TY - GEN AB - Motion detection is of utmost importance in several applications such as video surveillance, remote sensing and medical diagnosis, and a large number of algorithms have been proposed for implementation. In this paper we focus on low resources scenarios where standard solutions are inapplicable. We present a novel algorithm that exploits spacial correlation of neighbor pixels in an image to get the most accurate view of the moving scene without increasing computational burden. In conjunction with the proposed algorithm we investigate, to the best of our knowledge for the first time, several background models and update policies, comparing available approaches and exploring trade-offs between complexity and detection capability. AD - Politecnico di Torino, Torino, Italy AD - Politecnico di Torino, Torino, Italy AD - Politecnico di Torino, Torino, Italy AU - Dassatti, Alberto AU - Masera, Guido AU - Piccinini, Gianluca CY - Damascus, Syria DA - 2008-04 DO - 10.1109/ICTTA.2008.4530099 DO - DOI ID - 8236 JF - Proceedings of the 3rd International Conference on Information and Communication Technologies: From Theory to Applications KW - Ingénierie KW - motion detection KW - biosensors KW - sensor phenomena and characterization KW - video sequences KW - remote monitoring KW - costs KW - radio frequency KW - lighting KW - very large scale integration KW - video surveillance L1 - https://arodes.hes-so.ch/record/8236/files/Author%20postprint.pdf L2 - https://arodes.hes-so.ch/record/8236/files/Author%20postprint.pdf L4 - https://arodes.hes-so.ch/record/8236/files/Author%20postprint.pdf LA - eng LK - https://arodes.hes-so.ch/record/8236/files/Author%20postprint.pdf N1 - DASSATTI Alberto est chercheur à la HES-SO, HEIG-VD, depuis 2012. N2 - Motion detection is of utmost importance in several applications such as video surveillance, remote sensing and medical diagnosis, and a large number of algorithms have been proposed for implementation. In this paper we focus on low resources scenarios where standard solutions are inapplicable. We present a novel algorithm that exploits spacial correlation of neighbor pixels in an image to get the most accurate view of the moving scene without increasing computational burden. In conjunction with the proposed algorithm we investigate, to the best of our knowledge for the first time, several background models and update policies, comparing available approaches and exploring trade-offs between complexity and detection capability. PB - 7-11 april 2008 PP - Damascus, Syria PY - 2008-04 SN - 978-1-4244-1751-3 T1 - Low complexity motion detection with background modeling TI - Low complexity motion detection with background modeling UR - https://arodes.hes-so.ch/record/8236/files/Author%20postprint.pdf Y1 - 2008-04 ER -