Skip to main content Skip to main navigation


AI-based Maize and Weeds detection on the edge with CornWeed Dataset

Naeem Iqbal; Christoph Manss; Christian Scholz; Daniel Koenig; Matthias Igelbrink; Arno Ruckelshausen
In: Proceedings of the 18th Conference on Computer Science and Intelligence Systems. Workshop on AI in Agriculture (AgriAI-2023), located at 18th FedCSIS, September 17-20, Warsaw, Poland, Institute of Electrical and Electronics Engineers, 9/2023.


Agricultural applications with AI methods are used more heavily and the lack of wifi connections on the fields make cloud services unavailable. Consequently, the AI models have to be processed directly on the edge. In this paper, we evaluate state-of-the-art detection algorithms for their use in agriculture, in particular plant detection. The current paper also presents the \emph{CornWeed} data set, which has been recorded on land machines, showing labelled maize crops and weeds for plant detection. The paper provides accuracies for the state-of-the-art detection algorithms on the CornWeed data set, as well as FPS metrics for these networks on multiple edge devices. Moreover, for the FPS analysis, the detection algorithms are converted to ONNX and TensoRT engine files as they could be used as future standards for model exchange.