Abstract
Computer vision models are commonly defined for maximum constrained submodular functions lies at the core of low-level and high-level models. In such that, the pixels that are to be grouped or segmenting moving object remains a challenging task. This paper proposes a joint framework for maximizing submodular energy subject to a matroid constraint using Deep Submodular Function (DSF) optimization approximately to solve the weighted MAX-SAT (Maximum Satisfiability) problem and a new trajectory clustering method called Simple Slice Linear clustering (SSLIC) and motion cue method for trajectory clustering and motion segmentation. In this objective function, the illustrative trajectories of a small number are selected automatically by deep submodular maximization. Although, the exploitation of monotone and submodular properties are further maximized and the complexity is reduced by a continuous greedy algorithm. The bound guarantees a fully sliced curve of (1- S/e) to (1–1/e) with less running time. Lastly, the motion is segmented by the motion cue method to accurately differentiate the set of frames for different scenes. Experiments on the Hopkins 155, Berkley Motion Segmentation (BMS) and FBMS-59 datasets display the trajectory clustering and motion segmentation result over its superior performance with respect to 14 quality evaluation metrics. Hence the simulation result shows that the proposed joint framework attains better performance than existing methods on trajectory clustering and motion segmentation task.
Similar content being viewed by others
References
Buchbinder N, Feldman M, Seffi J, Schwartz R (2015) A tight linear time (1/2)-approximation for unconstrained submodular maximization. SIAM J Comput 44(5):1384–1402
Calinescu G, Chekuri C, Pal M, Vondrák J (2011) Maximizing a monotone submodular function subject to a matroid constraint. SIAM J Comput 40(6):1740–1766
Lin H, Bilmes J (2011) A class of submodular functions for document summarization. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (pp. 510-520)
Narasimhan M, Jojic N, Bilmes JA (2006) Q-clustering. In: Advances in Neural Information Processing Systems (pp. 979-986)
Liu D, Zhou KS, Bernhardt D, Comaniciu D (2010) Search strategies for multiple landmark detection by submodular maximization. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2831-2838). IEEE
Zhu F, Jiang Z, Shao L (2014) Submodular object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2457-2464)
Xu J, Mukherjee L, Li Y, Warner J, Rehg JM, Singh V (2015) Gaze-enabled egocentric video summarization via constrained submodular maximization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2235-2244)
Gygli M, Grabner H, Van Gool L (2015) Video summarization by learning submodular mixtures of objectives. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3090-3098)
Pokutta S, Singh M, Torrico A (2018) Efficient algorithms for robust submodular maximization under matroid constraints. arXiv preprint arXiv:1807.09405
de Veciana G, Hashemi A, Vikalo H (2019) Stochastic-greedy++: closing the optimality gap in exact weak submodular maximization. arXiv preprint arXiv:1907.09064
Mirzasoleiman B, Badanidiyuru A, Karbasi A (2016) Fast constrained submodular maximization: personalized data summarization. In: ICML (pp. 1358-1367)
Chakrabarti A, Kale S (2015) Submodular maximization meets streaming: Matchings, matroids, and more. Math Program 154(1–2):225–247
Badanidiyuru A, Mirzasoleiman B, Karbasi A, Krause A (2014) Streaming submodular maximization: massive data summarization on the fly. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 671-680)
Bateni M, Esfandiari H, Mirrokni V (2018) Optimal distributed submodular optimization via sketching. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 1138-1147)
Huang CC, Kakimura N, Yoshida Y (2017) Streaming algorithms for maximizing monotone submodular functions under a knapsack constraint. In: Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2017). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik
Norouzi-Fard A, Tarnawski J, Mitrović S, Zandieh A, Mousavifar A, Svensson O (2018) Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams. arXiv preprint arXiv:1808.01842
Agrawal S, Shadravan M, Stein C (2018) Submodular secretary problem with shortlists. arXiv preprint arXiv:1809.05082
Kumar R, Moseley B, Vassilvitskii S, Vattani A (2015) Fast greedy algorithms in mapreduce and streaming. ACM Trans Parallel Comput (TOPC) 2(3):1–22
Yu Q, Xu EL, Cui S (2016) Streaming algorithms for news and scientific literature recommendation: submodular maximization with a d-knapsack constraint. arXiv preprint arXiv:1603.05614
Iyer R, Bilmes J (2012) Algorithms for approximate minimization of the difference between submodular functions, with applications. arXiv preprint arXiv:1207.0560
Lin H, Bilme J (2010) Multi-document summarization via budgeted maximization of submodular functions. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (pp. 912–920)
Buchbinder N, Feldman M, Schwartz R (2017) Comparing apples and oranges: query trade-off in submodular maximization. Math Oper Res 42(2):308–329
Kuhnle A (2019) Interlaced greedy algorithm for maximization of submodular functions in nearly linear time. Adv Neural Inf Process Syst 2374-2384
Brox T, Malik J (2010) Object segmentation by long term analysis of point trajectories. In European conference on computer vision (pp. 282-295). Springer, Berlin, Heidelberg
Shi F, Zhou Z, Xiao J, Wu W (2013) Robust trajectory clustering for motion segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 3088-3095)
Wang G (2016) Robust structure from motion in the presence of outliers and missing data. arXiv preprint arXiv:1609.02638
Zhang Y, Luo B, Zhang L (2017) Permutation preference based alternate sampling and clustering for motion segmentation. IEEE Signal Processing Letters 25(3):432–436
Liu L, Zhou F, Bai XR, Tao ML, Zhang ZJ (2016) Joint cross-range scaling and 3D geometry reconstruction of ISAR targets based on factorization method. IEEE Trans Image Process 25(4):1740–1750
Zhang CC, Liu ZL (2017) Prior-free dependent motion segmentation using Helmholtz-Hodge decomposition based object-motion oriented map. J Comput Sci Technol 32(3):520–535
Chen W, Zhang E, Zhang Z (2016) A Laplacian structured representation model in subspace clustering for enhanced motion segmentation. Neurocomputing. 208:174–182
Chen L, Shen J, Wang W, Ni B (2015) Video object segmentation via dense trajectories. IEEE Trans Multimedia 17(12):2225–2234
Lee CM, Cheong LF (2017) Minimal basis subspace representation: a unified framework for rigid and non-rigid motion segmentation. Int J Comput Vis 121(2):209–233
Sarpatwar KK, Schieber B, Shachnai H (2019) Constrained submodular maximization via greedy local search. Oper Res Lett 47(1):1–6
Robey A, Adibi A, Schlotfeldt B, Pappas GJ, Hassani H (2019) Optimal algorithms for submodular maximization with distributed constraints. arXiv preprint arXiv:1909.13676
Sakaue S (2019) Approximation guarantees of stochastic greedy algorithms for non-monotone submodular maximization with a size constraint. arXiv preprint arXiv:1908.06242
Qian C, Yu Y, Tang K, Yao X, Zhou ZH (2019) Maximizing submodular or monotone approximately submodular functions by multi-objective evolutionary algorithms. Artif Intell 275:279–294
Adouani Y, Jarboui B, Masmoudi M (2019) A matheuristic for the 0–1 generalized quadratic multiple knapsack problem. Optim Lett 1-22
Jiang Y, Wang Y, Xu D, Yang R, Zhang Y (2019) Streaming algorithm for maximizing a monotone non-submodular function under d-knapsack constraint. Optim Lett 1–14
Shen J, Liang Z, Liu J, Sun H, Shao L, Tao D (2018) Multiobject tracking by submodular optimization. IEEE Trans Cybern 49(6):1990–2001
Shen J, Peng J, Shao L (2018) Submodular trajectories for better motion segmentation in videos. IEEE Trans Image Process 27(6):2688–2700
Zhang Y, Chen X, Li J, Teng W, Song H (2018) Exploring weakly labeled images for video object segmentation with submodular proposal selection. IEEE Trans Image Process 27(9):4245–4259
Liu F, Lin G, Qiao R, Shen C (2018) Structured learning of tree potentials in CRF for image segmentation. IEEE Trans Neural Netw Learn Syst 29(6):2631–2637
Verter V (2011) Uncapacitated and capacitated facility location problems. In: Foundations of location analysis (pp. 25–37). New York: Springer
Wang Y, Liu Y, Blasch E, Ling H (2017) Simultaneous trajectory association and clustering for motion segmentation. IEEE Signal Process Lett 25(1):145–149
Zhang Y, Lu H, Zhang L, Ruan X (2016) Combining motion and appearance cues for anomaly detection. Pattern Recogn 51:443–452
Mesbahi SC, Mahraz MA, Riffi J, Tairi H (2017) Head gesture recognition using optical flow based background subtraction. In: Proceedings of the Mediterranean Symposium on Smart City Applications (pp. 200-211). Cham: Springer
Tron R, Vidal R (2007) A benchmark for the comparison of 3-d motion segmentation algorithms. In: 2007 IEEE conference on computer vision and pattern recognition (pp. 1-8). IEEE
Ochs P, Malik J, Brox T (2013) Segmentation of moving objects by long term video analysis. IEEE Trans Pattern Anal Mach Intell 36(6):1187–1200
Jian YD, Chen CS (2010) Two-view motion segmentation with model selection and outlier removal by ransac-enhanced dirichlet process mixture models. Int J Comput Vis 88(3):489–501
Elhamifar E, Vidal R (2013) Sparse subspace clustering: algorithm, theory, and applications. IEEE Trans Pattern Anal Mach Intell 35(11):2765–2781
Lai T, Wang H, Yan Y, Chin TJ, Zhao WL (2016) Motion segmentation via a sparsity constraint. IEEE Trans Intell Transp Syst 18(4):973–983
Trobo IP, Díaz VG, Espada JP, Crespo RG, Moreno-Ger P (2019) Rapid modeling of human-defined AI behavior patterns in games. J Ambient Intell Humaniz Comput 10(7):2683–2692
Wang X, Dai Z (2019) Vision-based vehicle behavior monitoring method using a novel clustering algorithm. J Ambient Intell Humaniz Comput 28:1–9
Chin TJ, Suter D, Wang H (2010) Multi-structure model selection via kernel optimisation. In: 2010 IEEE computer society conference on computer vision and pattern recognition (pp. 3586-3593). IEEE
Liu G, Lin Z, Yan S, Sun J, Yu Y, Ma Y (2012) Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal Mach Intell 35(1):171–184
Hu H, Feng J, Zhou J (2014) Exploiting unsupervised and supervised constraints for subspace clustering. IEEE Trans Pattern Anal Mach Intell 37(8):1542–1557
Russell C, Yu R, Agapito L (2014) Video pop-up: monocular 3d reconstruction of dynamic scenes. In: European conference on computer vision (pp. 583-598). Cham: Springer
Abdelwahab MA, Abdelwahab MM, Uchiyama H, Shimada A, Taniguchi RI. (2016) Video object segmentation based on superpixel trajectories. In: International conference on image analysis and recognition (pp. 191-197). Cham: Springer
Keuper M, Andres B, Brox T (2017) Motion trajectory segmentation via minimum cost multicuts. In: Proceedings of the IEEE international conference on computer vision (pp. 3271–3279)
Keuper M (2017) Higher-order minimum cost lifted multicuts for motion segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 4242–4250)
Keuper M, Tang S, Andres B, Brox T, Schiele B (2018) Motion segmentation & multiple object tracking by correlation co-clustering. IEEE Trans Pattern Anal Mach Intell 42(1):140–153
Dong W, Wu XJ, Kittler J, Yin HF (2019) Sparse subspace clustering via nonconvex approximation. Pattern Anal Applic 22(1):165–176
Gong YJ, Zhou Y (2017) Differential evolutionary superpixel segmentation. IEEE Trans Image Process 27(3):1390–1404
Chai D (2019) SQL: Superpixels via quaternary labeling. Pattern Recogn 92:52–63
Xu L, Luo B, Pei Z (2018) Weak boundary preserved superpixel segmentation based on directed graph clustering. Signal Process Image Commun 65:231–239
Funding
There is no funding for this study.
Author information
Authors and Affiliations
Contributions
All the authors have participated in writing the manuscript and have revised the final version. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical approval
This article does not contain any studies with human participants and/or animals performed by any of the authors.
Informed consent
There is no informed consent for this study.
Conflict of interest
Authors declares that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chandriah, K.K., Naraganahalli, R.V. Maximizing a deep submodular function optimization with a weighted MAX-SAT problem for trajectory clustering and motion segmentation. Appl Intell 51, 8192–8211 (2021). https://doi.org/10.1007/s10489-021-02276-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02276-8