ANN estimation model for photogrammetry-based UAV flight planning optimisation

Makineci, Hasan Bilgehan; Karabörk, Hakan; Durdu, Akif

doi:10.1080/01431161.2021.1945159

Cited by 7 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it could be used to compare other studies, using different training, validation, and test data and methods. The estimation values in optimization studies where different UAVs were examined together (fixed-wing and rotary-wing) are less accurate than those from studies that investigated just one wing structure at a time [38]. Consequently, the resulting estimation errors in our study are satisfactory for flight planning of UAVs with rotary-wing structures.…”

Section: Computed Overlap Ratementioning

confidence: 63%

“…Determining the lowest possible number of hidden layers is necessary to optimize the training and estimation capabilities of the network. For example, too few hidden layers will reduce the accuracy, but having more hidden layers than needed takes more time to process, and the cost function is generated inaccurately [36][37][38].…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…The data used for analysis, testing, and performance were collected from operational UAV flight plans conducted in the field. Flight plans (figure 2) were created following the photogrammetry technique and considering aviation standards for UAVs [38].…”

Section: Data Collected From Photogrammetric Purpose Uav Flight Planningmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of UAV flight time and Battery Consumption for photogrammetric application using multiple machine learning algorithms

2022

Self Cite

View full text Add to dashboard Cite

In recent years, important research has been conducted in Machine Learning (ML), especially on Artificial Neural Networks (ANN). Adaptive-Network Based Fuzzy Inference Systems (ANFIS) and Particle Swarm Optimization-Fuzzy Inference System (PSO-FIS) algorithms are popular ML algorithms like ANN. In terms of their working architecture and results, ANN, ANFIS, and PSO-FIS algorithms can obtain useful solutions for different nonlinear problems. This study evaluated the performance of the ANN, ANFIS, and PSO-FIS algorithms and compared the estimation results. Regarding the application, the test and target data was obtained from the flights performed with Unmanned Aerial Vehicles (UAV), including how long the UAV operates (i.e., Flight Time, FT) and how much battery the UAV consumes during the flight (i.e., Battery Consumption, BC). To obtain FT and BC outputs, sixty-five pre- and post-flight data tables were created. The best iterations for estimating the outputs using the three ML algorithms (considering the minimum/maximum values, RMSE, R, and R2) were determined and discussed based on the training, validation, and test estimations.

show abstract

Section: Computed Overlap Ratementioning

confidence: 63%

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

See 1 more Smart Citation

Estimation of UAV flight time and Battery Consumption for photogrammetric application using multiple machine learning algorithms

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, recently it has been demonstrated that the multivision-stereo effect provided by different views during the photogrammetric reconstruction process of a scene could be a more important factor than photogrammetric flight parameters [9]. The use of computer vision algorithms during image processing has a greater effect on the planimetric and altimetric accuracy of DEMs than some photogrammetric parameters such as GSD, height, and flight speed [10][11][12]. In some cases, the accuracy of DEMs when using these algorithms can be compared to airborne LiDAR technology [13,14].…”

Section: Introductionmentioning

confidence: 99%

Performance and precision analysis of 3D surface modeling through UAVs: validation and comparison of different photogrammetric data processing software

Mora-Félix,

Rangel-Peraza,

Monjardín-Armenta

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

The planimetric and altimetric accuracies of the Digital Elevation Model (DEM) obtained from Unmanned Aerial Vehicle (UAV) depend on some photogrammetric parameters such as flight height, flight speed, and/or ground sample distance. In the last few years, the study of computer vision algorithms has increased focusing on their importance on the photogrammetric reconstruction process for land surface mapping. According to this, the main goal of this paper was to evaluate the performance of different photogrammetric processing software, such as Open Drone Map (ODM), Agisoft PhotoScan, and Pix4D, on DEM accuracy. For this purpose, a DJI Phantom 4 Pro drone was used for the acquisition of 600 images in a difficult topography area (630 ha) with 27 Ground Control Points (GCP) previously established. The photogrammetric products were generated, and a statistical analysis was carried out for the comparison of the DEMs. The results of the Root Mean Square Error (RMSE) show that the planimetric and altimetric accuracy of Agisoft PhotoScan (RMSExy = 0.514 m; RMSEz = 0.162 m) is greater than those obtained using Pix4D and ODM. Unsatisfactory results were obtained with ODM since deformations and high planimetric and altimetric errors were identified in the orthomosaic and DEM, which was related to inefficient key point detection and an incomplete mosaic construction process. Agisoft PhotoScan modeled the anthropogenic objects as part of the land surface, while Pix4d smoothed the terrain, eliminating these anthropogenic objects and not considering them as part of the ground surface.

show abstract

“…Point data produced by high-resolution laser scanning offers various solutions in cases where conventional techniques are impractical or impossible to apply [6,[8][9][10]. Unmanned Aerial Systems (UASs) are cost-effective systems capable of low-altitude flight, which can be operated remotely due to their pilotless use [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Accuracy Assessment Toward Merging of Terrestrial Laser Scanner Point Data and Unmanned Aerial System Point Data

Karasaka

Makineci

ERDAL

2023

Konya Journal of Engineering Sciences

View full text Add to dashboard Cite

Terrestrial Laser Scanning (TLS) techniques are widely preferred for 3D models of small and large objects, buildings, and historical and cultural heritages. However, sometimes relying on a single method for 3D modelling an object/structure is insufficient to arrive at a solution or meet expectations. For example, Unmanned Aerial Systems (UAS) provide perspective for building roofs, while terrestrial laser scanners provide general information about building facades. In this research, several facades of a selected building could not be modelled using terrestrial laser scanning, and UAS was used to complete the missing data for 3D modelling. The transformation matrix, a linear function, is created to merge different data types. In the transformation matrix, the scale was found to be 1:1.012. The accuracy analysis of the produced 3D model was also made by comparing the spatial measurements taken from different building facades and the differences in the measurement values obtained from the 3D model and calculating statistically. According to the accuracy analysis results, the Root Mean Square Error (RMSE) value is approximately 3 cm. The results of the accuracy research, which are within the 95% confidence interval with the three-sigma rule, are approximately 2 cm as RMSE. As a result of the study, it was determined that the data obtained from UAV photogrammetry and the data obtained by the TLS technique could be combined, and the integrated 3D model obtained can be used more efficiently.

show abstract

ANN estimation model for photogrammetry-based UAV flight planning optimisation

Cited by 7 publications

References 36 publications

Estimation of UAV flight time and Battery Consumption for photogrammetric application using multiple machine learning algorithms

Estimation of UAV flight time and Battery Consumption for photogrammetric application using multiple machine learning algorithms

Performance and precision analysis of 3D surface modeling through UAVs: validation and comparison of different photogrammetric data processing software

Accuracy Assessment Toward Merging of Terrestrial Laser Scanner Point Data and Unmanned Aerial System Point Data

Contact Info

Product

Resources

About