Abstract
Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated reflectance mosaics and was tested along with the mosaics based on original image digital number values (DN). Two alternative classifiers, a k nearest neighbor method (k-nn), combined with a genetic algorithm and a random forest method, were tested for predicting the tree species and genus, as well as for selecting an optimal set of remote sensing features for this task. The combination of VNIR, SWIR, and 3D features performed better than any of the data sets individually. Furthermore, the calibrated reflectance values performed better compared to uncorrected DN values. These trends were similar with both tested classifiers. Of the classifiers, the k-nn combined with the genetic algorithm provided consistently better results than the random forest algorithm. The best result was thus achieved using calibrated reflectance features from VNIR and SWIR imagery together with 3D point cloud features; the proportion of correctly-classified trees was 0.823 for tree species and 0.869 for tree genus.
Highlights
Recognition of tree species and acquiring geospatial information about tree species composition is essential in forest management, as well as in the management of other wooded habitats
The objective of this study was to investigate the use of high resolution photogrammetric point clouds in combination with HS imagery based on two novel cameras in visible to near-infrared (VNIR) (400–1000 nm) and short-wavelength infrared, an short-wave infrared (SWIR) (1100–1600 nm) spectral ranges in tree species recognition in an arboretum with large numbers of tree species
Classification Results of HS imagery and 3D data using k-nn+genetic algorithm (GA) classifier are presented in Figure 7a, and similacromrebTsinhuaelttisoqnuusasniontfitgaHttiSvheeimRraeFgsuecrltylsas(oosrfiifigteirnreaelarDsepNepcriveeasslueaennst)dedangdiennu3FDsigcdulaartseasif7uicbsai.ntiTgonhkse-nrbnea+ssGeudAltscolnbasasdsifeiifedfreroeannret calibrated reflectancepsreosefnHtedS ibnaFnigdusrean7ad, a3nDd sdimatialararreesuplrtsesuesinntgetdheinRFFicglaussriefie8raa(rek-pnrens+enGteAd icnlaFsigsuifireer7)b.aTnhde Figure 8b (RF classifiresru).ltTs hbeaspedroopnocratiliobnraotefdcroerfrleecctatnccleasssoefsHaSs wbaenldlsaasntdhe3Dkadpaptaaacroeepffirecsieenntetds ainreFpigruerseesn8taed for each combinati(okn-non+fGinApculatssdifaietar) ianndFi8gbu(rReF7cala,sbsiafinerd)
Summary
Recognition of tree species and acquiring geospatial information about tree species composition is essential in forest management, as well as in the management of other wooded habitats. In forest management, information about tree species dominance or species composition is needed, among other things, for estimating the woody biomass and growing stock and the estimation of the monetary value of the forest, e.g., [1,2,3]. Forest inventory methods based on the utilization of remote sensing data have used forest stands or sample plots as inventory units when estimating forest variables, such as the amount of biomass volume of growing stock, as well as averaged variables, such as the stand age or height. Stand level forest variables are typically an average or sum from a set of trees, of which the stand or sample plot are composed, and a certain amount of information is lost even when aiming at ecologically homogeneous inventory units. Increasing the level of detail can improve detailed modelling of forests and this can be used to predict forest growth and to improve satellite-based remote sensing by modelling the radiative transfer more accurately within the forest canopy
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.