张荣国,贾玉闪,胡静,刘小君,李晓明

• 1:太原科技大学计算机与技术学院
• 2:合肥工业大学机械工程学院

摘要(Abstract)：

使用静态空间特征通常无法得到准确的视频显著性目标对象,提出了超像素梯度流场与元胞自动机融合的视频图像显著性检测方法。首先,使用SLIC方法将视频帧分割成超像素,在超像素级上运用光流梯度和颜色梯度生成一个时空梯度函数,由时空梯度得到新的梯度流场值,将视频中运动信息充分利用起来;其次,在视频帧超像素图像上使用卷积神经网络得到其深度特征,通过元胞自动机使这些深度特征依自定义规则更新出粗略显著图,然后将梯度流场显著图与元胞自动机粗略显著图融合得到最终的显著图;最后,在ViSal数据集上、采用5种评估指标、与现有的4种方法进行对比实验,结果表明本文方法在动态视频图像显著性检测中有好的表现。

关键词(KeyWords)： 超像素;梯度流场;元胞自动机;视频图像

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(51875152);; 山西省自然科学基金(201801D121134);; 太原科技大学博士科研启动基金(20202057)

作者(Author): 张荣国,贾玉闪,胡静,刘小君,李晓明

参考文献(References)：

• [1] REN Z,GAO S,CHIA L T,et al.Region-Based saliency detection and its application in object recognition[J].IEEE Trans.on Circuits and Systems for Video Technology,2014,24(5):769-779.
• [2] LEI J J,WU M,ZHANG C Q,et al.Depth-Preserving stereo image retargeting based on pixel fusion[J].IEEE Trans.on Multimedia,2017,19(7):1442-1453.
• [3] MAHADEVAN V,VASCONCELOS N.Spatiotemporal saliency in dynamic scenes[J].IEEE Trans.On Pattern Analysis and Machine Intelligence,2010,32(1):171-177.
• [4] CUI X Y,LIU Q S,METAXAS D N.Temporal spectral residual:Fast motion saliency detection[C]//Proc.of the ACM MM.2009:617-620.
• [5] CHANG LIU,PONG C.YUEN,GUOPING QIU.Object motion detection using information theoretic spatio-temporal saliency[J].Pattern Recognition,2009,42(11):2897-2906.
• [6] XI T,ZHAO W,WANG H,LIN W S.Salient object detection with spatiotemporal background priors for video.IEEE Trans.On Image Processing,2017,26(7):3425-3436.
• [7] JIANG L,XU M,LIU T,et al.DeepVS:A Deep Learning Based Video Saliency Prediction Approach[C]//Proc.of the ECCV2018,Munich,Germany,Berlin:Springer:1-16.
• [8] JIANG L,XU M,WANG Z.SIGAL L.DeepVS2.0:A Saliency-Structured Deep Learning Method for Predicting Dynamic Visual Attention[J].International Journal of Computer Vision,2021,129(2):203-224.
• [9] 张荣国，刘小君，董磊，等.物体轮廓形状超像素图割快速提取方法[J].模式识别与人工智能，2015,28(4):344-353.
• [10] 裴高阳，张荣国，胡静，等.改进的 SLIC 超像素彩色图像分割方法[J].太原科技大学学报，2016,37(3):168-175.
• [11] BROX T,MALIK J.Large displacement optical flflow:Descriptor matching in variational motion estimation[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2011,33(3):500-513.
• [12] WANG W G,SHEN J B,SHAOL.Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement[J].IEEE Transactions on Image Processing,2015,24(11):4185-4196.
• [13] GUO C,MA Q,ZHANG L.Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform[C]//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition.US:IEEE CVPR,2008:24-26.
• [14] SEO H J,MILANFAR P.Static and space-time visual saliency detection by self-resemblance[J].Journal of Vision,2009,9(12):15-15.
• [15] ESA RAHTU,JUHO KANNALA,MIKKO SALO,et al.Segmenting Salient Objects from Images and Videos[C]//European Conference on Computer Vision.Springer,Berlin,Heidelberg,2010.
• [16] LIU Z,ZHANG X,LUO S,et al.Superpixel-Based Spatiotemporal Saliency Detection[J].IEEE Transactions on Circuits & Systems for Video Technology,2014,24(9):1522-1540.
• [17] 张荣国，贾玉闪，胡静，等.超像素内容感知先验的多尺度贝叶斯显著性检测方法[J].电子学报，2020,48(4):1509-1515.