Real-time GPU-based motion detection and tracking using full HD videos

Abstract

Video processing algorithms present a necessary tool for various domains related to computer vision such as motion tracking, videos indexation and event detection. However, the new video standards, especially those in high definitions, cause that current implementations, even running on modern hardware, no longer respect the needs of real-time processing. Several solutions have been proposed to overcome this constraint, by exploiting graphic processing units (GPUs). Although, they present a high potential of GPU, any is able to treat high definition videos efficiently. In this work, we propose a development scheme enabling an efficient exploitation of GPUs, in order to achieve real-time processing of Full HD videos. Based on this scheme, we developed GPU implementations of several methods related to motion tracking such as silhouette extraction, corners detection and tracking using optical flow estimation. These implementations are exploited for improving performances of an application of real-time motion detection using mobile camera. © Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2013.