Background scene modeling for PTZ cameras using RBM
Aasim Rafique, Ahmad Muqeem Sheri, Moongu Jeon · 2014
Background subtraction is primarily used as feature extraction and modeling in video analysis. Pan-tilt-zoom cameras, with their adjuvant capacity to capture the videos, add complexities to background model. Conventional techniques for background subtraction rely on the background model to extract the foreground object. In this work, we investigated restricted Boltzmann machine (RBM) to model the structure of the scene from videos captured by PTZ cameras. The generative modeling paradigm of RBM gives an extensive and non-parametric background learning framework. Experimentation results demonstrate the manifest ability of modeling structure of various scenes using RBM.