Loading...

Efficient scale estimation methods using lightweight deep convolutional neural networks for visual tracking

Marvasti Zadeh, S. M ; Sharif University of Technology | 2021

303 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/s00521-020-05586-z
  3. Publisher: Springer Science and Business Media Deutschland GmbH , 2021
  4. Abstract:
  5. In recent years, visual tracking methods that are based on discriminative correlation filters (DCFs) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficient scale estimation methods, which not only improve the visual tracking performance but also provide acceptable tracking speeds. The proposed methods are formulated based on either holistic or region representation of convolutional feature maps to efficiently integrate into DCF formulations to learn a robust scale model in the frequency domain. Moreover, against the conventional scale estimation methods with iterative feature extraction of different target regions, the proposed methods exploit proposed one-pass feature extraction processes that significantly improve the computational efficiency. Comprehensive experimental results on the OTB-50, OTB-100, TC-128 and VOT-2018 visual tracking datasets demonstrate that the proposed visual tracking methods outperform the state-of-the-art methods, effectively. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature
  6. Keywords:
  7. Computational efficiency ; Convolution ; Convolutional neural networks ; Deep neural networks ; Extraction ; Feature extraction ; Frequency domain analysis ; Computational burden ; Correlation filters ; Extraction process ; Frequency domains ; Scale estimation ; State-of-the-art methods ; Translation models ; Visual Tracking ; Iterative methods
  8. Source: Neural Computing and Applications ; 2021 ; 09410643 (ISSN)
  9. URL: https://link.springer.com/article/10.1007/s00521-020-05586-z