A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

Tøttrup, Daniel; Skovgaard, Stinus Lykke; Sejersen, Jonas le Fevre; Pimentel de Figueiredo, Rui

doi:10.3390/jimaging7120270

Open AccessArticle

A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

by

Daniel Tøttrup

^*

,

Stinus Lykke Skovgaard

^*

,

Jonas le Fevre Sejersen

^*

and

Rui Pimentel de Figueiredo

^*

Department of Electrical and Computer Engineering, Aarhus University, Nordre Ringgade, 18000 Aarhus, Denmark

^*

Authors to whom correspondence should be addressed.

J. Imaging 2021, 7(12), 270; https://doi.org/10.3390/jimaging7120270

Submission received: 22 October 2021 / Revised: 30 November 2021 / Accepted: 6 December 2021 / Published: 8 December 2021

(This article belongs to the Special Issue Visual Localization)

Download

Browse Figures

Versions Notes

Abstract

In this work we present a novel end-to-end solution for tracking objects (i.e., vessels), using video streams from aerial drones, in dynamic maritime environments. Our method relies on deep features, which are learned using realistic simulation data, for robust object detection, segmentation and tracking. Furthermore, we propose the use of rotated bounding-box representations, which are computed by taking advantage of pixel-level object segmentation, for improved tracking accuracy, by reducing erroneous data associations during tracking, when combined with the appearance-based features. A thorough set of experiments and results obtained in a realistic shipyard simulation environment, demonstrate that our method can accurately, and fast detect and track dynamic objects seen from a top-view.

Keywords: object detection; multiple object tracking; convolutional neural networks

Share and Cite

MDPI and ACS Style

Tøttrup, D.; Skovgaard, S.L.; Sejersen, J.l.F.; Pimentel de Figueiredo, R. A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images. J. Imaging 2021, 7, 270. https://doi.org/10.3390/jimaging7120270

AMA Style

Tøttrup D, Skovgaard SL, Sejersen JlF, Pimentel de Figueiredo R. A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images. Journal of Imaging. 2021; 7(12):270. https://doi.org/10.3390/jimaging7120270

Chicago/Turabian Style

Tøttrup, Daniel, Stinus Lykke Skovgaard, Jonas le Fevre Sejersen, and Rui Pimentel de Figueiredo. 2021. "A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images" Journal of Imaging 7, no. 12: 270. https://doi.org/10.3390/jimaging7120270

APA Style

Tøttrup, D., Skovgaard, S. L., Sejersen, J. l. F., & Pimentel de Figueiredo, R. (2021). A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images. Journal of Imaging, 7(12), 270. https://doi.org/10.3390/jimaging7120270

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI