Deep Learning-Based Instance Segmentation Method of Litchi Canopy from UAV-Acquired Images

Instance segmentation of fruit tree canopies from images acquired by unmanned aerial vehicles (UAVs) is significance for the precise management orchards. Although deep learning methods have been widely used in fields feature extraction and classification, there are still phenomena complex data strong dependence on software performances. This paper proposes a learning-based instance method litchi trees, which has simple structure lower requirements form. Considering that models require large amount training data, labor-friendly semi-auto image annotation introduced. The introduction this allows significant improvement efficiency pre-processing. Facing high requirement computing resources, partition-based presented high-resolution digital orthophoto maps (DOMs). Citrus added to set alleviate lack diversity original dataset. average precision (AP) selected evaluate metric proposed model. results show with help litchi-citrus datasets, best AP test reaches 96.25%.