Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos

Hugo de Lima Chaves, Kevyn Swhants Ribeiro, André de Souza Brito, Hemerson Tacon, Marcelo Bernardes Vieira, Augusto Santiago Cerqueira, Saulo Moraes Villela, Helena de Almeida Maia, Darwin Ttito Concha, Helio Pedrini

2020

Abstract

Siamese Neural Networks (SNNs) attracted the attention of the Visual Object Tracking community due to their relatively low computational cost and high efficacy to compare similarity between a reference and a candidate object to track its trajectory in a video over time. However, a video tracker that purely relies on an SNN might suffer from drifting due to changes in the target object. We propose a framework to take into account the changes of the target object in multiple time-based descriptors. In order to show its validity, we define long-term and short-term descriptors based on the first and the recent appearance of the object, respectively. Such memories are combined into a final descriptor that is the actual tracking reference. To compute the short-term memory descriptor, we estimate a filter bank through the usage of a genetic algorithm strategy. The final method has a low computational cost since it is applied through convolution operations along the tracking. According to the experiments performed in the widely used OTB50 dataset, our proposal improves the performance of an SNN dedicated to visual object tracking, being comparable to the state of the art methods.

Paper Citation

in Harvard Style

Chaves H., Ribeiro K., Brito A., Tacon H., Vieira M., Cerqueira A., Villela S., Maia H., Concha D. and Pedrini H. (2020). Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 685-694. DOI: 10.5220/0008957606850694

in Bibtex Style

@conference{visapp20,
author={Hugo de Lima Chaves and Kevyn Swhants Ribeiro and André de Souza Brito and Hemerson Tacon and Marcelo Bernardes Vieira and Augusto Santiago Cerqueira and Saulo Moraes Villela and Helena de Almeida Maia and Darwin Ttito Concha and Helio Pedrini},
title={Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={685-694},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008957606850694},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos
SN - 978-989-758-402-2
AU - Chaves H.
AU - Ribeiro K.
AU - Brito A.
AU - Tacon H.
AU - Vieira M.
AU - Cerqueira A.
AU - Villela S.
AU - Maia H.
AU - Concha D.
AU - Pedrini H.
PY - 2020
SP - 685
EP - 694
DO - 10.5220/0008957606850694
PB - SciTePress