Long-Term Target Tracking for UAV Based on Correlation Filter
During UAV target tracking, there still exist some issues such as severe deformation, scale variance, occlusion and even fast motion. In this paper, we propose a more stable, real-time and long-term target tracking algorithm based on correlation filter for these problems. Our proposed tracker mainly included the movement and scale transformation module, which can achieves the precise area of target by combining different scale transformation based on multiple position points. In addition, we exploit the keypoint-based method to solve the redetection issue caused by target disappearance in the UAV long-term tracking process, which ensure stability of the entire system. In this paper, we verify our algorithm on the representative UAV data set called UAV123. The experimental results show that our tracker performs superiorly against several traditional methods at speed of 26 frames per second during tracking.
KeywordsUAV tracking Long-term Correlation filter Redetection Keypoint
This work was supported in part by the National Natural Sciences Foundation of China (NSFC) under Grant 61525103, and the Shenzhen Fundamental Research Project under Grant JCYJ20150930150304185.
- 3.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. (2014)Google Scholar
- 4.Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. Comput. Sci. (2015)Google Scholar
- 7.Nebehay, G., Pflugfelder, R.: Consensus-based matching and tracking of keypoints for object tracking. In: IEEE Winter Conference on Applications of Computer Vision, Steamboat Springs, CO, 2014, pp. 862–869 (2014)Google Scholar
- 8.Danelljan, M., Khan, S.F., et al.:Adaptive color attributes for real-time visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1090–1097 (2014)Google Scholar
- 9.Bertinetto, L., Valmadre, J., et al.: Staple: complementary learners for real-time tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401–1409 (2016)Google Scholar
- 10.Supancic, J.S., Ramanan, D.: Self-paced learning for long-term tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2379–2386 (2013)Google Scholar
- 11.Hua, Y., Alahari, K., Schmid, C.: Occlusion and motion reasoning for long-term tracking. In: Computer Vision – ECCV 2014, pp. 172–187. Springer International Publishing, Heidelberg (2014)Google Scholar
- 12.Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, pp. 65.1–65.11 (2014)Google Scholar