Article citationsMore >>

Haykin, S. Neural Networks. A Comprehensive Foundation, Prentice Hall Inc., 1999.

has been cited by the following article:

Article

Real-Time Object Tracking by CUDA-accelerated Neural Network

1A.V. Rzhanov’s Institute of Semiconductor Physics SB RAS, Novosibirsk, Russia

2Novosibirsk State University, Novosibirsk, Russia


Journal of Computer Sciences and Applications. 2013, Vol. 1 No. 1, 1-4
DOI: 10.12691/jcsa-1-1-1
Copyright © 2013 Science and Education Publishing

Cite this paper:
Mikhail S. Tarkov, Sergey V. Dubynin. Real-Time Object Tracking by CUDA-accelerated Neural Network. Journal of Computer Sciences and Applications. 2013; 1(1):1-4. doi: 10.12691/jcsa-1-1-1.

Correspondence to: Mikhail S. Tarkov, A.V. Rzhanov’s Institute of Semiconductor Physics SB RAS, Novosibirsk, Russia. Email: tarkov@isp.nsc.ru

Abstract

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.

Keywords