<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>We present a novel approach to vision-based localization of electric city buses for assisted docking to a charging station. The method assumes that the charging station is a known object, and employs a monocular camera system for positioning upon carefully selected point features detected on the charging station. While the pose is estimated using a geometric method and taking advantage of the known structure of the feature points, the detection of keypoints themselves and the initial recognition of the charging station are accomplished using neural network models. We propose two novel neural network architectures for the estimation of keypoints. Extensive experiments presented in the paper made it possible to select the MRHKN architecture as the one that outperforms state-of-the-art keypoint detectors in the task considered, and offers the best performance with respect to the estimated translation and rotation of the bus with a low-cost hardware setup and minimal passive markers on the charging station.</p>
</abstract>

We present a novel approach to vision-based localization of electric city buses for assisted docking to a charging station. The method assumes that the charging station is a known object, and employs a monocular camera system for positioning upon carefully selected point features detected on the charging station. While the pose is estimated using a geometric method and taking advantage of the known structure of the feature points, the detection of keypoints themselves and the initial recognition of the charging station are accomplished using neural network models. We propose two novel neural network architectures for the estimation of keypoints. Extensive experiments presented in the paper made it possible to select the MRHKN architecture as the one that outperforms state-of-the-art keypoint detectors in the task considered, and offers the best performance with respect to the estimated translation and rotation of the bus with a low-cost hardware setup and minimal passive markers on the charging station.

Vision–Based Positioning of Electric Buses for Assisted Docking to Charging Stations

International Journal of Applied Mathematics and Computer Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

We present a novel approach to vision-based localization of electric city buses for assisted docking to a charging station. The method assumes that the...

Vision–Based Positioning of Electric Buses for Assisted Docking to Charging Stations

Publié en ligne: 30 déc. 2022

Pages: 583 - 599

Reçu: 09 janv. 2022

Accepté: 27 juil. 2022

DOI: https://doi.org/10.34768/amcs-2022-0041

Mots clés
AI transport, localization, monocular vision, deep learning, keypoints, advanced driver assistance system

© 2022 Tomasz Nowak et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Vision–Based Positioning of Electric Buses for Assisted Docking to Charging Stations

Publié en ligne: 30 déc. 2022

Pages: 583 - 599

Reçu: 09 janv. 2022

Accepté: 27 juil. 2022

DOI: https://doi.org/10.34768/amcs-2022-0041

Mots clésAI transport, localization, monocular vision, deep learning, keypoints, advanced driver assistance system

© 2022 Tomasz Nowak et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
AI transport, localization, monocular vision, deep learning, keypoints, advanced driver assistance system