Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields

Kevin Qiu, Dimitri Bulatov, Lukas Lucks

2022

Abstract

Convolutional neural networks are often trained on RGB images because it is standard practice to use transfer learning using a pre-trained model. Satellite and aerial imagery, however, usually have additional bands, such as infrared or elevation channels. Especially when it comes to detection of small objects, like cars, this additional information could provide a significant benefit. We developed a semantic segmentation model trained on the combined optical and elevation data. Moreover, a post-processing routine using Markov Random Fields was developed and compared to a sequence of pixel-wise and object-wise filtering steps. The models are evaluated on the Potsdam dataset on the pixel and object-based level, whereby accuracies around 90% were obtained.

Paper Citation

in Harvard Style

Qiu K., Bulatov D. and Lucks L. (2022). Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields. In Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, ISBN 978-989-758-591-3, pages 112-119. DOI: 10.5220/0011335900003289

in Bibtex Style

@conference{sigmap22,
author={Kevin Qiu and Dimitri Bulatov and Lukas Lucks},
title={Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields},
booktitle={Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP,},
year={2022},
pages={112-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011335900003289},
isbn={978-989-758-591-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP,
TI - Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields
SN - 978-989-758-591-3
AU - Qiu K.
AU - Bulatov D.
AU - Lucks L.
PY - 2022
SP - 112
EP - 119
DO - 10.5220/0011335900003289