System and method for vegetation detection from aerial photogrammetric multispectral data

A system for vegetation detection from aerial photogrammetric multispectral data, the aerial photogrammetric multispectral data capturing a plurality of vegetation, the system comprising one or more processors and a data storage, the one or more processors in communication with the data storage and configured to execute:

• a preprocessing module to receive the aerial photogrammetric multispectral data, and to perform orthorectification on the aerial photogrammetric multispectral data to derive an orthomosaic;
• a detection module to detect apexes of individual vegetation in a height model of the aerial photogrammetric multispectral data using Local Maxima (LM) detection, and to detect vegetation as detected apexes above a predetermined threshold in the height model;
• and
• a delineation module to:
• generate a fractional map of a vegetation class by applying a Fuzzy classifier on the orthomosaic using the detected vegetation to define the class;
• generate a binary ridge map using the height model to identify ridges;
• combine the binary ridge map and the fractional map of the vegetation class to generate a ridge integrated fractional map;
• perform delineation of individual vegetation on the ridge integrated fractional map on a vegetation class using an active contour algorithm;
• and
• output the delineated vegetation.