Bringing Semantics to the Vineyard: An Approach on Deep Learning-Based Vine Trunk Detection

dc.contributor.author André Silva Aguiar en
dc.contributor.author Monteiro,NN en
dc.contributor.author Filipe Neves Santos en
dc.contributor.author Eduardo Pires en
dc.contributor.author Daniel Queirós Silva en
dc.contributor.author Armando Sousa en
dc.contributor.author José Boaventura en
dc.contributor.other 5152 en
dc.contributor.other 5552 en
dc.contributor.other 5773 en
dc.contributor.other 5777 en
dc.contributor.other 7844 en
dc.contributor.other 8276 en
dc.date.accessioned 2023-05-04T09:38:25Z
dc.date.available 2023-05-04T09:38:25Z
dc.date.issued 2021 en
dc.description.abstract <jats:p>The development of robotic solutions in unstructured environments brings several challenges, mainly in developing safe and reliable navigation solutions. Agricultural environments are particularly unstructured and, therefore, challenging to the implementation of robotics. An example of this is the mountain vineyards, built-in steep slope hills, which are characterized by satellite signal blockage, terrain irregularities, harsh ground inclinations, and others. All of these factors impose the implementation of precise and reliable navigation algorithms, so that robots can operate safely. This work proposes the detection of semantic natural landmarks that are to be used in Simultaneous Localization and Mapping algorithms. Thus, Deep Learning models were trained and deployed to detect vine trunks. As significant contributions, we made available a novel vine trunk dataset, called VineSet, which was constituted by more than 9000 images and respective annotations for each trunk. VineSet was used to train state-of-the-art Single Shot Multibox Detector models. Additionally, we deployed these models in an Edge-AI fashion and achieve high frame rate execution. Finally, an assisted annotation tool was proposed to make the process of dataset building easier and improve models incrementally. The experiments show that our trained models can detect trunks with an Average Precision up to 84.16% and our assisted annotation tool facilitates the annotation process, even in other areas of agriculture, such as orchards and forests. Additional experiments were performed, where the impact of the amount of training data and the comparison between using Transfer Learning and training from scratch were evaluated. In these cases, some theoretical assumptions were verified.</jats:p> en
dc.identifier P-00T-EPG en
dc.identifier.uri http://dx.doi.org/10.3390/agriculture11020131 en
dc.identifier.uri https://repositorio.inesctec.pt/handle/123456789/13710
dc.language eng en
dc.rights info:eu-repo/semantics/openAccess en
dc.title Bringing Semantics to the Vineyard: An Approach on Deep Learning-Based Vine Trunk Detection en
dc.type en
dc.type Publication en
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
P-00T-EPG.pdf
Size:
23.12 MB
Format:
Adobe Portable Document Format
Description: