Accuracy assessment of high-resolution terrain data produced from UAV images georeferenced with on-board PPK positioning

Abstract

In recent years, unmanned aerial vehicles (UAVs) have increased rapidly and successfully established themselves as a tool for the rapid collection of high-resolution images as baseline data in land cover studies and topographic mapping. In photogrammetry using the SfM-MVS method of processing captured images, indirect georeferencing of the digital data through ground control points (GCPs) is usually applied. But selecting, marking, and coordinating GCPs in hardto-reach terrains is time-consuming and sometimes dangerous or impossible. The main objective of this study is to evaluate the accuracy of high-resolution topographic data (HRTD) products of photogrammetric processing of PPK-directly georeferenced images by SfM-MVS workflow. Direct and indirect methods of georeferencing digital products are compared. The planimetric and vertical root mean square error (RMSE) in the position of the validation points were calculated by the differences between measured coordinates in dense point clouds, orthophoto mosaics, and terrain surfaces (DSM), and precisely measured coordinates of the validation points by GNSSRTK receivers. The analysis is based on a statistical evaluation of experimental data obtained from a TAROT X6-based hexacopter equipped with two different image sensor configurations: 1) Sony RX0 action camera and 2) Sony A6000 mirrorless camera, and 3) DJI Phantom 4 Pro quadcopter with integrated additional L1-GNSS module for direct georeferencing by PPKmethod. HRTD generation was performed with three block control configurations for each UAV: 1) Indirect georeferencing via GCP only, 2) PPK direct georeferencing without GCP, and 3) PPK georeferencing using one GCP. Our research showed that when using L1-GNSS onboard receivers for PPK-georeferencing without any GCPs, the point cloud's planimetric accuracy (RMSExy) was from 0.125 to 0.231 cm, depending on the UAV/camera configuration. However, two flight missions produced significant vertical offsets, most likely due to ionospheric disturbances affecting the resolution of phase cycle ambiguities in the single-frequency receivers used. When adding one control point in the PPK georeferencing method, the planimetric and vertical accuracy of the data is comparable to the indirect GCP referencing method. Furthermore, our results show that camera properties (i.e., focal length, resolution, sensor quality) affect the quality and accuracy of digital products. The HRTDs were also evaluated according to the ASPRS (American Photogrammetry and Remote Sensing Society) Standards for Accuracy of Digital Geospatial Data. Analyzing the accuracy of the HRTDs obtained with the experimental UAV/camera configurations for the test area, the present study shows that the PPK-SfM-MVS workflow can provide quality data with a centimeters accuracy of the photogrammetric products.

Measurement Accuracy and Improvement of Thematic Information from Unmanned Aerial System Sensor Products in Cultural Heritage Applications

“…This vertical accuracy does not seem to affect the horizontal accuracy of the orthophotomosaic of the RGB sensor, but only accompanies the generated DSM of the RGB sensor. In corresponding image processing studies without the use of GCPs [4,[11][12][13][14][15][16][17][18], similar or larger differences in vertical accuracy were calculated on the one hand, while on the other hand a noticeable improvement in vertical accuracy, at least up to 50%, is observed in the different regions under study (obviously, in these studies more than one region is studied), and thus the very large difference in vertical accuracy calculated in one region can be considered accidental.…”

“…In general, the above values, 4.5 cm and 7.6 cm, are below the software accuracy values (Table 3). The large errors on the vertical axis can be reduced (up to half) if a small number of GCPs are used simultaneously in the solution, or if a quality sensor pre-calibration is used from the start, or if more than one GNSS base stations are used to calculate the average of the PPK measurement corrections [4,5,10,17,18,21].…”

“…In these applications, there are a variety of different terrains in the areas to be mapped (smooth to rugged terrain), a structured to unstructured mapping surface, different flight heights (from 30 m to 120 m), different sensors, classic image collection strips perpendicular to each other in the same flight, different UASs (multi-rotor, fixed-wing), etc. [4,[11][12][13][14][15][16][17][18]. However, there are also studies (though fewer) that report that the use of RTK or PPK (processing without GCPs) results in products of equal or better accuracy on all three axes as opposed to processing with the exclusive use of GCPs [19][20][21][22].…”

Accuracy analysis of UAV aerial photogrammetry based on RTK mode, flight altitude, and number of GCPs

“…The main factors are: (1) Hardware performance, including UAV wind resistance, temperature adaptability, navigation module configuration, gimbal stability performance, camera parameters, sensors, inertial measurement devices, and Real-Time Kinematic (RTK) modules [23]. For instance, camera parameters, such as focal length, resolution, and sensor performance, impact the quality and accuracy of digital products [24,25], and the RTK mode can significantly improve positioning accuracy [26]. (2) Flight environment, including flight time, meteorological conditions, topographic features, and signal transmission stability [27].…”

“…Among these, GCPs significantly influence the accuracy of aerial images. For consumer-grade UAVs without RTK modules, measurement accuracy can reach centimeter-level precision after adding an appropriate number of GCPs [25,[40][41][42]. Moreover, the precision of extracting target coordinates from aerial results is influenced by factors such as image resolution, quality, and user experience [41,43].…”