Abstract
Abstract. The objective of this work was the comparison of two different classification approaches to detect four different tree species of a highly diverse tropical Atlantic Forest area. In order to achieve the objective, images were acquired with the Rikola hyperspectral camera onboard the UX4 UAV. The study area is in the Western part of São Paulo State, a tropical Atlantic Forest area protected by governmental laws, which contains areas already deforested in the past and which are currently in regeneration. The tested approaches were one based only in the pixel values and other one based in regions. After the image acquisition, the images were radiometrically and geometrically processed. In addition, an airborne laser scanning point cloud was used to calculate the canopy height model of the area, which was used to detect the individual tree crowns with the superpixels method. Those superpixels were used to the region-based classification and to feature extraction. A total of 28 features were extracted where 25 correspond to the spectral bands acquired with the Rikola camera and three correspond to the three first principal components of the images. The features were extracted from the 91 samples recognized during a field work. From the total of samples, 19 were separated to validate the classification results. The chosen classifier was the Random Forests and the results presented a kappa coefficient of 18.20% and 36.57% for the pixel-based and region-based classifications showing that the second one had a better performance.
Highlights
Tree species recognition topic has been increased in the last years due to the forest importance and the development of different sensors and platforms to acquired Remote Sensing data (Fassnacht et al 2016; Maschler, Atzberger, Immitzer, 2018)
When hyperspectral sensor is on-board of those platforms, besides the very high spatial resolution (VHSR) information, the spectral information can be acquired in a more detailed way, in dozens of spectral bands, sufficient to reconstruct the spectral signature of targets and being possible to show spectral differences not detected by multispectral data
F-Score varied from 39.50% to 72.30%, where the lowest value was to Apuleia leiocarpa and the highest was to Hymenaea courbaril
Summary
Tree species recognition topic has been increased in the last years due to the forest importance and the development of different sensors and platforms to acquired Remote Sensing data (Fassnacht et al 2016; Maschler, Atzberger, Immitzer, 2018). Regarding the tree species mapping for forest inventories, they can be done using two mainly approaches: using data acquired in field or using remotely sensed data. The first one is not suitable, especially when the trees information are required over larger areas and the monitoring needs to repetitive (Immitzer, Atzberger, Koukal, 2012). With the miniaturized sensors and Unmanned Aerial Vehicles (UAVs) remotely information can be cheaper and faster acquired in comparison with the use of aircrafts or satellites especially if a higher temporal resolution is required. When hyperspectral sensor is on-board of those platforms, besides the VHSR information, the spectral information can be acquired in a more detailed way, in dozens of spectral bands, sufficient to reconstruct the spectral signature of targets and being possible to show spectral differences not detected by multispectral data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
