Drone images have allowed researchers to investigate novel questions due to their incredible spatial resolution. Ironically however, the level of detail in drone imagery renders traditional image analysis methods largely ineffective. This webinar will describe how Deep Learning methods can be used for object detection and segmentation in high resolution imagery. A workflow for doing Deep Learning in ArcGIS Pro will be explained, with a comparison of the results of two commonly used Deep Learning algorithms (MASK R-CNN and SAM) applied to drone imagery of orchard trees taken at different times of the year.

Speaker(s): Maggi Kelly, Shane Feirer