ABSTRACT
Video segmentation has become an important and active research area with a large diversity of proposed approaches. Graph-based methods, enabling top performance on recent benchmarks, usually focus on either obtaining a precise similarity graph or designing efficient graph cutting strategies. However, these two components are often conducted in two separated steps, and thus the obtained similarity graph may not be the optimal one for segmentation and this may lead to suboptimal results. In this paper, we propose a novel framework, joint graph learning and video segmentation (JGLVS)}, which learns the similarity graph and video segmentation simultaneously. JGLVS learns the similarity graph by assigning adaptive neighbors for each vertex based on multiple cues (appearance, motion, boundary and spatial information). Meanwhile, the new rank constraint is imposed to the Laplacian matrix of the similarity graph, such that the connected components in the resulted similarity graph are exactly equal to the number of segmentations. Furthermore, JGLVS can automatically weigh multiple cues and calibrate the pairwise distance of superpixels based on their topology structures. Most noticeably, empirical results on the challenging dataset VSB100 show that JGLVS achieves promising performance on the benchmark dataset which outperforms the state-of-the-art by up to 11% for the BPR metric.
- P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. From contours to regions: An empirical evaluation. In CVPR, pages 2294--2301, 2009.Google ScholarCross Ref
- P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 33(5):898--916, 2011. Google ScholarDigital Library
- W. Brendel and S. Todorovic. Video object segmentation by tracking regions. In ICCV, pages 833--840, 2009.Google ScholarCross Ref
- T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. In ECCV, pages 282--295, 2010. Google ScholarDigital Library
- L. Chen, J. Shen, W. Wang, and B. Ni. Video object segmentation via dense trajectories. IEEE Trans. Multimedia, 17(12):2225--2234, 2015.Google ScholarDigital Library
- J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha, and A. Yuille. Efficient multilevel brain tumor segmentation with integrated bayesian model classification. Medical Imaging, IEEE Transactions on, 27(5):629--640, 2008.Google Scholar
- K. Fan. On a Theorem of Weyl Concerning Eigenvalues of Linear Transformations. I. Proceedings of the National Academy of Science, 35:652--655, Nov. 1949.Google ScholarCross Ref
- K. Fragkiadaki and J. Shi. Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement. In CVPR, pages 2073--2080, 2011. Google ScholarDigital Library
- F. Galasso, R. Cipolla, and B. Schiele. Video segmentation with superpixels. In ACCV, 2012. Google ScholarDigital Library
- F. Galasso, M. Keuper, T. Brox, and B. Schiele. Spectral graph reduction for efficient image and streaming video segmentation. In CVPR, 2014. Google ScholarDigital Library
- F. Galasso, N. S. Nagaraja, T. J. Cardenas, T. Brox, and B. Schiele. A unified video segmentation benchmark: Annotation, metrics and analysis. In ICCV, 2013. Google ScholarDigital Library
- L. Gao, J. Song, F. Nie, Y. Yan, N. Sebe, and H. T. Shen. Optimal graph learning with partial tags and multiple features for image and video annotation. In CVPR, pages 4371--4379, 2015.Google ScholarCross Ref
- L. Gao, J. Song, F. Nie, F. Zou, N. Sebe, and H. T. Shen. Graph-without-cut: An ideal graph learning for image segmentation. In AAAI, pages 1188--1194, 2016.Google Scholar
- M. Grundmann, V. Kwatra, M. Han, and I. Essa. Efficient hierarchical graph-based video segmentation. In CVPR, pages 2141--2148, 2010.Google ScholarCross Ref
- A. Jain, S. Chatterjee, and R. Vidal. Coarse-to-fine semantic video segmentation using supervoxel trees. In ICCV, pages 1865--1872, 2013. Google ScholarDigital Library
- H. Jiang, G. Zhang, H. Wang, and H. Bao. Spatio-temporal video segmentation of static scenes and its applications. IEEE Trans. Multimedia, 17(1):3--15, 2015.Google ScholarCross Ref
- M. Keuper, B. Andres, and T. Brox. Motion trajectory segmentation via minimum cost multicuts. In ICCV, 2015. Google ScholarDigital Library
- M. Keuper, B. Andres, and T. Brox. Motion trajectory segmentation via minimum cost multicuts. In ICCV, pages 3271--3279, 2015. Google ScholarDigital Library
- A. Khoreva, F. Galasso, M. Hein, and B. Schiele. Classifier based graph construction for video segmentation. In CVPR, 2015.Google ScholarCross Ref
- C. Li, L. Lin, W. Zuo, S. Yan, and J. Tang. Sold: Sub-optimal low-rank decomposition for efficient video segmentation. In CVPR, 2015.Google Scholar
- B. Liu and X. He. Multiclass semantic video segmentation with object-level active inference. In CVPR, pages 4286--4294, 2015.Google ScholarCross Ref
- B. Luo, H. Li, T. Song, and C. Huang. Object segmentation from long video sequences. In ACM Multimedia, pages 1187--1190, 2015. Google ScholarDigital Library
- T. Ma and L. J. Latecki. Maximum weight cliques with mutex constraints for video object segmentation. In CVPR, pages 670--677, 2012. Google ScholarDigital Library
- N. S. Nagaraja, F. R. Schmidt, and T. Brox. Video segmentation with just a few strokes. In ICCV, pages 3235--3243, 2015. Google ScholarDigital Library
- F. Nie, X. Wang, and H. Huang. Clustering and projected clustering with adaptive neighbors. In SIGKDD, pages 977--986, 2014. Google ScholarDigital Library
- F. Nie, X. Wang, M. I. Jordan, and H. Huang. The constrained laplacian rank algorithm for graph-based clustering. In AAAI, pages 1969--1976, 2016.Google ScholarDigital Library
- P. Ochs and T. Brox. Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions. In ICCV, pages 1583--1590, 2011. Google ScholarDigital Library
- P. Ochs and T. Brox. Higher order motion models and spectral clustering. In CVPR, pages 614--621, 2012. Google ScholarDigital Library
- P. Ochs, J. Malik, and T. Brox. Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell., 36(6):1187--1200, 2014. Google ScholarDigital Library
- S. Paris. Edge-preserving smoothing and mean-shift segmentation of video streams. In ECCV, pages 460--473, 2008. Google ScholarDigital Library
- S. H. Raza, M. Grundmann, and I. A. Essa. Geometric context from videos. In CVPR, pages 3081--3088, 2013. Google ScholarDigital Library
- A. V. Reina, S. Avidan, H. Pfister, and E. L. Miller. Multiple hypothesis video segmentation from superpixel flows. In ECCV, pages 268--281, 2010. Google ScholarDigital Library
- F. Shen, C. Shen, Q. Shi, A. van den Hengel, Z. Tang, and H. T. Shen. Hashing on nonlinear manifolds. IEEE Trans. Image Processing, 24(6):1839--1851, 2015.Google ScholarDigital Library
- J. Son, I. Jung, K. Park, and B. Han. Tracking-by-segmentation with online gradient boosting decision tree. In ICCV, 2015. Google ScholarDigital Library
- J. Song, Y. Yang, Z. Huang, H. T. Shen, and J. Luo. Effective multiple feature hashing for large-scale near-duplicate video retrieval. IEEE Trans. Multimedia, 15(8):1997--2008, 2013. Google ScholarDigital Library
- H. Wang and C. Schmid. Action recognition with improved trajectories. In ICCV, 2013. Google ScholarDigital Library
- Y. Wang, J. Liu, Y. Li, and H. Lu. Semi- and weakly- supervised semantic segmentation with deep convolutional neural networks. In ACM Multimedia, pages 1223--1226, 2015. Google ScholarDigital Library
- C. Xu, C. Xiong, and J. J. Corso. Streaming hierarchical video segmentation. In ECCV, pages 626--639, 2012. Google ScholarDigital Library
- X. Yao, J. Han, G. Cheng, and L. Guo. Semantic segmentation based on stacked discriminative autoencoders and context-constrained weakly supervised learning. In ACM Multimedia, pages 1211--1214, 2015. Google ScholarDigital Library
- S. Yi and V. Pavlovic. Multi-cue structure preserving MRF for unconstrained video segmentation. In ICCV, 2015. Google ScholarDigital Library
- C.-P. Yu, H. Le, G. Zelinsky, and D. Samaras. Efficient video segmentation using parametric graph partitioning. In ICCV, 2015. Google ScholarDigital Library
- V. Zografos, R. Lenz, E. Ringaby, M. Felsberg, and K. Nordberg. Fast segmentation of sparse 3d point trajectories using group theoretical invariants. In ACCV, pages 675--691, 2014.Google Scholar
Index Terms
- Joint Graph Learning and Video Segmentation via Multiple Cues and Topology Calibration
Recommendations
An integrated similarity metric for graph-based color image segmentation
Graph-based method has become one of the major trends in image segmentation. In this paper, we focus on how to build the affinity matrix which is one of the key issues in graph-based color image segmentation. Four different metrics are integrated in ...
Improved graph-cut segmentation for ultrasound liver cyst image
An optimal contour segmentation for ultrasonic liver cyst image is presented through combining graph-based method with particle swarm optimization (PSO) in this paper. After automatic selecting the region of interest (ROI) for ultrasonic liver cyst ...
A graph-based approach for spatio-temporal segmentation of coronary arteries in X-ray angiographic sequences
The segmentation and tracking of coronary arteries (CAs) are critical steps for the computation of biophysical measurements in pediatric interventional cardiology. In the literature, most methods are focused on either segmenting the vessel lumen or on ...
Comments