Multi-View Background subtraction in Dynamic Scenes
|Typ||Master, IDP, Forschungspraxis|
|Betreuer||Dr.-Ing. Mohammadreza Babaee
Tel.: +49 (0)89 289-28543
|Beschreibung||Foreground detection is basically the first processing step in the automated analysis of video surveillance data. Although a significant amount of work has been done to address this problem, still we are far away to have a robust performance in a real world application. The main reason is that outdoor camera deployments are particularly problematic, due to the movement of the background scene itself. Some samples of input (top row) and output (bottom row) of an ideal background subtraction algorithm is presented below.
The goal of this project is to apply Mixture of Gaussian in conjunction with Conditional Random Field for background subtraction. We should apply our proposed technique to a multi-view data set, namely PETS 2009, instead of a single image to extract the foreground from background.
1. Dalal, Navneet, and Bill Triggs. "Histograms of oriented gradients for human detection." Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, 2005.
2. M. Hofmann, P.Tiefenbacher, G. Rigoll "Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter", in proc of IEEE Workshop on Change Detection, 2012
|Voraussetzung||It is expected that the candidate has a solid knowledge in Matlab and C++ Programming.
For further questions, please don’t hesitate to contact me via email to set an appointment.
|Bewerbung||If you are interested in this topic, we welcome the applications via the email address above. Please set the email subject to “<Type of application> application for topic 'XYZ'”, ex. “Master’s thesis application for topic 'XYZ'”, while clearly specifying why are you interested in the topic in the text of the message. Also make sure to attach your most recent CV (if you have one) and grade report.|