Detection Of Basal Stem Rot Using Deep Learning

The invention introduces a method for detecting Basal Stem Rot (BSR) in oil palm trees. It employs Terrestrial Laser Scanning (TLS) technology to capture canopy images, which are then processed to create detailed 3D views of the trees. Using image analysis and a convolutional neural network (CNN) model, the method categorizes trees into healthy and non-healthy groups, further classifying non-healthy trees by infection severity. Data pre-processing and augmenting enhance image quality. The approach involves transfer learning with pre-trained CNN models and evaluates their performance using metrics. Overall, this method offers a comprehensive solution for BSR detection in oil palm trees.