Scalable photogrammetry with high performance computing. Gniady, T., Ruan, G., Sherman, W., Tuna, E., & Wernert, E. In Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact (PEARC17), volume Part F1287, pages 3, 2017. Association for Computing Machinery. Website doi abstract bibtex Photogrammetry is used to build 3-dimensional models of everything from terrains to ancient statues. In the past, the stitching process was done on powerful PCs and could take weeks for large datasets. Even relatively small objects often required several hours to stitch together. With the availability of parallel processing options in the latest release of Agisoft PhotoScan, it is possible to leverage the power of high performance computing on large datasets. This poster presents the results of benchmarking tests for three datasets processed at two different model quality levels, medium and high (there are four times more points in the dense point cloud at the high setting) using 2, 4, 8, and 16 nodes. The purpose of the benchmarking is to determine how to optimize software license usage and compute resources against time and output quality. The poster also details the matrix of user-specified parameters that have been built into the python script that submits the parallel jobs. These parameters have evolved through the assessment of needs of users who are using the HPC deployment of photogrammetry as a service.We are excited by the uptake of this new service around campus in different fields across multiple disciplines. A group of cultural heritage experts will be using the service from Italy this summer, and a graduate student in anthropology will be stitching aerial data sets from Mexico. © 2017 Copyright held by the owner/author(s).
@inproceedings{
title = {Scalable photogrammetry with high performance computing},
type = {inproceedings},
year = {2017},
keywords = {Benchmarking,Compute resources,Cultural heritages,Graduate s,Photogrammetry,Students},
pages = {3},
volume = {Part F1287},
websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025826260&doi=10.1145%2F3093338.3104174&partnerID=40&md5=3d7c365c1289d519e724ab1c35dfad07},
publisher = {Association for Computing Machinery},
id = {1b613bc0-0610-3573-badb-6c05df967054},
created = {2018-08-09T16:38:15.973Z},
file_attached = {false},
profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
group_id = {27e0553c-8ec0-31bd-b42c-825b8a5a9ae8},
last_modified = {2019-08-27T16:51:40.266Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Gniady2017},
source_type = {conference},
notes = {cited By 0; Conference of 2017 Practice and Experience in Advanced Research Computing, PEARC 2017 ; Conference Date: 9 July 2017 Through 13 July 2017; Conference Code:128771},
private_publication = {false},
abstract = {Photogrammetry is used to build 3-dimensional models of everything from terrains to ancient statues. In the past, the stitching process was done on powerful PCs and could take weeks for large datasets. Even relatively small objects often required several hours to stitch together. With the availability of parallel processing options in the latest release of Agisoft PhotoScan, it is possible to leverage the power of high performance computing on large datasets. This poster presents the results of benchmarking tests for three datasets processed at two different model quality levels, medium and high (there are four times more points in the dense point cloud at the high setting) using 2, 4, 8, and 16 nodes. The purpose of the benchmarking is to determine how to optimize software license usage and compute resources against time and output quality. The poster also details the matrix of user-specified parameters that have been built into the python script that submits the parallel jobs. These parameters have evolved through the assessment of needs of users who are using the HPC deployment of photogrammetry as a service.We are excited by the uptake of this new service around campus in different fields across multiple disciplines. A group of cultural heritage experts will be using the service from Italy this summer, and a graduate student in anthropology will be stitching aerial data sets from Mexico. © 2017 Copyright held by the owner/author(s).},
bibtype = {inproceedings},
author = {Gniady, T and Ruan, G and Sherman, W and Tuna, E and Wernert, E},
doi = {10.1145/3093338.3104174},
booktitle = {Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact (PEARC17)}
}
Downloads: 0
{"_id":"d5epMzkR9y3kZpGp7","bibbaseid":"gniady-ruan-sherman-tuna-wernert-scalablephotogrammetrywithhighperformancecomputing-2017","downloads":0,"creationDate":"2018-03-12T19:10:27.198Z","title":"Scalable photogrammetry with high performance computing","author_short":["Gniady, T.","Ruan, G.","Sherman, W.","Tuna, E.","Wernert, E."],"year":2017,"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibdata":{"title":"Scalable photogrammetry with high performance computing","type":"inproceedings","year":"2017","keywords":"Benchmarking,Compute resources,Cultural heritages,Graduate s,Photogrammetry,Students","pages":"3","volume":"Part F1287","websites":"https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025826260&doi=10.1145%2F3093338.3104174&partnerID=40&md5=3d7c365c1289d519e724ab1c35dfad07","publisher":"Association for Computing Machinery","id":"1b613bc0-0610-3573-badb-6c05df967054","created":"2018-08-09T16:38:15.973Z","file_attached":false,"profile_id":"42d295c0-0737-38d6-8b43-508cab6ea85d","group_id":"27e0553c-8ec0-31bd-b42c-825b8a5a9ae8","last_modified":"2019-08-27T16:51:40.266Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Gniady2017","source_type":"conference","notes":"cited By 0; Conference of 2017 Practice and Experience in Advanced Research Computing, PEARC 2017 ; Conference Date: 9 July 2017 Through 13 July 2017; Conference Code:128771","private_publication":false,"abstract":"Photogrammetry is used to build 3-dimensional models of everything from terrains to ancient statues. In the past, the stitching process was done on powerful PCs and could take weeks for large datasets. Even relatively small objects often required several hours to stitch together. With the availability of parallel processing options in the latest release of Agisoft PhotoScan, it is possible to leverage the power of high performance computing on large datasets. This poster presents the results of benchmarking tests for three datasets processed at two different model quality levels, medium and high (there are four times more points in the dense point cloud at the high setting) using 2, 4, 8, and 16 nodes. The purpose of the benchmarking is to determine how to optimize software license usage and compute resources against time and output quality. The poster also details the matrix of user-specified parameters that have been built into the python script that submits the parallel jobs. These parameters have evolved through the assessment of needs of users who are using the HPC deployment of photogrammetry as a service.We are excited by the uptake of this new service around campus in different fields across multiple disciplines. A group of cultural heritage experts will be using the service from Italy this summer, and a graduate student in anthropology will be stitching aerial data sets from Mexico. © 2017 Copyright held by the owner/author(s).","bibtype":"inproceedings","author":"Gniady, T and Ruan, G and Sherman, W and Tuna, E and Wernert, E","doi":"10.1145/3093338.3104174","booktitle":"Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact (PEARC17)","bibtex":"@inproceedings{\n title = {Scalable photogrammetry with high performance computing},\n type = {inproceedings},\n year = {2017},\n keywords = {Benchmarking,Compute resources,Cultural heritages,Graduate s,Photogrammetry,Students},\n pages = {3},\n volume = {Part F1287},\n websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025826260&doi=10.1145%2F3093338.3104174&partnerID=40&md5=3d7c365c1289d519e724ab1c35dfad07},\n publisher = {Association for Computing Machinery},\n id = {1b613bc0-0610-3573-badb-6c05df967054},\n created = {2018-08-09T16:38:15.973Z},\n file_attached = {false},\n profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},\n group_id = {27e0553c-8ec0-31bd-b42c-825b8a5a9ae8},\n last_modified = {2019-08-27T16:51:40.266Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Gniady2017},\n source_type = {conference},\n notes = {cited By 0; Conference of 2017 Practice and Experience in Advanced Research Computing, PEARC 2017 ; Conference Date: 9 July 2017 Through 13 July 2017; Conference Code:128771},\n private_publication = {false},\n abstract = {Photogrammetry is used to build 3-dimensional models of everything from terrains to ancient statues. In the past, the stitching process was done on powerful PCs and could take weeks for large datasets. Even relatively small objects often required several hours to stitch together. With the availability of parallel processing options in the latest release of Agisoft PhotoScan, it is possible to leverage the power of high performance computing on large datasets. This poster presents the results of benchmarking tests for three datasets processed at two different model quality levels, medium and high (there are four times more points in the dense point cloud at the high setting) using 2, 4, 8, and 16 nodes. The purpose of the benchmarking is to determine how to optimize software license usage and compute resources against time and output quality. The poster also details the matrix of user-specified parameters that have been built into the python script that submits the parallel jobs. These parameters have evolved through the assessment of needs of users who are using the HPC deployment of photogrammetry as a service.We are excited by the uptake of this new service around campus in different fields across multiple disciplines. A group of cultural heritage experts will be using the service from Italy this summer, and a graduate student in anthropology will be stitching aerial data sets from Mexico. © 2017 Copyright held by the owner/author(s).},\n bibtype = {inproceedings},\n author = {Gniady, T and Ruan, G and Sherman, W and Tuna, E and Wernert, E},\n doi = {10.1145/3093338.3104174},\n booktitle = {Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact (PEARC17)}\n}","author_short":["Gniady, T.","Ruan, G.","Sherman, W.","Tuna, E.","Wernert, E."],"urls":{"Website":"https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025826260&doi=10.1145%2F3093338.3104174&partnerID=40&md5=3d7c365c1289d519e724ab1c35dfad07"},"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibbaseid":"gniady-ruan-sherman-tuna-wernert-scalablephotogrammetrywithhighperformancecomputing-2017","role":"author","keyword":["Benchmarking","Compute resources","Cultural heritages","Graduate s","Photogrammetry","Students"],"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["scalable","photogrammetry","high","performance","computing","gniady","ruan","sherman","tuna","wernert"],"keywords":["benchmarking","compute resources","cultural heritages","graduate s","photogrammetry","students"],"authorIDs":[],"dataSources":["zgahneP4uAjKbudrQ","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}