SIMBAT Project
The specific tasks to be developed in this project are derived from the development of proofs of concept in two areas of work with drones.
GIS enrichment module
This project consists of two parts. In the first part, tree detections of the area of interest are obtained from lidar data. In the second part, using these detections and an orthophoto of the area of interest, we use a neural network model capable of detecting and georeferencing trees from orthophotos. All the resulting detections (.shp) can be visualized using QGIS tool.
Publication
Automatic individual tree detection from combination of
aerial imagery, LiDAR and environment context
AUTHORS
PUBLICATION Date
September, 2021
PUBLISHED IN
Advances in Intelligent Systems and Computing Chapter of book series
Geographic Information Systems (GIS) allow analysis based on geo-referenced data. Currently only simple geo-referenced information is available, such as road networks or types of terrain, but there are other geo-referenced data that would be very useful to facilitate decision-making. These data are not collected as they are very hard to generate manually, but remote sensing data and artificial intelligence can be used to accomplish it. This work aims to develop an automatic framework for the extraction of geo-referenced trees, through the union Light Detection and Ranging (LiDAR) point clouds, aerial imagery, and existing GIS environment context. The results of the process are satisfactory, improving in some several areas the LiDAR-based detections using only imagery. However, issues such as false positives need to be corrected in the future. Merging both data sources would allow better results to be achieved.
Grant PDC2021-121567-C22 funded by:
