Automated tree detection for forest inventories, Plantation, Bulgaria

Country:

Bulgaria

Date:

2018

Categories:

Drone Mapper, Forest Manager

Tags:

Remote sensing, Forest Information System, Monitoring

Client:

Private Client

About

Forest inventory information is very important, especially during the first months and years after the plantation establishment. Having information about the mortality and growth dynamics of the plantation supports improved decision making related to replanting, soil improvement, and early thinning activities.

 

In the past, forest inventories have been time-consuming and came at a relatively high cost. Field operator teams had to walk through the plantation and manually conducted their measurements, which significantly limited the coverage per time.

 

Though, recent technological developments, like drones and high computational power, have enabled the development of more efficient forest monitoring approaches. With drones it has become possible to capture areas of several hundred hectares a day and carry out automated tree measurements.

Automated tree inventory

In this case study we have carried out automated tree inventory for a young tree plantation in Bulgaria based on high-resolution drone imagery.

 

Based on this imagery, a detailed Digital Surface Model was created in which the trees stand out from the background of the terrain.  With the help of a set of algorithms, individual trees were isolated, their position and size determined. The extracted data was exported into standard shape files for further forest statistic analysis in GIS software.

Digital Surface Model (DSM) of a plantation. Trees stand out from the background.

Results of the automated tree detection and height measurement. The size of the green circles correlate with the tree height.  Red circles indicate trees which could not be reconstructed due to a limited data quality.

Labels showing the tree height of individual trees (in meters).