An approach for automated lithological classification of point clouds

Walton, Gabriel; Mills, G.; Fotopoulos, G.; Radovanovic, R. S.; Stancliffe, R.P.W.

doi:10.1130/ges01326.1

Cited by 12 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hand scanner's increased mobility also allows for the semi-automatic lithological characterization workflow to be applied at locations that cannot be accessed with a terrestrial laser scanner. For example, Sturzenegger and Stead (2009) and Walton et al (2016) discuss how occlusions and orientation bias often result from the fixed position of TLS systems. This can be mitigated with the hand scanners since the operator can move around the outcrop to ensure complete capture via multiple orientations.…”

Section: Geological Applications Of Acquired 3-d Point Cloud Datamentioning

confidence: 99%

Augmenting geological field mapping with real-time, 3-D digital outcrop scanning and modeling

et al. 2022

View full text Add to dashboard Cite

Hand scanners are compact, lightweight, and capable of generating 3-D digital models. Although they do not compare to conventional methods (terrestrial laser scanning and photogrammetry) in terms of coverage, resolution, and accuracy, they offer increased mobility, speed, and real-time processing capabilities in the field. This study investigates the use of hand scanners for real-time, 3-D digital outcrop modeling to augment geological field mapping campaigns and highlights the advantages and the limitations. The utility of incorporating hand scanners as an additional tool for augmenting geological mapping is assessed based on 41 outcrop scans from the Gould Lake area, which is located 20 km north of Kingston, Ontario, Canada. The 3-D digital outcrop models gathered included two distinct metamorphic lithologies (marble and quartzofeldspathic gneiss) measuring up to 2.5 m high × 7 m long with an average surface area of 18 m2. This average scan size would take less than 10 min to capture, result in ~18 million individual points per scan, and provide a spatial resolution of ~1 cm for outcrop features. Throughout the course of the investigation, the main benefit of capturing multiple 3-D digital outcrop models was the ability to integrate this real-time, in situ geospatial, and geologic information across multiple visualization scales. This utility and retention of outcrop-scale geospatial information was shown to enhance the understanding of multi-scale geological relationships.

show abstract

Section: Geological Applications Of Acquired 3-d Point Cloud Datamentioning

confidence: 99%

Augmenting geological field mapping with real-time, 3-D digital outcrop scanning and modeling

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To ameliorate these issues, a small but growing body of research is being conducted in true 3-D using methods specifically developed for point cloud data. These can be divided into two distinct but converging categories: (1) spatial methods that make predictions based on geometry and spatial relationships [111]- [116], and (2) spectral methods that use textural features and/or point spectra [117]- [120].…”

Section: From 2-d Raster To 3-d Point Cloudmentioning

confidence: 99%

“…Many of these applications classify each point separately based entirely on its spectral characteristics (e.g., by using the random forest method to classify individual point spectra [117]; Fig. 9 ), but a few approaches that incorporate spatial and texture or reflectance information are beginning to emerge [118]- [120]. These provide a first step towards combined spectral-spatial classification of multi or hyperspectral point clouds.…”

Section: A State Of the Artmentioning

confidence: 99%

The Potential of Machine Learning for a More Responsible Sourcing of Critical Raw Materials

Ghamisi¹,

Shahi²,

Duan³

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The digitization and automation of the raw material sector is required to attain the targets set by the Paris Agreements and support the sustainable development goals defined by the United Nations. While many aspects of the industry will be affected, most of the technological innovations will require smart imaging sensors. In this review, we assess the relevant recent developments of Machine Learning for the processing of imaging sensor data. We first describe the main imagers and the acquired data types as well as the platforms on which they can be installed. We briefly describe radiometric and geometric corrections as these procedures have been already described extensively in previous works. We focus on the description of innovative processing workflows and illustrate the most prominent approaches with examples. We also provide a list of available resources, codes, and libraries for researchers at different levels, from students to senior researchers, willing to explore novel methodologies on the challenging topics of raw material extraction, classification, and process automatization.

show abstract

“…However, all of these authors use point clouds from light detection and rating (LiDAR) equipment. Walton et al (2016) show the application of automation methods through algorithms of feature detection for lithology classification using a point cloud from LiDAR.…”

Section: Introductionmentioning

confidence: 99%

Automated lithological classification using UAV and machine learning on an open cast mine

Beretta

Rodrigues

Peroni

et al. 2019

Applied Earth Science

View full text Add to dashboard Cite

Mine planning is directly dependent on the lithological features and the definition of contacts between materials. Geological modelling is a continual duty that is performed using observation data, which includes open faces information. New data must be continuously acquired and more details are added to the model. This task can benefit from the automation of lithological detection. Unmanned aerial vehicles (UAVs) are widely used in open pit mining projects, with low risk to the operators, to the aircraft or third parties. Topographic modelling using UAV imagery is now common in the mining industry. The next step, presented here, is to automate the surface feature detection using machine learning (ML) algorithms to classify a complete detailed geological model. An inexpensive aircraft was used on a Brazilian phosphate mine with point spacing as small as 10 cm.

show abstract

An approach for automated lithological classification of point clouds

Cited by 12 publications

References 38 publications

Augmenting geological field mapping with real-time, 3-D digital outcrop scanning and modeling

Augmenting geological field mapping with real-time, 3-D digital outcrop scanning and modeling

The Potential of Machine Learning for a More Responsible Sourcing of Critical Raw Materials

Automated lithological classification using UAV and machine learning on an open cast mine

Contact Info

Product

Resources

About