test
server time: root: http://itiis.org
current_path: /journals/tiis/digital-library/manuscript/1148
current_url: http://itiis.org/journals/tiis/digital-library/manuscript/1148
Background Subtraction for Moving Cameras Based on Trajectory-controlled Segmentation and Label Inference
  • KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Background Subtraction for Moving Cameras Based on Trajectory-controlled Segmentation and Label Inference

Vol. 9, No. 10, October 30, 2015
10.3837/tiis.2015.10.018, Download Paper (Free):

Abstract

We propose a background subtraction method for moving cameras based on trajectory classification, image segmentation and label inference. In the trajectory classification process, PCA-based outlier detection strategy is used to remove the outliers in the foreground trajectories. Combining optical flow trajectory with watershed algorithm, we propose a trajectory-controlled watershed segmentation algorithm which effectively improves the edge-preserving performance and prevents the over-smooth problem. Finally, label inference based on Markov Random field is conducted for labeling the unlabeled pixels. Experimental results on the motionseg database demonstrate the promising performance of the proposed approach compared with other competing methods.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
X. Yin, B. Wang, W. Li, Y. Liu and M. Zhang, "Background Subtraction for Moving Cameras Based on Trajectory-controlled Segmentation and Label Inference," KSII Transactions on Internet and Information Systems, vol. 9, no. 10, pp. 4092-4107, 2015. DOI: 10.3837/tiis.2015.10.018.

[ACM Style]
Xiaoqing Yin, Bin Wang, Weili Li, Yu Liu, and Maojun Zhang. 2015. Background Subtraction for Moving Cameras Based on Trajectory-controlled Segmentation and Label Inference. KSII Transactions on Internet and Information Systems, 9, 10, (2015), 4092-4107. DOI: 10.3837/tiis.2015.10.018.