects of disparity magnitude and depth of focus[J]. Journal of the Society for Information Display, 1995, 3(3): 101-103. 王勤, 王瓊?cè)A, 劉春玲. 視差與空間頻率對(duì)自由立體顯示器觀看舒適度的影響[J]. 光電子 激光, 2012, 23(8): 1604-1608. WANG Qin, WANG Qionghua, and LIU Chunling. Effects of parallax and spatial frequency on visual comfort in autostereoscopic display[J]. Journal of Optoelectronics Laser, 2012, 23(8): 1604-1608. SOHN H, JUNG Y J, LEE S, et al. Predicting visual discomfort using object size and disparity information in stereoscopic images[J]. IEEE Transactions on Broadcasting, 2013, 59(1): 28-37. 姜求平, 邵楓, 蔣剛毅, 等. 基于視覺重要區(qū)域的立體圖像視覺舒適度客觀評(píng)價(jià)方法[J]. 電子與信息學(xué)報(bào), 2014, 36(4): 875-881. doi: 103724/SP.J.1146.2013.00946. JIANG Qiuping, SHAO Feng, JIANG Gangyi, et al. An objective stereoscopic image visual comfort assessment metric based on visual important regions[J]. Journal of Electronics Information Technology, 2014, 36(4): 875-881. doi: 103724/SP.J.1146.2013.00946. KIM H, LEE S, and BOVIK A C. Saliency prediction on stereoscopic videos[J]. IEEE Transactions on Image Processing, 2014, 23(4): 1476-1490. LAMBOOIJ M, IJSSELSTEIJN W, FORTUIN M, et al. Visual discomfort and visual fatigue of stereoscopic displays: a review[J]. Journal of Imaging Science and Technology, 2009, 53(4): 030201. HOLLIMAN N. 3D Display Systems[M]. London: UK, IOP Press, 2004: 7-8. ISO/IEC JTC1/SC29/WG11 M16923. Depth Estimation Reference Software (DERS) 5.0[R]. Xian, China, 2009. WILCOX L M and HESS R F. Dmax for stereopsis depends on size, not spatial frequency content[J]. Visual Research, 1995, 35(9): 1061-1069. -
計(jì)量
- 文章訪問數(shù): 1640
- HTML全文瀏覽量: 187
- PDF下載量: 469
- 被引次數(shù): 0