3D Dense Reconstruction of Road Surface from UAV Images and Comparison of SfM Based Software Performance

Zeybek, Mustafa; Biçici, Serkan

doi:10.48123/rsgis.983251

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of GPR, RM and IRT allowed the collection of detailed internal data on the exact nature and extent of the defects, and the overall condition of the examined heritage. Typically, single NDT procedures are used, but the current study clearly shows the benefits of integrating methods and the combined use of multiple techniques in maximizing data, both quantitatively and qualitatively (Sbartaï et al, 2007;Pellicer and Gibson, 2011;Fernandes et al, 2015;Zeybek and Biçici, 2020;Biçici and Zeybek, 2021;Zeybek and Biçici, 2021).…”

Section: Discussionmentioning

confidence: 83%

Türkiye'de İpek Yolu Uzaktan Algılama İzleme ve Değerlendirme: Drone Sistemlerinin GPR ve RM ile Entegrasyonu

Kılıç

2022

Turk J Remote Sens GIS

View full text Add to dashboard Cite

Maintaining a country’s heritage requires the implementation of appropriate methods, which enable the condition assessment of historic infrastructure with preferably zero damages/interventions and minimum post-inspections. A vast expanse of intricate land- and sea-route networks is known as the Silk Roads. They were crucial in bringing Eastern and Western cultures together. Additionally, it has been noted that major cities in Western Anatolia, such as Baghdad or Izmir, have been able to establish links because to their advantageous position. Non-Destructive Techniques (NDT) can meet such criteria, while they are also time and cost-efficient. This paper recommends the combined use of several techniques to maximize information range and accuracy. More specifically, High Definition and Infrared Thermography (IRT) drone systems to assess sub-surface state and detect external heritage defects, and Ground Penetrating Radar (GPR) and Resistivity Measurement (RM) for detecting internal defects. By accumulating suitable data from heritage structures along the Silk Road in Turkey, this study presents a comprehensive approach that can accurately identify surficial and internal defects, in terms of their location and size.

show abstract

Section: Discussionmentioning

confidence: 83%

Türkiye'de İpek Yolu Uzaktan Algılama İzleme ve Değerlendirme: Drone Sistemlerinin GPR ve RM ile Entegrasyonu

Kılıç

2022

Turk J Remote Sens GIS

View full text Add to dashboard Cite

show abstract

“…LiDAR sensors have a high resolution and accuracy when measuring objects [66] and represent a promising technology for road maintenance in the near future [67]. Zeybek and Bicici [68] have shown that LiDAR sensors can detect deformations on the road surface. This 3D sensor technology will revolutionize measurement methods, offering high-density data and visualizations for small-scale projects.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Approach to Surface Deformation Estimation in Forest Road and Trail Networks Using Unmanned Aerial Vehicle Real-Time Kinematic-Derived Data for Monitoring and Maintenance

Siafali,

Tsioras

2024

Forests

View full text Add to dashboard Cite

The significant increase in hiking, wood extraction, and transportation activities exerts a notable impact on the environmental balance along trails and forest roads in the form of soil degradation. The aim of this study was to develop a Deformation Classification Model for the surface of a multi-use trail, as well as to calculate sediment deposition and generate a flood hazard map in a partially forested region. The eBee X mapping Unmanned Aerial Vehicle (UAV) equipped with the senseFly S.O.D.A. 3D camera and Real-Time Kinematic (RTK) technology flew over the study area of 149 ha in Northern Greece at an altitude of 120 m and achieved a high spatial resolution of 2.6 cm. The specific constellation of fixed-wing equipment makes the use of ground control points obsolete, compared to previous, in most cases polycopter-based, terrain deformation research. Employing the same methodology, two distinct classifications were applied, utilizing the Digital Surface Model (DSM) and Digital Elevation Model (DEM) for analysis. The Geolocation Errors and Statistics for Bundle Block Adjustment exhibited a high level of accuracy in the model, with the mean values for each of the three directions (X, Y, Z) being 0.000023 m, −0.000044 m, and 0.000177 m, respectively. The standard deviation of the error in each direction was 0.022535 m, 0.019567 m, and 0.020261 m, respectively. In addition, the Root Mean Square (RMS) error was estimated to be 0.022535 m, 0.019567 m, and 0.020262 m, respectively. A total of 20 and 30 altitude categories were defined at a 4 cm spatial resolution, each assigned specific ranges of values, respectively. The area of each altitude category was quantified in square meters (m2), while the volume of each category was measured in cubic meters (m3). The development of a Deformation Classification Model for the deck of a trail or forest road, coupled with the computation of earthworks and the generation of a flood hazards map, represents an efficient approach that can provide valuable support to forest managers during the planning phase or maintenance activities of hiking trails and forest roads.

show abstract

“…One widely used technology is the mobile laser scanning (MLS) system [12,13]. Additionally, unmanned aerial vehicles (UAVs) have recently become a popular technology for this purpose [14][15][16]. In this technology, images collected from UAV flights are converted into 3D data using photogrammetry technology [17].…”

Section: Introductionmentioning

confidence: 99%

Different KNN parameters on road surface extraction from UAV-based point cloud under several machine learning algorithms

Biçici

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate road surface from a three-dimensional (3D) point cloud depends on various parameters. One crucial parameter is the set of point features. Point features enable classification by capturing characteristics of the surface on which the points are located. These features are calculated based on the closest points surrounding each point. In this study, the K-nearest neighbors algorithm (KNN) was applied to identify these closest points. The KNN algorithm requires only one input, the number of closest points (k). Eight different point features were developed using different k values, and their impact on road surface classification from the 3D point cloud was investigated. It was observed that there is no significant improvement in classification accuracy until a certain k value. However, better classification accuracy was achieved after a certain k value. The effect of different k values was also investigated under different training sample structures and machine learning (ML) algorithms. When training samples were selected from a single location as a large group, similar classification accuracy was obtained across different k values. Conversely, when training samples were chosen from various regions in smaller groups rather than a single large group, improved classification was observed as the k value increased. Additionally, it was noted that five different ML algorithms-random forest, support vector machine, generalized linear model, linear discriminant analysis, and robust linear discriminant analysis-have almost similar performance under different k values. Finally, using the optimum k value, improvements of up to 4.543% and 6.601% in accuracy and quality measures, respectively, were found.

show abstract

3D Dense Reconstruction of Road Surface from UAV Images and Comparison of SfM Based Software Performance

Cited by 5 publications

References 17 publications

Türkiye'de İpek Yolu Uzaktan Algılama İzleme ve Değerlendirme: Drone Sistemlerinin GPR ve RM ile Entegrasyonu

Türkiye'de İpek Yolu Uzaktan Algılama İzleme ve Değerlendirme: Drone Sistemlerinin GPR ve RM ile Entegrasyonu

An Innovative Approach to Surface Deformation Estimation in Forest Road and Trail Networks Using Unmanned Aerial Vehicle Real-Time Kinematic-Derived Data for Monitoring and Maintenance

Different KNN parameters on road surface extraction from UAV-based point cloud under several machine learning algorithms

Contact Info

Product

Resources

About