Real-Time Object Tracking by CUDA-accelerated Neural Network
Mikhail S. Tarkov, Sergey V. Dubynin · Journal of Computer Sciences and Applications · 2013
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.