Adaptive exploitation of pre-trained deep convolutional neural networks for robust visual tracking
Autor: | Shohreh Kasaei, Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan |
---|---|
Rok vydání: | 2021 |
Předmět: |
Computer Networks and Communications
Computer science business.industry Generalization Deep learning Feature extraction 020207 software engineering Pattern recognition 02 engineering and technology Convolutional neural network Discriminative model Hardware and Architecture Feature (computer vision) Robustness (computer science) 0202 electrical engineering electronic engineering information engineering Media Technology Eye tracking Artificial intelligence business Software |
Zdroj: | Multimedia Tools and Applications. 80:22027-22076 |
ISSN: | 1573-7721 1380-7501 |
Popis: | Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved a great success in challenging scenarios for visual tracking purposes. Although many of those trackers utilize the feature maps from pre-trained convolutional neural networks (CNNs), the effects of selecting different models and exploiting various combinations of their feature maps are still not compared completely. To the best of our knowledge, all those methods use a fixed number of convolutional feature maps without considering the scene attributes (e.g., occlusion, deformation, and fast motion) that might occur during tracking. As a pre-requisition, this paper proposes adaptive discriminative correlation filters (DCF) based on the methods that can exploit CNN models with different topologies. First, the paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model. Second, with the aid of analysis results as attribute dictionaries, an adaptive exploitation of deep features is proposed to improve the accuracy and robustness of visual trackers regarding video characteristics. Third, the generalization of proposed method is validated on various tracking datasets as well as CNN models with similar architectures. Finally, extensive experimental results demonstrate the effectiveness of proposed adaptive method compared with the state-of-the-art visual tracking methods. |
Databáze: | OpenAIRE |
Externí odkaz: |