Thesis subject

MSc thesis topic: High-resolution UAV imagery for fruit counting in orchards utilizing deep learning

Advances in sensor miniaturization are increasing the global popularity of unmanned aerial vehicle (UAV) in agriculture. In the context of smart agriculture, site-specific management in fruit orchards is required throughout the whole growing season – from flowering, fruitlet development, ripening, harvest, till tree dormancy. Yet, the application of UAV in orchard management is in its infancy. Are you the brave and ambitious explorer who can not wait to redefinite the tiny orchard world with the sharp sword of UAV?

Detailed spatial apple yield information is key for growers to facilitate efficient utilization of resources and to optimize and streamline the harvest process. So far, however, there has been little discussion about the feasibility of utilizing UAV in apple counting, though it has great potential to provide efficient and more reliable estimation results than manual work. Further studies regarding the individual tree identification and apple counting, based on multiple UAV products, such as high resolution RGB images, orthophoto and 3D point clouds, would be worthwhile.

Objectives

Literature review: yield estimation in orchards
Algorithm design, deep learning architecture building
Experiments in the already available datasets

Literature

Zhang, C., Valente, J., Kooistra, L. et al. Orchard management with small unmanned aerial vehicles: a survey of sensing and analysis approaches. Precision Agric (2021).
Apolo-Apolo OE, Pérez-Ruiz M, Martínez-Guanter J, Valente J. A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique. Front Plant Sci. 2020;11:1086. Published 2020 Jul 15. doi:10.3389/fpls.2020.01086
Kang, H.; Zhou, H.; Wang, X.; Chen, C. Real-Time Fruit Recognition and Grasping Estimation for Robotic Apple Harvesting. Sensors 2020, 20, 5670.
Gongal, A., Silwal, A., Amatya, S., Karkee, M., Zhang, Q., & Lewis, K. (2016). Apple crop-load estimation with over-the-row machine vision system. Computers and Electronics in Agriculture, 120, 26–35.

Theme(s): Sensing & measuring