Lightweight Mapping of Unstructured Environments
| dc.contributor.advisor | Amayo, Paul | |
| dc.contributor.advisor | Patel Amir | |
| dc.contributor.author | Katsoulis, Michael | |
| dc.date.accessioned | 2024-07-04T13:56:27Z | |
| dc.date.available | 2024-07-04T13:56:27Z | |
| dc.date.issued | 2024 | |
| dc.date.updated | 2024-07-03T13:43:41Z | |
| dc.description.abstract | We present a computationally, size and cost-lightweight monocular reconstruction pipeline that produces high-quality reconstructions in an unstructured agricultural environment consisting of orchards and vineyards. The pipeline has to be deployed and tested on ground vehicles equipped only with a single monocular camera sensor. Running on a CPU only, while achieving a sufficient resolution to identify individual plants without limitations on maximum path length. We show that a simple visual odometry system is capable of providing performance that is more accurate than GPS, with a relative transform error of 0.19m, without the need for techniques such as bundle adjustment or loop closure. Towards this contribution, we evaluate the impact of the choice of image feature on the accuracy of the visual odometry as well as the impact of the choice of disparity estimation method on the accuracy. Additionally, we show that state-of-the-art unsupervised monocular depth networks can outperform stereo techniques in terms of accuracy achieved when estimating the depth in an agricultural setting. We also show that lightweight pyramid-based methods are able to match the performance of deep monocular depth networks at the task of disparity estimation. The pipeline presented is optimised for application in agricultural environments and is lightweight in terms of size, weight, power and computational requirements. The pipeline functions using only a single camera and without any other sensors or sources of additional information making | |
| dc.identifier.apacitation | Katsoulis, M. (2024). <i>Lightweight Mapping of Unstructured Environments</i>. (). ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/40315 | en_ZA |
| dc.identifier.chicagocitation | Katsoulis, Michael. <i>"Lightweight Mapping of Unstructured Environments."</i> ., ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024. http://hdl.handle.net/11427/40315 | en_ZA |
| dc.identifier.citation | Katsoulis, M. 2024. Lightweight Mapping of Unstructured Environments. . ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. http://hdl.handle.net/11427/40315 | en_ZA |
| dc.identifier.ris | TY - Thesis / Dissertation AU - Katsoulis, Michael AB - We present a computationally, size and cost-lightweight monocular reconstruction pipeline that produces high-quality reconstructions in an unstructured agricultural environment consisting of orchards and vineyards. The pipeline has to be deployed and tested on ground vehicles equipped only with a single monocular camera sensor. Running on a CPU only, while achieving a sufficient resolution to identify individual plants without limitations on maximum path length. We show that a simple visual odometry system is capable of providing performance that is more accurate than GPS, with a relative transform error of 0.19m, without the need for techniques such as bundle adjustment or loop closure. Towards this contribution, we evaluate the impact of the choice of image feature on the accuracy of the visual odometry as well as the impact of the choice of disparity estimation method on the accuracy. Additionally, we show that state-of-the-art unsupervised monocular depth networks can outperform stereo techniques in terms of accuracy achieved when estimating the depth in an agricultural setting. We also show that lightweight pyramid-based methods are able to match the performance of deep monocular depth networks at the task of disparity estimation. The pipeline presented is optimised for application in agricultural environments and is lightweight in terms of size, weight, power and computational requirements. The pipeline functions using only a single camera and without any other sensors or sources of additional information making DA - 2024 DB - OpenUCT DP - University of Cape Town KW - Engineering LK - https://open.uct.ac.za PY - 2024 T1 - Lightweight Mapping of Unstructured Environments TI - Lightweight Mapping of Unstructured Environments UR - http://hdl.handle.net/11427/40315 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/40315 | |
| dc.identifier.vancouvercitation | Katsoulis M. Lightweight Mapping of Unstructured Environments. []. ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/40315 | en_ZA |
| dc.language.rfc3066 | Eng | |
| dc.publisher.department | Department of Electrical Engineering | |
| dc.publisher.faculty | Faculty of Engineering and the Built Environment | |
| dc.subject | Engineering | |
| dc.title | Lightweight Mapping of Unstructured Environments | |
| dc.type | Thesis / Dissertation | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MSc |