eng Science and Education Publishing Journal of Computer Sciences and Applications 2328-725X 2013-02-28 1 1 1 4 10.12691/jcsa-1-1-1 JCSA2013111 article Mikhail S. Tarkov tarkov@isp.nsc.ru 1 Sergey V. Dubynin 2 A.V. Rzhanov's Institute of Semiconductor Physics SB RAS, Novosibirsk, Russia Novosibirsk State University, Novosibirsk, Russia An algorithm is proposed for tracking objects in real time. The algorithm is based on neural network implemented on GPU. Investigation and parameter optimization of the algorithm are realized. Tracking process has accelerated by 10 times and the training process has accelerated by 2 times versus to the sequential algorithm version. The maximum resolution of the frame for real-time tracking and the optimum frame sampling from a movie are calculated. http://pubs.sciepub.com/jcsa/1/1/1/jcsa-1-1-1.pdf object tracking neural network parallel computing CUDA