Comparison of deep learning methods for grapevine growth stage recognition
Martin Schieck, Philippe Krajsic, Felix Loos, Abdulbaree Hussein, Bogdan Franczyk, Adrianna Kozierkiewicz, Marcin Pietranik
Abstract
Monitoring the phenological development stages of grapes represents a challenge in viticulture. It includes the phenological distinction of the growth stages of grapevines and the continuous technological developments, especially in computer vision, enabling a detailed classification of economically relevant development stages of grapes. In the present work, we show that based on a cascading computer vision approach, the development stages of grapes can be classified and distinguished at the micro level. In a comparative experiment (ResNet, DenseNet, InceptionV3), it could be shown that a ResNet architecture provides the best classification results with an average accuracy of 88.1%.