Open Access Open Access  Restricted Access Subscription Access

Video Object Co-Segmentation


Affiliations
1 Department of CSE, V.S.B Engineering College, Karur, Tamilnadu, India
 

Objective: The main motivation of this research is to discover and segment out common object regions in different videos.

Methods: The proposed system introduced a spatio-temporal scale-invariant feature transforms (SIFT) flow descriptor which is used to incorporate across-video correspondence. In order to improve the system performance particle swarm optimization (PSO) is used which captures the optimal inter-frame motion based on the position and velocity updation of the particle. In this optimization process, we use a spatio-temporal SIFT flow that integrates optical flow, which captures inter-frame motion, and conventional SIFT flow, which captures across-videos correspondence information. This novel spatio-temporal SIFT flow generates reliable estimations of common foregrounds over the entire video data set.

Findings: The experimental results show that the proposed system achieves better performance compared with existing system in terms of accuracy, precision, recall and f-measure.

Improvement: The proposed algorithm increases the overall system performances by spatio-temporal scale-invariant feature transform flow descriptor and particle swarm optimization algorithm prominently.


Keywords

Salient Object, Object Refinement, Spatio-Temporal SIFT Flow and Particle Swarms.
User
Notifications

  • Hong Li, Bee June Tye, Ee Ping Ong, Weisi Lin, Chi Chung Ko. Multiple motion object segmentation based on homogenous region merging. In IEEE International Symposium on Circuits and Systems.2011; no. 5, 175-178.
  • Alex Levinshtein. Low and mid-level shape priors for image segmentation. University of Toronto, 2010.
  • Anestis Papazoglou, Vittorio Ferrari. Fast object segmentation in unconstrained video. In Proceedings of the IEEE International Conference on Computer Vision, 2013; 1777-1784.
  • Jiaming Guo, Zhuwen Li, Loong-Fah Cheong, Steven Zhiying Zhou. Video Co-segmentation for Meaningful Action Extraction. IEEE International Conference on Computer Vision, 2013; 2232-2239.
  • Yue Fu, Ahmet Ekin, A. Murat Tekalp, Rajiv Mehrotra. Temporal Segmentation of Video Objects for Hierarchical Object-Based Motion Description. IEEE Transactions on image processing, 2001; 11(2), 135-145.
  • Yong Jae Lee, Jaechul Kim, Kristen Grauman. Key-Segments for Video Object Segmentation. Proceedings of the International Conference on Computer Vision (ICCV), 2011 ; 1995-2002.
  • Adarsh Kowdle, Sudipta N. Sinha, Richard Szeliski. Multiple View Object Co-segmentation using Appearance and Stereo Cues. Computer Vision–ECCV 2012; 789-803.
  • Badri Narayan Subudhi, Pradipta Kumar Nanda Ashish Ghosh. A Change Information Based Fast Algorithm for Video Object Detection and Tracking. IEEE Transactions on circuits and systems for video technology. 2011; 21(7), 993-1004.
  • Shaikh RA, Li JP, Khan A, Kumar K. Content Analysis using Shape and Spatial Layout with Markov Random Field. Indian Journal of Science and Technology, 2016 Mar 3; 9(7), 1-6.
  • M. Sindhana Devi, M. Soranamagesweri. An Analysis of Various Noise Removal Techniques to Enhance Image Quality, Indian Journal of Innovations & Developments, 2015; 4(7), 1-7.

Abstract Views: 196

PDF Views: 0




  • Video Object Co-Segmentation

Abstract Views: 196  |  PDF Views: 0

Authors

M. Suryaprabha
Department of CSE, V.S.B Engineering College, Karur, Tamilnadu, India
V. Shunmughavel
Department of CSE, V.S.B Engineering College, Karur, Tamilnadu, India

Abstract


Objective: The main motivation of this research is to discover and segment out common object regions in different videos.

Methods: The proposed system introduced a spatio-temporal scale-invariant feature transforms (SIFT) flow descriptor which is used to incorporate across-video correspondence. In order to improve the system performance particle swarm optimization (PSO) is used which captures the optimal inter-frame motion based on the position and velocity updation of the particle. In this optimization process, we use a spatio-temporal SIFT flow that integrates optical flow, which captures inter-frame motion, and conventional SIFT flow, which captures across-videos correspondence information. This novel spatio-temporal SIFT flow generates reliable estimations of common foregrounds over the entire video data set.

Findings: The experimental results show that the proposed system achieves better performance compared with existing system in terms of accuracy, precision, recall and f-measure.

Improvement: The proposed algorithm increases the overall system performances by spatio-temporal scale-invariant feature transform flow descriptor and particle swarm optimization algorithm prominently.


Keywords


Salient Object, Object Refinement, Spatio-Temporal SIFT Flow and Particle Swarms.

References