Keaikitse, MBrink, WGovender, Natasha2012-10-302012-10-302012-10Keaikitse, M., Brink, W. and Govender, N. Detection of moving objects: The first stage of an autonomous surveillance system. 4th CSIR Biennial Conference: Real problems relevant solutions, CSIR, Pretoria, 9-10 October 2012http://hdl.handle.net/10204/62494th CSIR Biennial Conference: Real problems relevant solutions, CSIR, Pretoria, 9-10 October 2012Object detection is an essential first stage in a surveillance system, primarily because it focuses all the subsequent processes. The standard approach to object detection is background subtraction. At the core of background subtraction is a module that maintains an image that is representative of the scene monitored by a camera. This work compares two background subbtraction/maintenance algorithms: adaptive Gaussian mixture model and the Wallflower method. The algorithms are evaluated using video footage of the real world. The Receiver Operating Characteristic (ROC) curves are used to quantify the performance of the algorithms. In our experiments, the adaptive Gaussian mixture model outperforms the Wallflower method.enObject detectionBackground subtractionReceiver Operating CharacteristicROCVideo surveillance systemsWallflower algorithmAdaptive Gaussian mixture modelConference PresentationKeaikitse, M., Brink, W., & Govender, N. (2012). Detection of moving objects: The first stage of an autonomous surveillance system. http://hdl.handle.net/10204/6249Keaikitse, M, W Brink, and Natasha Govender. "Detection of moving objects: The first stage of an autonomous surveillance system." (2012): http://hdl.handle.net/10204/6249Keaikitse M, Brink W, Govender N, Detection of moving objects: The first stage of an autonomous surveillance system; 2012. http://hdl.handle.net/10204/6249 .TY - Conference Presentation AU - Keaikitse, M AU - Brink, W AU - Govender, Natasha AB - Object detection is an essential first stage in a surveillance system, primarily because it focuses all the subsequent processes. The standard approach to object detection is background subtraction. At the core of background subtraction is a module that maintains an image that is representative of the scene monitored by a camera. This work compares two background subbtraction/maintenance algorithms: adaptive Gaussian mixture model and the Wallflower method. The algorithms are evaluated using video footage of the real world. The Receiver Operating Characteristic (ROC) curves are used to quantify the performance of the algorithms. In our experiments, the adaptive Gaussian mixture model outperforms the Wallflower method. DA - 2012-10 DB - ResearchSpace DP - CSIR KW - Object detection KW - Background subtraction KW - Receiver Operating Characteristic KW - ROC KW - Video surveillance systems KW - Wallflower algorithm KW - Adaptive Gaussian mixture model LK - https://researchspace.csir.co.za PY - 2012 T1 - Detection of moving objects: The first stage of an autonomous surveillance system TI - Detection of moving objects: The first stage of an autonomous surveillance system UR - http://hdl.handle.net/10204/6249 ER -