End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box

The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to an object in a video stream, given only the bounding box for that object on the first frame. In 2015, a new type of vid...

Full description

Saved in:
Bibliographic Details
Published in2019 XVI International Symposium "Problems of Redundancy in Information and Control Systems" (REDUNDANCY) pp. 165 - 170
Main Authors Belyaev, Vladislav, Malysheva, Aleksandra, Shpilman, Aleksei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2019
Subjects
Correlation
Decoding
Machine learning
Object tracking
Proposals
Redundancy
siamese networks
Task analysis
transformer
visual tracking
Online AccessGet full text

Cover

More Information
Summary:The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to an object in a video stream, given only the bounding box for that object on the first frame. In 2015, a new type of video object tracking (VOT) dataset was created that introduced rotated bounding boxes as an extension of axis-aligned ones. In this work, we introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture. We also present a new type of loss function, which takes into account the bounding box overlap and orientation.Our Deep Object Tracking model with Circular Loss Function (DOTCL) shows an considerable improvement in terms of robustness over current state-of-the-art end-to-end deep learning models. It also outperforms state-of-the-art object tracking methods on VOT2018 dataset in terms of expected average overlap (EAO) metric.
DOI:10.1109/REDUNDANCY48165.2019.9003330