深圳大学学报理工版

提出一种基于人类视觉灵敏度与空间加权离散余弦系数差异度的显著性检测模型.该模型将图像块的离散余弦低频系数作为其特征向量,以取代颜色和亮度等基本特征.每个图像块的显著性不仅计算与其余所有图像块的空间加权特征差异度之和,还用人类视觉灵敏度加权.通过与6种典型的显著性检测模型在3个眼动跟踪数据集上进行对比实验,结果表明,该模型显著性检测性能优于所有对比算法.此外,将该显著性检测模型用于新一代高效率视频编码(high efficiency video coding,HEVC)中也获得了很好的效果.

A new saliency detection model based on human visual sensitivity and spatial weighted dissimilarity of discrete cosine transformation(DCT)coefficients is proposed. The DCT coefficients were used as the feature vector to replace the color and intensity of image patches to compute contrast. The salient value for each image patch was calculated not only by the dissimilarity between the DCT coefficients of this patch and other patches in the whole image but also by the dissimilarity in weighted human visual sensitivity. The experimental results show that the proposed saliency detection model outperforms other state-of-the-art detection models in three eye-tracking datasets. In addition, the proposed model is also applied to new video coding technology, namely high efficiency video coding(HEVC), and achiev better performance than conventional algorithms.

引言
1 图像显著性定义
2 特征提取与显著性计算
3 结果与分析
4 结语

图1 显著性检测流程示意图<br/>Fig.1 (Color online)Saliency detecting flow diagram

图1 显著性检测流程示意图
Fig.1 (Color online)Saliency detecting flow diagram

图2 观看距离和视网膜离心距离关系[13]<br/>Fig.2 Relationship between viewing distance and retina eccentricity[13]

图2 观看距离和视网膜离心距离关系[13]
Fig.2 Relationship between viewing distance and retina eccentricity[13]

图3 输入图像与其对应显著图<br/>Fig.3 (Color online)Input images and saliency maps

图3 输入图像与其对应显著图
Fig.3 (Color online)Input images and saliency maps

图4 不同特征维度与不同图像块尺度时的NSS得分曲线<br/>Fig.4 (Color online)NSS cure with different feature d and image patch size s

图4 不同特征维度与不同图像块尺度时的NSS得分曲线
Fig.4 (Color online)NSS cure with different feature d and image patch size s

图5 在人眼跟踪数据库上的显著图主观对比<br/>Fig.5 (Color online)Subjective comparison with visual saliency in the eye-tracking database

图5 在人眼跟踪数据库上的显著图主观对比
Fig.5 (Color online)Subjective comparison with visual saliency in the eye-tracking database

表1 在3个眼动跟踪数据库上的AUC均值和标准差结果<br/>Table 1 Mean and standard deviation of AUC in three eye-tracking datasets

表1 在3个眼动跟踪数据库上的AUC均值和标准差结果
Table 1 Mean and standard deviation of AUC in three eye-tracking datasets

图6 3个眼动跟踪数据库上的NSS和CC均值对比<br/>Fig.6 (Color online)Mean of NSS and CC on three eye-tracking datasets

图6 3个眼动跟踪数据库上的NSS和CC均值对比
Fig.6 (Color online)Mean of NSS and CC on three eye-tracking datasets

图7 编码模型P-R曲线对比图<br/>Fig.7 (Color online)P-R cure of video coding model

图7 编码模型P-R曲线对比图
Fig.7 (Color online)P-R cure of video coding model

[1] Grill-Spector K,Malach R.The human visual cortex[J].Annual Review Neuroscience,2004,27(1):649- 677.
[2] Wang Z,Lu L G,Bovik A C.Foveation scalable video coding with automatic fixation selection[J].IEEE Transactions on Image Processing,2003,12(2):243-254.
[3] Rutishauser U,Walther D,Koch C,et al.Is bottom-up attention useful for object recognition?[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington:IEEE Press,2004,2:37- 44.
[4] Han Junwei,Ngan K N,Li Mingjing,et al.Unsupervised extraction of visual attention objects in color images[J].IEEE Transactions on Circuits and Systems for Video Technology,2006,16(1):141-145.
[5] Treisman A M, Gelade G.A feature-integration theory of attention[J].Cognitive Psychology,1980,12(1):97-136.
[6] Harel J,Koch C,Perona P.Graph-based visual saliency[C]// Advances in Neural Information Processing Systems.Cambridge(USA):MIT Press,2007:545-552.
[7] Bruce N D B,Tsotsos J K.Saliency based on information maximization[C]// Advances in Neural Information Processing Systems.Cambridge(USA):MIT Press,2006,18:155-163.
[8] Goferman S,Zelnik-Manor L,Tal A.Context-aware saliency detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):1915-1926.
[9] Guo Chenlei,Ma Qi,Zhang Liming.Spatio-temporal saliency detection using phase spectrum of quaternion Fourier transform[C]// IEEE Conference on Computer Vision and Pattern Recognition.Alaska(USA):IEEE Press.2008:1-8.
[10] Murray N,Vanrell M,Otazu X,et al.Saliency estimation using a non-parametric low-level vision model[C]// IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Providence(USA):IEEE Press,2011:433- 440.
[11] Hou X D,Harel J,Koch C.Image signature: highlighting sparse salient regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):194-201.
[12] Ahmed N,Natarajan T,Rao K R.Discrete cosine transform[J].IEEE Transactions on Computers,1974,23(1):90-93.
[13] Geisler W S,Perry J S.Real-time foveated multiresolution system for low-bandwidth video communication[C]// SPIE Proceedings in Human Vision and Electronic Imaging.[S.l.]:SPIE,1998:293-305.
[14] Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259.
[15] Abutaleb A,Eloteifi A.Automatic thresholding of gray-level pictures using 2D entropy[J]. Computer Vision,Graphics,and Image Processing,1989,47(1):22-32.
[16] Jain A K.Fundamentals of digital image processing[M].Noida(India):Pearson Education India,2007.
[17] Li J,Levine M D,An X,et al.Visual saliency based on scale-space analysis in the frequency domain[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(4): 996-1010.
[18] Xu Juan,Jiang Ming,Wang Shuo,et al.Predicting human gaze beyond pixels[J].Journal of Vision,2014,14(1): 28-1-28-20.
[19] Judd T,Ehinger K,Durand F,et al.Learning to predict where humans look[C]// The 12th International Conference on Computer Vision.Kyoto(Japan):IEEE Press,2009:2106-2113.
[20] Borji A,Tavakoli H R,Sihite D N,et al.Analysis of scores,datasets,and models in visual saliency prediction[C]// In Proceedings of International Conference on Computer Vision(ICCV).Sydney(Australia):IEEE Press,2013:921-928,
[21] Sullivan G J,Topiwala P N,Luthra A.The H.264/AVC advanced video coding standard:overview and introduction to the fidelity range extensions[C]// SPIE Conference on Applications of Digital Image Processing XXVII.[S.l.]:SPIE,2004,5558:454- 474.
[22] Sullivan G J,Ohm J-R,Han W-J,et al.Overview of the high efficiency video coding(HEVC)standard[J].IEEE Transactions on Circuits and Systems for Video Technology,2012,22(12):1649-1668.
[23] Hadizadeh H,Bajic I V.Saliency-aware video compression[J].IEEE Transactions on Image Processing,2014,23(1):19-33.
[24] Chen Z,Guillemot C.Perceptually-friendly H.264/AVC video coding based on foveated just-noticeable-distortion model[J].IEEE Transactions on Circuits and Systems for Video Technology,2010,20(6):806-819.
[25] Hadizadeh H,Enriquez M J,Bajic I V.Eye-tracking database for a set of standard video sequences[J].IEEE Transactions on Image Processing,2012,21(2):898-903.
[26] Li Z C,Qin S Y,Itti L.Visual attention guided bit allocation in video compression[J].Image and Vision Computing,2011,29(1): 1-14.

备注

引言

1 图像显著性定义

2 特征提取与显著性计算

3 结果与分析

4 结语

期刊信息

备注

引言

1 图像显著性定义

2 特征提取与显著性计算

3 结果与分析

4 结 语

期刊信息

4 结语