Uma Nova Abordagem em Inteligência de Enxames Aprimorados Aplicada ao Rastreamento de Alvos em Vídeo

Abstract

This work proposes a approach to balance knowledge transfer and particle diversity in swarm intelligence algorithms in dynamic optimization problems. The method was designed to be applied to the problem of video tracking targets. It is also proposed, to use a robust version to outliers of the Double Exponential Smoothing (RDES) model, used to predict the target position in the frame delimiting the solution space in a more promising region for target tracking. To assess the quality of the proposed approach, an appropriate tracker for a discrete solution space was implemented using the meta-heuristic Shuffled Frog Leaping Algorithm (SFLA) adapted to dynamic optimization problems, named the Dynamic SFLA (DSFLA). The DSFLA was compared with other classic and current trackers whose algorithms are based on swarm intelligence. The trackers were compared in terms of the average processing time per frame and the area under curve of the success rate per Pascal metric. For the experiment, we used a random sample of videos obtained from the public Hanyang visual tracker benchmark. The experimental results suggest that the DSFLA has an efficient processing time and higher quality of tracking compared with the other trackers analyzed in this work. The success rate of the DSFLA tracker is about 7.2 to 76.6% higher on average when comparing the success rate of its competitors. The average processing time per frame is about at least 10% faster than competing trackers, except one that was about 26% faster than the DSFLA tracker. The results also show that the predictions of the RDES model are quite accurate. The DSFLA results were also compared to the results of the first 10 trackers placed on the Hanyang visual tracker OPE 100 challenge list. The result of the 95% confidence interval places the DSFLA in the top 6 on the list.