Yield Prognosis for the Agrarian Management of Vineyards using Deep Learning for Object Counting
Year: 2019
Type: article
Abstract: In various applications, the counting of objects based on image dataplays a pivotal role. In this paper we first conducted a literature review to displaythe state of the art in counting objects and summarized the results by extractingseveral important concepts that describe the counting problem as well as thesolution. In a second step we applied this knowledge to yield prognosis invineyards, where we used Deep Learning models to detect the objects. Whilethese methods used in the detection step are state of the art and perform very well,several problems are usually introduced by the constraint of only counting anobject once in the counting step. We provide a solution for this common problemby identifying unique objects and tracking them throughout a sequence of imagesin order to avoid counting objects more than once, resulting in an automated yieldprognosis model for vineyards.
Authors: Kai Heinrich, Andreas Roth, Lukas Breithaupt, Bjørn Møller, Johannes Maresch
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W2966147615