3D positioning accuracy and land cover classification performance of multispectral RTK UAVs

Authors : Umut Gunes SEFERCİK, Taşkın KAVZOĞLU, İsmail ÇÖLKESEN, Mertcan NAZAR, Muhammed Yusuf ÖZTÜRK, Samed ADALI, Salih DİNÇ

Pages : 119-128

Doi:10.26833/ijeg.1074791

View : 6 | Download : 3

Publication Date : 2023-07-05

Article Type : Research Paper

Abstract :Lately, unmanned aerial vehicle insert ignore into journalissuearticles values(UAV); become a prominent technology in remote sensing studies with the advantage of high-resolution, low-cost, rapidly and periodically achievable three-dimensional insert ignore into journalissuearticles values(3D); data. UAV enables data capturing in different flight altitudes, imaging geometries, and viewing angles which make detailed monitoring and modelling of target objects possible. Against earlier times, UAVs have been improved by integrating real-time kinematic insert ignore into journalissuearticles values(RTK); positioning and multispectral insert ignore into journalissuearticles values(MS); imaging equipment. In this study, positioning accuracy and land cover classification potential of RTK equipped MS UAVs were evaluated by point-based geolocation accuracy analysis and pixel-based ensemble learning algorithms. In positioning accuracy evaluation, ground control points insert ignore into journalissuearticles values(GCPs);, pre-defined by terrestrial global navigation satellite system insert ignore into journalissuearticles values(GNSS); measurements, were used as the reference data while Random Forest insert ignore into journalissuearticles values(RF); and Extreme Gradient Boosting insert ignore into journalissuearticles values(XGBoost); algorithms were applied for land cover classification. In addition, the spectral signatures of some major land classes, achieved by UAV MS bands, were compared with reference terrestrial spectro-radiometer measurements. The results demonstrated that the positioning accuracy of MS RTK UAV is ±1.1 cm in X, ±2.7 cm in Y, and ±5.7 cm in Z as root mean square error insert ignore into journalissuearticles values(RMSE);. In RF and XGBoost pixel-based land cover classification, 13 independent land cover classes were detected with overall accuracies and kappa statistics of 93.14% and 93.37%, 0.92 and 0.93, respectively.
Keywords : UAV, Multispectral, RTK, Machine Learning, Land Cover Classification