Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6941683 | Signal Processing: Image Communication | 2018 | 25 Pages |
Abstract
We propose a novel visual tracking algorithm based on the representations from a pre-trained Convolutional Neural Network (CNN). Our algorithm pre-trains a simplified CNN using a large set of videos with tracking ground truths to obtain a generic target representation. When tracking, Particle Filtering (PF) is combined to the fully-connected layer in the pre-trained CNN. Deep representations and hand-crafted features help to model tracking. To optimize the particles' distribution, the velocity and acceleration information aids to calculate dynamic model. Meanwhile, our algorithm updates the tracking model in a lazy manner to avoid shift and expensive computation. As compared to previous methods, our results demonstrate superior performances in existing tracking benchmarks.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Xiaoyan Qian, Lei Han, Yuedong Wang, Meng Ding,