Vol.3, No.2, 2021, pp.63-72, doi:10.32604/jai.2021.010455
Hybrid Efficient Convolution Operators for Visual Tracking
  • Yu Wang*
Department of Computer Science, Harbin Institute of Technology, Weihai, 264200, China
* Corresponding Author: Yu Wang. Email:
Received 30 August 2020; Accepted 18 April 2021; Issue published 08 May 2021
Visual tracking is a classical computer vision problem with many applications. Efficient convolution operators (ECO) is one of the most outstanding visual tracking algorithms in recent years, it has shown great performance using discriminative correlation filter (DCF) together with HOG, color maps and VGGNet features. Inspired by new deep learning models, this paper propose a hybrid efficient convolution operators integrating fully convolution network (FCN) and residual network (ResNet) for visual tracking, where FCN and ResNet are introduced in our proposed method to segment the objects from backgrounds and extract hierarchical feature maps of objects, respectively. Compared with the traditional VGGNet, our approach has higher accuracy for dealing with the issues of segmentation and image size. The experiments show that our approach would obtain better performance than ECO in terms of precision plot and success rate plot on OTB-2013 and UAV123 datasets.
Visual tracking; deep learning; convolutional neural network; hybrid convolution operator
Cite This Article
. , "Hybrid efficient convolution operators for visual tracking," Journal on Artificial Intelligence, vol. 3, no.2, pp. 63–72, 2021.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.