Evaluation of Segmentation Methods for Spoil Pile Delineation Using UAV Images

S. Thiruchittampalam, B. P. Banerjee, S. K. Singh, N. F. Glenn, S. Raval

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Mine dump stability depends on the correct placement of fundamental units - i.e., spoil piles, based on their geological and geotechnical characteristics. In-field characterization of individual piles is strenuous. To this end, image-based characterization of spoil piles using remote data obtained through unpiloted aerial system is a potential complementary solution. Several high-level image processing techniques such as object-based classification and feature extraction, inherently rely on effective segmentation. However, studies on segmentation algorithms for spoil pile delineation are lacking. This study provides insight on colour-based and morphology-based segmentation approaches to progress avenues for object-based analysis for spoil characterization in the mine environment.

Original languageEnglish
Title of host publicationIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2450-2453
Number of pages4
ISBN (Electronic)9798350320107
DOIs
StatePublished - 2023
Event2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States
Duration: 16 Jul 202321 Jul 2023

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2023-July

Conference

Conference2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/TerritoryUnited States
CityPasadena
Period16/07/2321/07/23

Keywords

  • Mean-shift segmentation
  • Mine dumps
  • Simple linear iterative clustering
  • Spoil piles
  • Voronoi-based segmentation

Fingerprint

Dive into the research topics of 'Evaluation of Segmentation Methods for Spoil Pile Delineation Using UAV Images'. Together they form a unique fingerprint.

Cite this