Tree Detection and Localization Approach for UAV-based Forest Inspection

Abstract

This paper addressed an UAV-based solution for forest inspection from the aspect of data processing. Insect infected trees can be identified from aerial imagery. The forest inspection data processing divided into two main phases, which are tree detection and tree localization. For the tree detection task, the Deep Learning-based approach has been used. In this study, a conventional and active learning method have been used for the training. In order to map the detected trees from the video frame to geographical locations, a custom geo-localization algorithm has been developed. The proposed system loads the inspection video as an input and calculates and outputs the detected trees’ GPS coordinates. In the calculation Digital Elevation Model and camera parameters are used in addition to drone geo-data to calculate the tree positions.