Search academic texts

Information × Registration Number 0310U002212, 0107U012110 , R & D reports Title Methods and Means for Improving Objects Detection in Video Stream popup.stage_title Розробка та експериментальні дослідження методів і засобів покращення виявлення об'єктів у відеопотоці Head Sachenko Anatoly Olexiyovych, Registration Date 18-02-2010 Organization Ternopol National Economic University popup.description2 The research objects are video surveillance systems. The goal of the project is to develop an improved motion de-tection methods and algorithms in different illumination conditions with the usage of background subtraction tech-nique as well as splitting image to the quadtree for reducing of the processing time of each frame. Also to develop methods for tracking of the moving objects in video stream. The main results of this project are the following: ana-lyzed well-known methods and algorithms for motion detection in video stream and selected directions of their im-provement; improved method of motion detection from video stream by using hierarchical data structure. Such ap-proach allowed significantly increasing of the performance of detection process. Also it was proposed an adaptive background updating model depending if the current pixel belongs to foreground or background. This allowed to de-tect motion in the frame during a long time as well as take into account the scene illumination changes; developed a method for tracking of the moving objects with the usage of Kalman filter; developed an information technology based on the abovementioned methods. It was implemented in Microsoft Visual Studio Team System 2008 using С++ and also utilizes Intel Open Computer Vision Library. Product Description popup.authors Куриляк Юрій Орестович popup.nrat_date 2020-04-02 Close