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

Abstract

Lately, unmanned aerial vehicle (UAV) become a prominent technology in remote sensing studies with the advantage of high-resolution, low-cost, rapidly and periodically achievable three-dimensional (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 (RTK) positioning and multispectral (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 (GCPs), pre-defined by terrestrial global navigation satellite system (GNSS) measurements, were used as the reference data while Random Forest (RF) and Extreme Gradient Boosting (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 (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.

Three-dimensional positioning algorithm for converter station patrol inspection based on multi-sensor filtering

“…Among them, 𝝅 is the positioning of the inspection robot for the converter station; 𝚽 3D positioning information perceived by multiple sensors; 𝒇 𝝅 is a nonlinear function. In order to correct the nonlinear drift error of the sensor, a correction link is introduced in series at the output end [18]. The details are shown in Figure 2.…”

“…𝐱 𝐭|𝐭 𝐉 𝐏 𝐭 𝛉 𝐣 𝐏 𝐭 𝐐 𝐭 (18) So, the purpose of using the Kalman filtering algorithm is to adaptively obtain a Kalman gain 𝐏 𝐭 , use to perform firstorder low-pass filtering on 𝐱 𝐭|𝐭 𝟏 and 𝐎 𝐭 , complete the best fusion, and obtain three-dimensional positioning results.…”

Python-based evaluation of road network constraints for electric scooters and bicycles: Izmit Example

“…Finally, the usage information of the land where the road is located will be included in the cost calculations. Land use data is a raster data obtained from [28][29][30][31][32][33]. In order to adapt this data to the road network, 30-meter buffer zones were created for all road vector data.…”

Semantic segmentation of very-high spatial resolution satellite images: A comparative analysis of 3D-CNN and traditional machine learning algorithms for automatic vineyard detection

“…Multispectral image classification has been used in monitoring tropical forests, which are an important and rich source in terms of biological diversity [6], in determining the spatial distribution of vineyards [7][8][9], in monitoring coastal changes [10], in monitoring urban development [11], in agriculture [12], designing rangeland information systems [13], in object extraction [14], in land cover classification [15][16][17][18][19][20], burning area mapping [21], and in classification of different product types [22].…”

“…International Journal of Engineering and Geosciences, 2024, 9(1),[12][13][14][15][16][17][18][19][20][21][22][23][24] …”