Computer vision applications in the mining industry: a systematic review
PeerJ Computer Science · 17.06.2026 · 12 · e3915
DOI: 10.7717/peerj-cs.3915 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift PeerJ Computer Science, online erschienen am 17.06.2026. Verfasst von Cristian Suazo und 7 weiteren Autor:innen. Die Arbeit nennt 148 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Computer vision (CV) is a highly-relevant field within the artificial intelligence that enables machines to interpret and analyse visual data from the physical world, mimicking human vision. In the mining industry, CV applications have become popular as a means to address critical challenges such as optimizing resource extraction, improving safety, and minimizing environmental impact. However, existing research often addresses specific use cases, resulting in a fragmented understanding of CV’s broader applications across the sector. Based on the PRISMA 2020 guidelines, this systematic literature review (SLR) addresses this gap by consolidating diverse research into a broad resource. Peer-reviewed journal articles (2019–2024) from Web of Science and Scopus were reviewed, with 101 studies meeting inclusion criteria. The findings indicate that CV technologies have evolved from isolated tools to interconnected analytical ecosystems spanning the entire mining value chain. Applications range from safety monitoring and ore detection to environmental assessments, enhanced by multi-sensor fusion and deep learning. However, a critical validation gap emerges: while safety rhetoric dominates adoption justifications, fewer than 25% of studies provide quantitative validation. Environmental robustness remains the primary technical barrier, with methodological fragmentation undermining deployment confidence. The field requires a shift toward comprehensive field validation, standardized frameworks, and responsible deployment. This transformation signals the emergence of predictive, environmentally conscious mining practices that will fundamentally reshape resource extraction while advancing CV capabilities for sustainable industrial applications.
Zitieren
APA
Suazo, C., Soto, R., Crawford, B., Vega, E., Hermosilla, P., Fritz, A. P., Ortiz, P., & Gajardo, D. (2026). Computer vision applications in the mining industry: a systematic review. PeerJ Computer Science, 12, e3915. https://doi.org/10.7717/peerj-cs.3915
Vancouver
Suazo C, Soto R, Crawford B, Vega E, Hermosilla P, Fritz AP, et al. Computer vision applications in the mining industry: a systematic review. PeerJ Computer Science. 2026;12:e3915. doi:10.7717/peerj-cs.3915
BibTeX
@article{Suazo2026,
author = {Suazo, Cristian and Soto, Ricardo and Crawford, Broderick and Vega, Emanuel and Hermosilla, Pamela and Fritz, Alvaro Peña and Ortiz, Pablo and Gajardo, Daniel},
title = {Computer vision applications in the mining industry: a systematic review},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3915},
doi = {10.7717/peerj-cs.3915}
}
EUVIMED