English

Unsupervised Deep Context Prediction for Background Foreground Separation

Computer Vision and Pattern Recognition 2018-07-18 v1

Abstract

In many advanced video based applications background modeling is a pre-processing step to eliminate redundant data, for instance in tracking or video surveillance applications. Over the past years background subtraction is usually based on low level or hand-crafted features such as raw color components, gradients, or local binary patterns. The background subtraction algorithms performance suffer in the presence of various challenges such as dynamic backgrounds, photometric variations, camera jitters, and shadows. To handle these challenges for the purpose of accurate background modeling we propose a unified framework based on the algorithm of image inpainting. It is an unsupervised visual feature learning hybrid Generative Adversarial algorithm based on context prediction. We have also presented the solution of random region inpainting by the fusion of center region inpaiting and random region inpainting with the help of poisson blending technique. Furthermore we also evaluated foreground object detection with the fusion of our proposed method and morphological operations. The comparison of our proposed method with 12 state-of-the-art methods shows its stability in the application of background estimation and foreground detection.

Keywords

Cite

@article{arxiv.1805.07903,
  title  = {Unsupervised Deep Context Prediction for Background Foreground Separation},
  author = {Maryam Sultana and Arif Mahmood and Sajid Javed and Soon Ki Jung},
  journal= {arXiv preprint arXiv:1805.07903},
  year   = {2018}
}

Comments

17 pages

R2 v1 2026-06-23T02:02:17.207Z