Visual node prediction for visual tracking
- 3 Downloads
A novel visual tracking algorithm based on visual node (VN) prediction is proposed in this paper. First, we count the distribution area and gray levels of the larger probability density in the VN. Then, all the frequencies of the VN are calculated, of which the weaker frequency gradient is removed by filtration. The stronger frequency gradient of the VN is reserved. Finally, we estimate the optimal object position by maximizing the likelihood of node clusters, which are formed by VNs. Extensive experiments show that the proposed approach has good adaptability to variable-structure tracking and outperforms the state-of-the-art trackers.
KeywordsVisual node Visual node prediction Visual node frequency Node balance Node cluster Object tracking
Heng Yuan, Wen-Tao Jiang, and Wan-Jun Liu are supported by the National Natural Science Foundation of the Republic of China under Grant 61601213 and NSF of Liaoning province under Grant 20170540426 and Liaoning province education department project under Grant LJ2017QL034, LJYL049. Sheng-Chong Zhang is supported by the China People’s Liberation Army weapons and equipment fund under Grant 61421070101162107002.
- 12.Wang, X., Li, C., Luo, B., et al.: SINT++: robust visual tracking via adversarial positive instance generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4864–4873 (2018)Google Scholar
- 13.Dominik, A.K.: BoBoT—Bonn benchmark on tracking. http://www.iai.uni-bonn.de/~kleind/tracking/index.htm (2010). Accessed 1 Mar 2017
- 14.Choi, J., Chang, H.J., Jeong, J., et al.: Visual tracking using attention-modulated disintegration and integration. In: Computer Vision and Pattern Recognition. IEEE, pp. 4321–4330 (2016)Google Scholar
- 18.Bertinetto, L., Valmadre, J., Golodetz, S., et al.: Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401–1409 (2016)Google Scholar