A Model for Yield Estimation Based on Sea Buckthorn Images

Sea buckthorn is an extremely drought-tolerant, resilient and sustainable crop that can be grown in areas with harsh climates scarce resources to provide a source of nutrition income for the local population. The use image-based yield estimation methods allows better management sea cultivation improve its productivity sustainability, while error fruit information due occlusion well reduced by combining analysing image features extracted using binocular cameras. In this paper, mature wild mountainous north Hohhot City, Inner Mongolia Autonomous Region, were used as study target. Firstly, complete images branches collected cameras extracted. include colour index fruits, number fruits total four texture parameters, ASM, CON, COR HOM. significant correlation weight selected calculation feature obtained introduced into BP neural network model training then was obtained. results showed best achieved coefficient determination R2 = 0.99267 root mean square RMSE 0.5214.