一种基于交替凸优化的视频对象分割算法
|
摘要
现有视频对象分割方案多数存在应用场景受限、运动背景过分割等问题,为此,提出一种可从视频序列中自动检测重要对象的无监督视频对象分割算法。从前景和背景概率分布的角度引入马尔可夫能量、时空能量和对抗能量。将视频对象分割问题建模为基于3种混合能量最小化的非凸优化问题,利用基于交替凸优化的方法将其分解为2个二次规划问题。采用前向-反向传递策略,以充分利用时域相关性从而提高对象分割的可靠性。结合多种视频数据集进行仿真,结果表明,与其他最新的视频对象分割算法相比,该算法的分割性能有明显提高。
There are some deficiencies while using existing schemes,such as limited application scenes and over segmentation of motion background.An unsupervised video object segmentation algorithm is proposed,which can automatically detect important objects from video sequences.Markov energy,time and space energy,as well as antagonism energy are introduced from the view of the foreground and background probability distribution.Then,the problem of detecting important objects from the background is modeled as a non convex optimization problem based on the mixed energy minimization,and a method based on Alternation Convex Optimization(ACO) is proposed to decompose the problem into two kinds of two quadratic programming problems.In order to make full use of time-domain correlation to improve the reliability of object segmentation,a forward-backward deliver strategy is also adopted.A comprehensive simulation is carried out based on a variety of video datasets.Experimental results show that the performance of the algorithm in this paper is significantly better than the other latest video object segmentation algorithms.
There are some deficiencies while using existing schemes,such as limited application scenes and over segmentation of motion background.An unsupervised video object segmentation algorithm is proposed,which can automatically detect important objects from video sequences.Markov energy,time and space energy,as well as antagonism energy are introduced from the view of the foreground and background probability distribution.Then,the problem of detecting important objects from the background is modeled as a non convex optimization problem based on the mixed energy minimization,and a method based on Alternation Convex Optimization(ACO) is proposed to decompose the problem into two kinds of two quadratic programming problems.In order to make full use of time-domain correlation to improve the reliability of object segmentation,a forward-backward deliver strategy is also adopted.A comprehensive simulation is carried out based on a variety of video datasets.Experimental results show that the performance of the algorithm in this paper is significantly better than the other latest video object segmentation algorithms.
引文
[1] WANG W,SHEN J,YANG R,et al.Saliency-aware video object segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(1):20-33.
[2] 苏亮亮,唐俊,梁栋,等.基于最大化子模和RRWM的视频协同分割[J].自动化学报,2016,42(10):1532-1541.
[3] SPAMPINATO C,PALAZZO S,GIORDANO D.Gamifying video object segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(10):1942-1958.
[4] ENDRES I,HOIEM D.Category independent object proposals[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:575-588.
[5] CHOCKALINGAM P,PRADEEP N,BIRCHFIELD S.Adaptive fragments-based tracking of non-rigid objects using level sets[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2009:1530-1537.
[6] Barnich O,DROOGENBROECK M V.ViBe:a universal background subtraction algorithm for video sequences [J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[7] BROX T,MALIK J.Object segmentation by long term analysis of point trajectories[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:282-295.
[8] GIORDANO D,MURABITO F,PALAZZO S,et al.Superpixel-based video object segmentation using perceptual organization and location prior [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:4814-4822.
[9] OCHS P,BROX T.Higher order motion models and spectral clustering[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:614-621.
[10] WANG W,SHEN J,PORIKLI F.Saliency-aware geodesic video object segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3395-3402.
[11] LEE Y J,KIM J,GRAUMAN K.Key-segments for video object segmentation[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEE Press,2011:1995-2002.
[12] MA T,LATECKI L J.Maximum weight cliques with mutex constraints for video object segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:670-677.
[13] PAPAZOGLOU A,FERRARI V.Fast object segmentation in unconstrained video[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:1777-1784.
[14] ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[15] ZHANG D,JAVED O,SHAH M.Video object segmentation through spatially accurate and temporally dense extraction of primary object regions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:628-635.
[16] BAMPIS C G,MARAGOS P,BOVIK A C.Graph-driven diffusion and random walk schemes for image segmentation[J].IEEE Transactions on Image Processing,2017,26(1):35-50.
[17] BANJAC G,GOULART P,STELLATO B,et al.Infeasibility detection in the alternating direction method of multipliers for convex optimization[J].IEEE Transactions on Power Electronics,2017,32(5):4007-4020.
[18] GRANT M,BOYD S,YE Y.CVX:Matlab software for disciplined convex programming[M].Berlin,Germany:Springer,2008:109-120.
[19] KANDA N,LU X,KAWAI H.Maximum-a-posteriori- based decoding for end-to-end acoustic models[J].IEEE/ACM Transactions on Audio,Speech,and Language Proessing,2017,25(5):1023-1034.
[2] 苏亮亮,唐俊,梁栋,等.基于最大化子模和RRWM的视频协同分割[J].自动化学报,2016,42(10):1532-1541.
[3] SPAMPINATO C,PALAZZO S,GIORDANO D.Gamifying video object segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(10):1942-1958.
[4] ENDRES I,HOIEM D.Category independent object proposals[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:575-588.
[5] CHOCKALINGAM P,PRADEEP N,BIRCHFIELD S.Adaptive fragments-based tracking of non-rigid objects using level sets[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2009:1530-1537.
[6] Barnich O,DROOGENBROECK M V.ViBe:a universal background subtraction algorithm for video sequences [J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[7] BROX T,MALIK J.Object segmentation by long term analysis of point trajectories[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:282-295.
[8] GIORDANO D,MURABITO F,PALAZZO S,et al.Superpixel-based video object segmentation using perceptual organization and location prior [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:4814-4822.
[9] OCHS P,BROX T.Higher order motion models and spectral clustering[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:614-621.
[10] WANG W,SHEN J,PORIKLI F.Saliency-aware geodesic video object segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3395-3402.
[11] LEE Y J,KIM J,GRAUMAN K.Key-segments for video object segmentation[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEE Press,2011:1995-2002.
[12] MA T,LATECKI L J.Maximum weight cliques with mutex constraints for video object segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:670-677.
[13] PAPAZOGLOU A,FERRARI V.Fast object segmentation in unconstrained video[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:1777-1784.
[14] ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[15] ZHANG D,JAVED O,SHAH M.Video object segmentation through spatially accurate and temporally dense extraction of primary object regions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:628-635.
[16] BAMPIS C G,MARAGOS P,BOVIK A C.Graph-driven diffusion and random walk schemes for image segmentation[J].IEEE Transactions on Image Processing,2017,26(1):35-50.
[17] BANJAC G,GOULART P,STELLATO B,et al.Infeasibility detection in the alternating direction method of multipliers for convex optimization[J].IEEE Transactions on Power Electronics,2017,32(5):4007-4020.
[18] GRANT M,BOYD S,YE Y.CVX:Matlab software for disciplined convex programming[M].Berlin,Germany:Springer,2008:109-120.
[19] KANDA N,LU X,KAWAI H.Maximum-a-posteriori- based decoding for end-to-end acoustic models[J].IEEE/ACM Transactions on Audio,Speech,and Language Proessing,2017,25(5):1023-1034.