Parallel Video Processing Techniques for Surveillance Applications
Leonidas Deligiannidis, Hamid Reza Arabnia · 2014
In this paper we present several solutions to Security Surveillance and their applications while utilizing parallel processing for improved performance. The algorithms presented in this paper are explained in detail and their implementations are provided for free for educational purposes. These algorithms with their implementations are being taught in our Parallel Processing course utilizing NVidia's Cuda language and framework. We chose the topic of Security Surveillance in our Parallel Processing course because the results are visual and applicable in many situations such as Surveillance of parking lots (monitoring our car for example), dormitory rooms, offices, etc. Image processing techniques and algorithms are discussed in this paper, and extended to real-time high definition video processing focusing on surveillance.