{"id":{"repo_id":"unr","oai_identifier":"oai:scholarwolf.unr.edu:11714/11050"},"canonical_url":"https://search.dev.ndltd.org/etd/unr/oai:scholarwolf.unr.edu:11714/11050","repository":{"repo_id":"unr","name":"University of Nevada - Reno","base_url":"https://scholarwolf.unr.edu/server/oai/request"},"display":{"title":"Automated Detection and Localization of Blastholes Through UAV Imaging and Machine Learning","abstract":"Drilling accuracy is the primary factor influencing the explosive energy distribution of a blasting process. Therefore, knowing the final location of drillholes is crucial to obtain optimal blasting results. This research proposed a new methodology to control the drilling accuracy in open-pit mines using aerial images (captured through drones) and machine learning. The main focus of the study is to analyze if photogrammetry combined with machine learning can be used to detect drillholes in photogrammetry representations of blast patterns automatically. In this context, machine learning involves the development of algorithms trained to perform a task that implies a sort of human decision. To verify if machine learning can detect drillholes over photogrammetry representations, we started the project by collecting several datasets from different mine sites in Nevada (U.S.A.). Then, the images were processed to create photogrammetry representations of the drill patterns. These representations were Orthomosaic (union of photos) and Digital Elevation Models (DEM). In the process, thousands of patches were extracted and augmented from the photogrammetry representations. The patches were used to train and test SVM Models and CNN architectures to locate drillholes in cluttered scenes (typical in drill patterns). Once the training process reached enough validation accuracy, we tested the models with data left apart at the beginning of the process (testing datasets). The high recall, precision, and percentage of drillholes detected results obtained in our experiments demonstrate that using machine learning and photogrammetry is a feasible way to detect drillholes over photogrammetry representations. This novel technique provides a new solution for engineers to control the drilling accuracy, optimizing the blasting process by achieving more realistic simulations before implementing the designs.","abstract_html":"Drilling accuracy is the primary factor influencing the explosive energy distribution of a blasting process. Therefore, knowing the final location of drillholes is crucial to obtain optimal blasting results. This research proposed a new methodology to control the drilling accuracy in open-pit mines using aerial images (captured through drones) and machine learning. The main focus of the study is to analyze if photogrammetry combined with machine learning can be used to detect drillholes in photogrammetry representations of blast patterns automatically. In this context, machine learning involves the development of algorithms trained to perform a task that implies a sort of human decision. To verify if machine learning can detect drillholes over photogrammetry representations, we started the project by collecting several datasets from different mine sites in Nevada (U.S.A.). Then, the images were processed to create photogrammetry representations of the drill patterns. These representations were Orthomosaic (union of photos) and Digital Elevation Models (DEM). In the process, thousands of patches were extracted and augmented from the photogrammetry representations. The patches were used to train and test SVM Models and CNN architectures to locate drillholes in cluttered scenes (typical in drill patterns). Once the training process reached enough validation accuracy, we tested the models with data left apart at the beginning of the process (testing datasets). The high recall, precision, and percentage of drillholes detected results obtained in our experiments demonstrate that using machine learning and photogrammetry is a feasible way to detect drillholes over photogrammetry representations. This novel technique provides a new solution for engineers to control the drilling accuracy, optimizing the blasting process by achieving more realistic simulations before implementing the designs.","abstract_has_math":false,"creators":["Valencia, Jorge"],"institution":"University of Nevada, Reno","degree_name":"Doctor of Philosophy","degree_level":"Doctorate Degree","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Sattarvand, Javad"],"committee_chairs":[],"committee_members":["Vahidi, Ehsan","Chu, Pengbo","Kallu, Raj","Shoemaker, Kevin"],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T21:47:36Z","subjects":["Convolutional Neural Networks","Drill And Blast Engineering","Machine Learning","Mining Engineering","Photogrammetry","Support Vector Machine"],"languages":[],"rights":["Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarwolf.unr.edu/handle/11714/11050","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Sattarvand, Javad"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Vahidi, Ehsan","Chu, Pengbo","Kallu, Raj","Shoemaker, Kevin"]},{"key":"dc:creator","label":"Author","values":["Valencia, Jorge"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-08-22T19:04:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-22T19:04:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctorate Degree"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Nevada, Reno"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Convolutional Neural Networks","Drill And Blast Engineering","Machine Learning","Mining Engineering","Photogrammetry","Support Vector Machine"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarwolf.unr.edu/handle/11714/11050"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Drilling accuracy is the primary factor influencing the explosive energy distribution of a blasting process. Therefore, knowing the final location of drillholes is crucial to obtain optimal blasting results. This research proposed a new methodology to control the drilling accuracy in open-pit mines using aerial images (captured through drones) and machine learning. The main focus of the study is to analyze if photogrammetry combined with machine learning can be used to detect drillholes in photogrammetry representations of blast patterns automatically. In this context, machine learning involves the development of algorithms trained to perform a task that implies a sort of human decision. To verify if machine learning can detect drillholes over photogrammetry representations, we started the project by collecting several datasets from different mine sites in Nevada (U.S.A.). Then, the images were processed to create photogrammetry representations of the drill patterns. These representations were Orthomosaic (union of photos) and Digital Elevation Models (DEM). In the process, thousands of patches were extracted and augmented from the photogrammetry representations. The patches were used to train and test SVM Models and CNN architectures to locate drillholes in cluttered scenes (typical in drill patterns). Once the training process reached enough validation accuracy, we tested the models with data left apart at the beginning of the process (testing datasets). The high recall, precision, and percentage of drillholes detected results obtained in our experiments demonstrate that using machine learning and photogrammetry is a feasible way to detect drillholes over photogrammetry representations. This novel technique provides a new solution for engineers to control the drilling accuracy, optimizing the blasting process by achieving more realistic simulations before implementing the designs."]},{"key":"dc:format","label":"Dc Format","values":["PDF"]},{"key":"dc:title","label":"Title","values":["Automated Detection and Localization of Blastholes Through UAV Imaging and Machine Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Sattarvand, Javad"],"dc:contributor.committeemember":["Vahidi, Ehsan","Chu, Pengbo","Kallu, Raj","Shoemaker, Kevin"],"dc:creator":["Valencia, Jorge"],"dc:date.accessioned":["2024-08-22T19:04:18Z"],"dc:date.available":["2024-08-22T19:04:18Z"],"dc:date.issued":["2024"],"dc:description.abstract":["Drilling accuracy is the primary factor influencing the explosive energy distribution of a blasting process. Therefore, knowing the final location of drillholes is crucial to obtain optimal blasting results. This research proposed a new methodology to control the drilling accuracy in open-pit mines using aerial images (captured through drones) and machine learning. The main focus of the study is to analyze if photogrammetry combined with machine learning can be used to detect drillholes in photogrammetry representations of blast patterns automatically. In this context, machine learning involves the development of algorithms trained to perform a task that implies a sort of human decision. To verify if machine learning can detect drillholes over photogrammetry representations, we started the project by collecting several datasets from different mine sites in Nevada (U.S.A.). Then, the images were processed to create photogrammetry representations of the drill patterns. These representations were Orthomosaic (union of photos) and Digital Elevation Models (DEM). In the process, thousands of patches were extracted and augmented from the photogrammetry representations. The patches were used to train and test SVM Models and CNN architectures to locate drillholes in cluttered scenes (typical in drill patterns). Once the training process reached enough validation accuracy, we tested the models with data left apart at the beginning of the process (testing datasets). The high recall, precision, and percentage of drillholes detected results obtained in our experiments demonstrate that using machine learning and photogrammetry is a feasible way to detect drillholes over photogrammetry representations. This novel technique provides a new solution for engineers to control the drilling accuracy, optimizing the blasting process by achieving more realistic simulations before implementing the designs."],"dc:format":["PDF"],"dc:identifier.uri":["https://scholarwolf.unr.edu/handle/11714/11050"],"dc:rights":["Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International"],"dc:subject":["Convolutional Neural Networks","Drill And Blast Engineering","Machine Learning","Mining Engineering","Photogrammetry","Support Vector Machine"],"dc:title":["Automated Detection and Localization of Blastholes Through UAV Imaging and Machine Learning"],"dc:type":["Dissertation"],"thesis:degree_level":["Doctorate Degree"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Nevada, Reno"]},"updated_at":"2026-07-27T21:47:36Z"}