Moving Objects Segmentation in Video Sequence based on Bayesian network

Paper


Duong, Thach-Thao and Duong, Anh-Duc. 2010. "Moving Objects Segmentation in Video Sequence based on Bayesian network." 8th IEEE-RIVF International Conference on Computing and Communication Technologies: Research, Innovation and Vision for the Future (RIVF 2010). Hanoi, Vietnam 01 - 04 Nov 2010 https://doi.org/10.1109/RIVF.2010.5633458
Paper/Presentation Title

Moving Objects Segmentation in Video Sequence based on Bayesian network

Presentation TypePaper
AuthorsDuong, Thach-Thao (Author) and Duong, Anh-Duc (Author)
Journal or Proceedings TitleProceedings of the 8th IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF 2010)
ERA Conference ID72545
Number of Pages6
Year2010
ISBN9781424480746
9781424480753
Digital Object Identifier (DOI)https://doi.org/10.1109/RIVF.2010.5633458
Web Address (URL) of Paperhttps://ieeexplore.ieee.org/document/5633458
Conference/Event8th IEEE-RIVF International Conference on Computing and Communication Technologies: Research, Innovation and Vision for the Future (RIVF 2010)
IEEE-RIVF International Conference on Computing and Communication Technologies
Event Details
8th IEEE-RIVF International Conference on Computing and Communication Technologies: Research, Innovation and Vision for the Future (RIVF 2010)
Event Date
01 to end of 04 Nov 2010
Event Location
Hanoi, Vietnam
Event Details
IEEE-RIVF International Conference on Computing and Communication Technologies
Abstract

This paper proposes an improvement over moving objects segmentation method for video sequence based on Bayesian network. The method integrates temporal and spatial features by Bayesian network through three fields, which are motion vector field, intensity segmentation field and object video segmentation field. Markov random field aims to push the spatial connectivity between regions. The improvement concentrates on the MAP estimation procedure in order to obtain the exact segmentation results. The Iterative MAP Estimation may cause much more error in estimation procedure and degrade the convergence of the algorithm. This paper proposes a non-iterative Estimation as an improvement for this algorithm. The non-iterative MAP estimation does not need the previous segmentation result. Therefore, the inaccurate segmentation result of former stage does not have effect on the current segmentation stage. Additionally, the non-iterative MAP estimation was designed to adapt the original model so that it does not cause failure from the theory. Experiments show that the improvement is better than the original version and has good results in some benchmark video sequences.

KeywordsBayesian network; MAP estimation; Markov random field; Moving objects; Video segmentation
ANZSRC Field of Research 2020460304. Computer vision
Byline AffiliationsVietnam National University, Vietnam
Institution of OriginUniversity of Southern Queensland
Permalink -

https://research.usq.edu.au/item/q7122/moving-objects-segmentation-in-video-sequence-based-on-bayesian-network

  • 71
    total views
  • 2
    total downloads
  • 3
    views this month
  • 0
    downloads this month

Export as

Related outputs

Trap Avoidance in Local Search Using Pseudo-Conflict Learning
Pham, Duc Nghia, Duong, Thach-Thao and Sattar, Abdul. 2012. "Trap Avoidance in Local Search Using Pseudo-Conflict Learning." 26th AAAI Conference on Artificial Intelligence (AAAI 2012). Toronto, Canada 22 - 26 Jul 2012 United States.
Weight-Enhanced Diversification in Stochastic Local Search for Satisfiability
Duong, Thach-Thao, Pham, Duc Nghia, Sattar, Abdul and Newton, M. A. Hakim. 2013. "Weight-Enhanced Diversification in Stochastic Local Search for Satisfiability." Rossi, Francesca (ed.) 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013). Beijing, China 03 - 09 Aug 2013
Integrated data envelopment analysis: Linear vs. nonlinear model
Mahdiloo, Mahdi, Toloo, Mehdi, Duong, Thach-Thao, Saen, Reza Farzipoor and Tatham, Peter. 2018. "Integrated data envelopment analysis: Linear vs. nonlinear model." European Journal of Operational Research. 268 (1), pp. 255-267. https://doi.org/10.1016/j.ejor.2018.01.008
Some comments on improving discriminating power in data envelopment models based on deviation variables framework
Mahdiloo, Mahdi, Lim, Sungmook, Duong, Thach-Thao and Harvie, Charles. 2021. "Some comments on improving discriminating power in data envelopment models based on deviation variables framework." European Journal of Operational Research. 295 (1), pp. 394-397. https://doi.org/10.1016/j.ejor.2021.02.056
Trap escape for local search by backtracking and conflict reverse
Duong, Huu-Phuoc, Duong, Thach-Thao, Pham, Duc Nghia, Sattar, Abdul and Duong, Anh Duc. 2013. "Trap escape for local search by backtracking and conflict reverse." Jaeger, Manfred, Nielsen, Thomas Dyhre and Viappiani, Paolo (ed.) 12th Scandinavian Conference on Artificial Intelligence (SCAI 2013). Aalborg, Denmark 20 - 22 Nov 2013 Amsterdam. https://doi.org/10.3233/978-1-61499-330-8-85
Diversify Intensification Phases in Local Search for SAT with a New Probability Distribution
Duong, Thach-Thao, Pham, Duc-Nghia and Sattar, Abdul. 2013. "Diversify Intensification Phases in Local Search for SAT with a New Probability Distribution." Cranefield, Stephen and Nayak, Abhaya (ed.) 26th Australasian Joint Conference on Artificial Intelligence (AI 2013). Dunedin, New Zealand 01 - 06 Dec 2013 Switzerland. https://doi.org/10.1007/978-3-319-03680-9_18
A Study of Local Minimum Avoidance Heuristics for SAT
Duong, Thach-Thao, Pham, Duc Nghia and Sattar, Abdul. 2012. "A Study of Local Minimum Avoidance Heuristics for SAT." De Raedt, Luc, Bessiere, Christian, Dubois, Didier, Doherty, Patrick, Frasconi, Paolo, Heintz, Fredrik and Lucas, Peter (ed.) 20th European Conference on Artificial Intelligence (ECAI 2012). Montpellier, France 27 - 31 Aug 2012 Netherlands. https://doi.org/10.3233/978-1-61499-098-7-300
A Method to Avoid Duplicative Flipping in Local Search for SAT
Duong, Thach-Thao, Pham, Duc Nghia and Sattar, Abdul. 2012. "A Method to Avoid Duplicative Flipping in Local Search for SAT." Thielscher, Michael and Zhang, Dongmo (ed.) 25th Australasian Joint Conference on Artificial Intelligence (AI 2012). Sydney, Australia 04 - 07 Dec 2012 Berlin. https://doi.org/10.1007/978-3-642-35101-3_19
Unsupervised Learning for Image Classification based on Distribution of Hierarchical Feature Tree
Duong, Thach-Thao, Lim, Joo-Hwee, Vu, Hai-Quan and Chevallet, Jean-Pierre. 2008. "Unsupervised Learning for Image Classification based on Distribution of Hierarchical Feature Tree." 2008 IEEE International Conference on Research, Innovation and Vision for the Future in Computing and Communication Technologies (RIVF 2008). Ho Chi Minh, Vietnam 13 - 17 Jul 2008 United States. https://doi.org/10.1109/RIVF.2008.4586371
Image retrieval based on visual information concepts and automatic image annotation
Ly, Quoc Ngoc, Duong, Anh Doc, Duong, Thach Thao and Ngo, Duc Thanh. 2006. "Image retrieval based on visual information concepts and automatic image annotation." Duc, Duong Anh, Dong, Thuy Thi Bich, Ho, Tu-Bao and Nguyen, Dinh Thuc (ed.) 1st International Conference on Theories and Applications of Computer Science (ICTACS 2006). Ho Chi Minh City, Vietnam 03 - 05 Aug 2006 United States. https://doi.org/10.1142/9789812772671_0006