Automated crop monitoring solutions to assess the blooming charge in orchards: Preliminary results achieved by a prototype mobile lab used on apple trees

Abstract

The paper presents and discusses the use of a mobile lab (ByeLab) equipped with optical sensors (OptRx™ and LiDAR), GNSS- RTK system and an Inertial Measurement Unit (IMU), to carry out a site-specific bloom charge assessment in apple trees. The collected data are firstly synchronized by a LabView software and then processed by dedicated algorithms in MatLab®. Preliminary investigations were performed in order to evaluate the features of the flower and leaves reflectance signature. It was observed that low NDVI values corresponded to the flowers while higher values to the leaves. It was expected that NDVI show a negative correlation with the bloom charge. Using Terrestrial Laser Scanner it was possible to validate the information about the canopy thickness collected by the LiDARs mounted on the ByeLab. The OptRx™ do not seem suitable to be applied to perform an estimation of the flower charge but, merging the data collected by the two types of sensors it is possible to build descriptive maps, which provide information about canopy thickness and vegetation index values. These can be used as reference for automating machines to be applied in thinning operations according to a site-specific approach.