Evaluating segmentation methods for UAV-Based Spoil Pile Delineation
Abstract Mine waste dumps consist of individual, blob-like spoil piles, each with unique geological and geotechnical attributes that contribute to the overall stability of the dump. Manually characterising these individual spoil piles presents challenges due to issues of accessibility, safety risks,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-77616-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850208623400058880 |
|---|---|
| author | Sureka Thiruchittampalam Bikram Pratap Banerjee Nancy F Glenn Simit Raval |
| author_facet | Sureka Thiruchittampalam Bikram Pratap Banerjee Nancy F Glenn Simit Raval |
| author_sort | Sureka Thiruchittampalam |
| collection | DOAJ |
| description | Abstract Mine waste dumps consist of individual, blob-like spoil piles, each with unique geological and geotechnical attributes that contribute to the overall stability of the dump. Manually characterising these individual spoil piles presents challenges due to issues of accessibility, safety risks, and time consumption. Analysis of remotely acquired images, through object-based classification, offers a promising solution for the effective identification and characterisation of individual spoil piles. However, object-based classification’s effectiveness hinges on segmentation, an aspect often overlooked in spoil pile analysis. Therefore, this study aims to identify and compare various segmentation approaches to pave the way for image-based spoil characterisation. A comparative analysis is conducted between traditional segmentation approaches and those rooted in deep learning methodologies. Among the diverse segmentation approaches evaluated, the morphology-based deep learning segmentation approach, Segment Anything Model (SAM), exhibited superior performance compared to other approaches. This outcome underscores the effectiveness of incorporating morphological data and deep learning techniques for accurate and efficient segmentation of spoil pile. The findings of this study provide valuable insights into the optimisation of segmentation strategies, thereby contributing to the application of image-based monitoring of spoil piles and promoting the sustainable and hazard free management of mine dump environments. |
| format | Article |
| id | doaj-art-3bee6f43630949a2a8afe1ca667a7c13 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3bee6f43630949a2a8afe1ca667a7c132025-08-20T02:10:12ZengNature PortfolioScientific Reports2045-23222025-03-0115111310.1038/s41598-024-77616-yEvaluating segmentation methods for UAV-Based Spoil Pile DelineationSureka Thiruchittampalam0Bikram Pratap Banerjee1Nancy F Glenn2Simit Raval3School of Minerals and Energy Resources Engineering, University of New South WalesSchool of Surveying and Built Environment, University of Southern QueenslandDepartment of Geosciences, Boise State UniversitySchool of Minerals and Energy Resources Engineering, University of New South WalesAbstract Mine waste dumps consist of individual, blob-like spoil piles, each with unique geological and geotechnical attributes that contribute to the overall stability of the dump. Manually characterising these individual spoil piles presents challenges due to issues of accessibility, safety risks, and time consumption. Analysis of remotely acquired images, through object-based classification, offers a promising solution for the effective identification and characterisation of individual spoil piles. However, object-based classification’s effectiveness hinges on segmentation, an aspect often overlooked in spoil pile analysis. Therefore, this study aims to identify and compare various segmentation approaches to pave the way for image-based spoil characterisation. A comparative analysis is conducted between traditional segmentation approaches and those rooted in deep learning methodologies. Among the diverse segmentation approaches evaluated, the morphology-based deep learning segmentation approach, Segment Anything Model (SAM), exhibited superior performance compared to other approaches. This outcome underscores the effectiveness of incorporating morphological data and deep learning techniques for accurate and efficient segmentation of spoil pile. The findings of this study provide valuable insights into the optimisation of segmentation strategies, thereby contributing to the application of image-based monitoring of spoil piles and promoting the sustainable and hazard free management of mine dump environments.https://doi.org/10.1038/s41598-024-77616-yMean shift segmentationSimple linear iterative clusteringVoronoi-based segmentationStarDist segmentationSegment anything model |
| spellingShingle | Sureka Thiruchittampalam Bikram Pratap Banerjee Nancy F Glenn Simit Raval Evaluating segmentation methods for UAV-Based Spoil Pile Delineation Scientific Reports Mean shift segmentation Simple linear iterative clustering Voronoi-based segmentation StarDist segmentation Segment anything model |
| title | Evaluating segmentation methods for UAV-Based Spoil Pile Delineation |
| title_full | Evaluating segmentation methods for UAV-Based Spoil Pile Delineation |
| title_fullStr | Evaluating segmentation methods for UAV-Based Spoil Pile Delineation |
| title_full_unstemmed | Evaluating segmentation methods for UAV-Based Spoil Pile Delineation |
| title_short | Evaluating segmentation methods for UAV-Based Spoil Pile Delineation |
| title_sort | evaluating segmentation methods for uav based spoil pile delineation |
| topic | Mean shift segmentation Simple linear iterative clustering Voronoi-based segmentation StarDist segmentation Segment anything model |
| url | https://doi.org/10.1038/s41598-024-77616-y |
| work_keys_str_mv | AT surekathiruchittampalam evaluatingsegmentationmethodsforuavbasedspoilpiledelineation AT bikrampratapbanerjee evaluatingsegmentationmethodsforuavbasedspoilpiledelineation AT nancyfglenn evaluatingsegmentationmethodsforuavbasedspoilpiledelineation AT simitraval evaluatingsegmentationmethodsforuavbasedspoilpiledelineation |