A Deep Learning Based Approach for Strawberry Yield Prediction via Semantic Graphics
Talha Ilyas, Hyongsuk Kim
Abstract
In Korea, strawberry producers lack efficient and precise yield forecasts, which would allow them to deploy optimal manpower, equipment, and other resources for harvesting, shipping, and marketing. Reliable estimation of the quantity of strawberry fruit with respect to their ripeness level is critical for forecasting the upcoming strawberry production. Typically, the quantity and ripeness of fruits are estimated manually, which is labor-intensive and time-consuming. In this case, automated yield prediction based on robotic agriculture is a realistic option. We provide in this study an automated strawberry fruit recognition and counting system for accurate and reliable yield prediction. This paper proposes a unique neural network training approach for strawberry fruit counting and ripeness detection that combines semantic graphics for data annotation with a fully convolutional neural network (FCN). Semantic graphics, the suggested data annotation approach, is straightforward to apply, and the desired targets can be quickly tagged with little effort. Moreover, the proposed FCN is an enhanced encoder-decoder network designed specifically for efficient learning of semantic graphics. Quantitative analysis of proposed algorithm showed 4.47% increase in detection accuracy over prior techniques while running at higher frames per second.