Grants and Contributions:

Grant or Award spanning more than one fiscal year (2017-2018 to 2018-2019).

This project aims at designing video analytic algorithms that will be implemented in a prototype smart camera.x000D
They are: 1) Detection of an unauthorized person/intrusion and 2) Detection of dwelling. Although, severalx000D
methods exist in the scientific literature for performing such tasks, most of them are either not very robust orx000D
not adapted for running on a embedded platform with more limited resources (processor and memory). Ourx000D
partner company wishes to perform on an embedded system these tasks in real-time. Our investigations willx000D
therefore focus on researching methods and algorithms that can be implemented efficiently in a smart camera,x000D
yet that are robust, for detecting intrusion and dwelling in surveillance videos.x000D
We will investigate how subsampling can be used to process fewer pixels per frame, but yet detect the objectsx000D
of interest in background subtraction algorithms. We will also investigate the background update mechanismsx000D
to select or adapt only the most useful ones. Furthermore, we will design a motion history approach tox000D
accumulate the detected foreground detections. Decisions will be made based on the accumulation map usingx000D
machine learning techniques.