In this study, a plurality of camera sensors distributed in the agricultural land was integrated into the Raspberry Pi, and photos were taken to observe whether the foliage of the crop was harmful or not. The image data were transmitted to the Alexnet, VGG-16 and VGG-19 convolutional nerves through deep learning methods. The network architecture extracts image features to detect the presence of pests and identifies the types of pests. Compared by the classification accuracy, training model and prediction time with a classifier based on a neural network, and a Support Vector Machine, the identified pest results will be immediately displayed on the farming management app as a timely epidemic prevention management of the farming.
CITATION STYLE
Chen, C. J., Wu, J. S., Chang, C. Y., & Huang, Y. M. (2020). Agricultural pests damage detection using deep learning. In Advances in Intelligent Systems and Computing (Vol. 1036, pp. 545–554). Springer Verlag. https://doi.org/10.1007/978-3-030-29029-0_53
Mendeley helps you to discover research relevant for your work.