Curriculum learning-based strategy for low-density archaeological mound detection from historical maps in India and Pakistan
This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented...
Saved in:
Published in | Scientific reports Vol. 13; no. 1; p. 11257 |
---|---|
Main Authors | , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
England
Nature Publishing Group
12.07.2023
Nature Publishing Group UK Nature Portfolio |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km
, the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. |
---|---|
AbstractList | Abstract This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km2, the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km 2 , the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km2, the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. Abstract This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km 2 , the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km , the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map. |
ArticleNumber | 11257 |
Author | de Souza, Jonas Gregorio Petrie, Cameron A Gerrits, Petrus J Tomaney, Jack Suárez-Moreno, María Berganzo-Besga, Iban Khan, Afifa Alam, Aftab Campbell, Rosie Lumbreras, Felipe Orengo, Hector A Roberts, Rebecca C |
Author_xml | – sequence: 1 givenname: Iban surname: Berganzo-Besga fullname: Berganzo-Besga, Iban organization: Landscape Archaeology Research Group (GIAP), Catalan Institute of Classical Archaeology (ICAC), Pl. Rovellat s/n, 43003, Tarragona, Spain – sequence: 2 givenname: Hector A surname: Orengo fullname: Orengo, Hector A email: horengo@icac.cat, horengo@icac.cat organization: Catalan Institution for Research and Advanced Studies (ICREA), Passeig Lluís Companys 23, 08010, Barcelona, Spain. horengo@icac.cat – sequence: 3 givenname: Felipe surname: Lumbreras fullname: Lumbreras, Felipe organization: Computer Science Department, Computer Vision Center, Universitat Autònoma de Barcelona, Edifici O, Campus UAB, 08193, Bellaterra, Spain – sequence: 4 givenname: Aftab surname: Alam fullname: Alam, Aftab organization: Banaras Hindu University, Ajagara, Varanasi, Uttar Pradesh, 221005, India – sequence: 5 givenname: Rosie surname: Campbell fullname: Campbell, Rosie organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 6 givenname: Petrus J surname: Gerrits fullname: Gerrits, Petrus J organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 7 givenname: Jonas Gregorio surname: de Souza fullname: de Souza, Jonas Gregorio organization: Complexity and Socio-Ecological Dynamics (CaSEs) Research Group, Universitat Pompeu Fabra, Barcelona, Spain – sequence: 8 givenname: Afifa surname: Khan fullname: Khan, Afifa organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 9 givenname: María surname: Suárez-Moreno fullname: Suárez-Moreno, María organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 10 givenname: Jack surname: Tomaney fullname: Tomaney, Jack organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 11 givenname: Rebecca C surname: Roberts fullname: Roberts, Rebecca C organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing St., Cambridge, CB2 3ER, UK – sequence: 12 givenname: Cameron A surname: Petrie fullname: Petrie, Cameron A organization: Department of Archaeology, University of Cambridge, Downing St., Cambridge, CB2 3DZ, UK |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37438385$$D View this record in MEDLINE/PubMed |
BookMark | eNpdUstuFDEQHKEgEkJ-gAOyxIXLgJ8z9gmhiMdKkeAAZ6vHj10vM_Ziz4SsxMfj7IYowRdbrupqu7qeNycxRdc0Lwl-SzCT7wonQskWU9YySRRub540ZxRz0VJG6cmD82lzUcoW1yWo4kQ9a05Zz5lkUpw1fy6XnINZxmVCo4McQ1y3AxRnUZkzzG69Rz5lNKbfrXWxhHmPIJsNuDSmdTAwoikt0SLrZmfmkCLyOU1oE8qc8hGHXUEholW0ARBU7jf4WWGIL5qnHsbiLu728-bHp4_fL7-0V18_ry4_XLWGq35uFZe9EHQQlCveccWk6pUxFqAjHgPtzNBh6buOd95y2xPvuQdghvLBDb5j583qqGsTbPUuhwnyXicI-nCR8lpDnoMZnfac9WCVwIzZ2hwkplxI4dmglKSMVa33R63dMkzOGherTeMj0cdIDBu9Tte6Tq06TklVeHOnkNOvxZVZT6EYN44QXVqKppJ1sg4I31Jf_0fdpiXH6tWBRZhSRFQWPbJMTqVk5-9fQ_BtW6mPYdE1LPoQFn1Ti149_Md9yb9osL98u73j |
CitedBy_id | crossref_primary_10_1108_JD_05_2022_0096 crossref_primary_10_1002_arp_1926 crossref_primary_10_1038_d44151_023_00106_z |
Cites_doi | 10.1016/j.jas.2015.10.008 10.1109/TPAMI.2016.2577031 10.3390/geosciences9010021 10.1109/CVPR.2015.7298965 10.1016/j.jas.2022.105654 10.1002/arp.1807 10.1002/arp.1822 10.1016/j.patcog.2019.02.023 10.3390/land11111964 10.3390/geosciences9010011 10.1007/s11263-022-01611-x 10.1109/ICCV.2017.322 10.1109/ICCV.2015.169 10.1145/1007730.1007735 10.1016/j.jas.2021.105433 10.3390/rs12030500 10.3390/rs13204181 10.3390/rs11182089 10.1145/3343031.3350535 |
ContentType | Journal Article |
Copyright | 2023. The Author(s). The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. The Author(s) 2023 |
Copyright_xml | – notice: 2023. The Author(s). – notice: The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: The Author(s) 2023 |
DBID | NPM AAYXX CITATION 3V. 7X7 7XB 88A 88E 88I 8FE 8FH 8FI 8FJ 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. LK8 M0S M1P M2P M7P PIMPY PQEST PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA |
DOI | 10.1038/s41598-023-38190-x |
DatabaseName | PubMed CrossRef ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Biology Database (Alumni Edition) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni Edition) ProQuest Central ProQuest Central Essentials Biological Science Collection ProQuest Central ProQuest Natural Science Collection ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Biological Sciences Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) Science Database Biological Science Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
DatabaseTitle | PubMed CrossRef Publicly Available Content Database ProQuest Central Student ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection ProQuest Central China ProQuest Biology Journals (Alumni Edition) ProQuest Central Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Biological Science Collection ProQuest Medical Library (Alumni) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest Central (Alumni) MEDLINE - Academic |
DatabaseTitleList | Publicly Available Content Database CrossRef PubMed |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Biology |
EISSN | 2045-2322 |
EndPage | 11257 |
ExternalDocumentID | oai_doaj_org_article_f437ad95033d497a8024585f3b998233 10_1038_s41598_023_38190_x 37438385 |
Genre | Journal Article |
GeographicLocations | Pakistan India |
GeographicLocations_xml | – name: India – name: Pakistan |
GrantInformation_xml | – fundername: ; |
GroupedDBID | 0R~ 3V. 4.4 53G 5VS 7X7 88A 88E 88I 8FE 8FH 8FI 8FJ AAFWJ AAJSJ AAKDD ABDBF ABUWG ACGFS ACSMW ADBBV ADRAZ AENEX AFKRA AFPKN AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ BVXVI C6C CCPQU DIK DWQXO EBD EBLON EBS ESX FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE KQ8 LK8 M0L M1P M2P M48 M7P M~E NAO NPM OK1 PIMPY PQQKQ PROAC PSQYO RIG RNT RNTTT RPM SNYQT UKHRP AAYXX CITATION 7XB 8FK K9. PQEST PQUKI PRINS Q9U 7X8 5PM |
ID | FETCH-LOGICAL-c497t-9487552b5249464938979ccdaa61f0a26cb608f6646fd4d71ff4faa3c24bebf63 |
IEDL.DBID | RPM |
ISSN | 2045-2322 |
IngestDate | Thu Sep 05 15:48:16 EDT 2024 Tue Sep 17 21:30:15 EDT 2024 Tue Aug 27 04:39:46 EDT 2024 Fri Sep 13 10:50:19 EDT 2024 Fri Aug 23 01:50:24 EDT 2024 Sat Sep 28 08:09:43 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Language | English |
License | 2023. The Author(s). Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c497t-9487552b5249464938979ccdaa61f0a26cb608f6646fd4d71ff4faa3c24bebf63 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10338521/ |
PMID | 37438385 |
PQID | 2836139915 |
PQPubID | 2041939 |
PageCount | 1 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_f437ad95033d497a8024585f3b998233 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10338521 proquest_miscellaneous_2836874301 proquest_journals_2836139915 crossref_primary_10_1038_s41598_023_38190_x pubmed_primary_37438385 |
PublicationCentury | 2000 |
PublicationDate | 2023-07-12 |
PublicationDateYYYYMMDD | 2023-07-12 |
PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-12 day: 12 |
PublicationDecade | 2020 |
PublicationPlace | England |
PublicationPlace_xml | – name: England – name: London |
PublicationTitle | Scientific reports |
PublicationTitleAlternate | Sci Rep |
PublicationYear | 2023 |
Publisher | Nature Publishing Group Nature Publishing Group UK Nature Portfolio |
Publisher_xml | – name: Nature Publishing Group – name: Nature Publishing Group UK – name: Nature Portfolio |
References | A Luque (38190_CR23) 2019; 91 AS Green (38190_CR3) 2019; 11 38190_CR20 38190_CR22 38190_CR21 HA Orengo (38190_CR9) 2021; 28 S Ren (38190_CR18) 2016; 39 I Berganzo-Besga (38190_CR5) 2022; 11 38190_CR6 A Garcia-Molsosa (38190_CR10) 2021; 28 I Berganzo-Besga (38190_CR25) 2022; 148 HA Orengo (38190_CR26) 2015; 2015 38190_CR7 DS Davis (38190_CR8) 2021; 132 38190_CR17 38190_CR16 38190_CR19 CA Petrie (38190_CR1) 2019; 9 A Garcia-Molsosa (38190_CR2) 2019; 9 W Verschoof van der Vaart (38190_CR12) 2022; 2022 38190_CR13 GEAPA Batista (38190_CR24) 2004; 6 I Berganzo-Besga (38190_CR4) 2021; 13 38190_CR15 M Soroush (38190_CR11) 2020; 12 38190_CR14 |
References_xml | – volume: 2015 start-page: 100 issue: 64 year: 2015 ident: 38190_CR26 publication-title: J. Archaeol. Sci. doi: 10.1016/j.jas.2015.10.008 contributor: fullname: HA Orengo – volume: 39 start-page: 1137 year: 2016 ident: 38190_CR18 publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2577031 contributor: fullname: S Ren – volume: 9 start-page: 21 year: 2019 ident: 38190_CR2 publication-title: Geosciences doi: 10.3390/geosciences9010021 contributor: fullname: A Garcia-Molsosa – ident: 38190_CR19 doi: 10.1109/CVPR.2015.7298965 – volume: 148 start-page: 105654 year: 2022 ident: 38190_CR25 publication-title: J. Archaeol. Sci. doi: 10.1016/j.jas.2022.105654 contributor: fullname: I Berganzo-Besga – volume: 28 start-page: 187 year: 2021 ident: 38190_CR10 publication-title: Archaeol. Prospect. doi: 10.1002/arp.1807 contributor: fullname: A Garcia-Molsosa – volume: 28 start-page: 1 year: 2021 ident: 38190_CR9 publication-title: Archaeol. Prospect. doi: 10.1002/arp.1822 contributor: fullname: HA Orengo – ident: 38190_CR14 – volume: 91 start-page: 216 year: 2019 ident: 38190_CR23 publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.02.023 contributor: fullname: A Luque – volume: 11 start-page: 1964 year: 2022 ident: 38190_CR5 publication-title: Land doi: 10.3390/land11111964 contributor: fullname: I Berganzo-Besga – ident: 38190_CR13 – volume: 9 start-page: 11 year: 2019 ident: 38190_CR1 publication-title: Geosciences doi: 10.3390/geosciences9010011 contributor: fullname: CA Petrie – ident: 38190_CR7 – ident: 38190_CR21 doi: 10.1007/s11263-022-01611-x – volume: 2022 start-page: 1 year: 2022 ident: 38190_CR12 publication-title: Archaeol. Prospect. contributor: fullname: W Verschoof van der Vaart – ident: 38190_CR16 doi: 10.1109/ICCV.2017.322 – ident: 38190_CR17 doi: 10.1109/ICCV.2015.169 – volume: 6 start-page: 20 issue: 1 year: 2004 ident: 38190_CR24 publication-title: ACM SIGKDD Explor. Newslett. doi: 10.1145/1007730.1007735 contributor: fullname: GEAPA Batista – volume: 132 start-page: 105433 year: 2021 ident: 38190_CR8 publication-title: J. Archaeol. Sci. doi: 10.1016/j.jas.2021.105433 contributor: fullname: DS Davis – volume: 12 start-page: 500 year: 2020 ident: 38190_CR11 publication-title: Remote Sens. doi: 10.3390/rs12030500 contributor: fullname: M Soroush – ident: 38190_CR15 – volume: 13 start-page: 4181 year: 2021 ident: 38190_CR4 publication-title: Remote Sens. doi: 10.3390/rs13204181 contributor: fullname: I Berganzo-Besga – volume: 11 start-page: 2089 year: 2019 ident: 38190_CR3 publication-title: Remote Sens. doi: 10.3390/rs11182089 contributor: fullname: AS Green – ident: 38190_CR20 doi: 10.1145/3343031.3350535 – ident: 38190_CR22 – ident: 38190_CR6 |
SSID | ssj0000529419 |
Score | 2.452899 |
Snippet | This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps.... Abstract This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical... Abstract This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical... |
SourceID | doaj pubmedcentral proquest crossref pubmed |
SourceType | Open Website Open Access Repository Aggregation Database Index Database |
StartPage | 11257 |
SubjectTerms | Algorithms Curricula Landscape Mounds Surveys Urban sprawl |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PSx0xEA4iFLyU1tp2W5UUvElwN8lmk2MrFVtoTwreQrJJqlDzxLdSH_jHO0n2Le9JwYvXzQ-SzGTnm2TyDUIHgQUXBDekt9QQLlxNwI0QJHRG9rQ3qss83b9-i9Nz_vOivVhJ9ZViwgo9cFm4o8BZZ5xKt22OK-gh3RXKNjALjgJlheezaVecqcLqTRVv1PhKpmbyaA6WKr0mo4wkJ6Um92uWKBP2_w9lPg2WXLE-J2_Q6xE24q9luG_Rho_b6FVJJLl4hx6Op5M8POaB-EOSgXJ4XuhnFxjQKf47-0dcClkfFjizJPnlvw9fp_xK2Pkhx2ZFnN6d4MuJRARfm5s5vor4RwSNwgbqjuAz7qDzk-9nx6dkzKtAeljBgajkpLTUtuB6ccEVYJZO9b0zRjShNlT0VtQyCMFFcNx1TQg8GMN6yq23QbD3aDPOov-IMO8ka4zwnVEW-vZWtI5LC26PlQFkVKHD5Rrrm0KfofO1N5O6SESDRHSWiL6v0Lckhqlmor7OH0Ah9KgQ-jmFqNDuUoh63I9zDSAKcAtg4bZCX6Zi2EnpesREP7srdSQAqrqp0Ici82kkrEuUrhJayzVtWBvqekm8usxs3TBXaEibTy8xuc9oK-W7T4fLDd1Fm8Ptnd8DVDTY_bwBHgHjUQqH priority: 102 providerName: Directory of Open Access Journals – databaseName: Health & Medical Collection dbid: 7X7 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwELZKERIXxLuBgozEDVmb2I7tnBBUVAsSnKi0t8iPuK1Ek6Wbiq7UH98Z5wGLENfETpzM2PPNjP0NIW-jiCEqaZl33DKpQs7AjVAsams897bSiaf76ze1PJFfVuVqjyynszC4rXJaE9NCHTqPMfIFmEGwPIBmyoV1GAXw_eL9-ifD-lGYZx2LadwhdwsOsAI0W6_0HG3BfJYsqvHUTC7MYgOWC0-XccHQacnZ9Y5lSgT-_0Kdf2-e_MMaHT8kD0YYST8Mcn9E9pr2Mbk3FJbcPiE3R3Nkj451IU4ZGqxANwMd7ZYCWqU_ul8s4Bb2fksTa1IzrYX0Aust0dD0aa9WS_EcCj2bSUXohV1v6HlLP7egYdRC2xGMtk_JyfGn70dLNtZZYF5WumcVOi0ldyW4YlLJCjCMrrwP1qoi5pYr71RuolJSxSCDLmKU0VrhuXSNi0o8I_tt1zYHhEptRGFVo23l4NmNU2WQxoEb5EyMwmXk3fSP6_VAp1GnNLgw9SCRGiRSJ4nU1xn5iGKYWyIVdrrQXZ7W48yqoxTahgrTsQFeaQ0mk00JLwNPkguRkcNJiPU4Pzf1b23KyJv5NswsTJfYtumuhjYGAFZeZOT5IPN5JEIjxauB3mZHG3aGununPT9L7N3wrdCRFy_-P66X5D5WtscwcsEPyX5_edW8AvzTu9dJtW8BYaYHbw priority: 102 providerName: ProQuest – databaseName: Scholars Portal Open Access Journals dbid: M48 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1La9wwEBYhodBL6btuk6JCb0WtLcl6HEpIQ0NaSE9dyE1IlpQEEm-y69As5MdnZNmmW_bYqyVZj5nxfGNJ3yD0MbLoo-CWNI5awoUvCYQRgkRpVUMbq2XP033ySxzP-M_T-nQLjemOhgVcbgztUj6p2eLy893Nah8M_mu-Mq6-LMEJpYtilJEUf5QEMOUO5YwnjT8Z4H7m-qaaV3q4O7O56Zp_6mn8N2HPf49Q_uWTjp6iJwOYxAdZ-s_QVmifo0c5veTqBbo_nP7v4SE7xBlJbsvjZSalXWHArPhy_of4dJC9W-GeOymMX0R8lbIuYR-6_sRWi9NtFHw-UYvgK3u9xBct_tGCnmELdQdI2r5Es6Pvvw-PyZBtgTRcy47oFLrU1NUQkHHBNSAZqZvGWyuqWFoqGidKFYXgInruZRUjj9ayhnIXXBTsFdpu5214gzCXilVWBGm1g3cHJ2rPlYNgyKkYmSvQp3GNzXUm1TD9ZjhTJkvEgERMLxFzV6BvSQxTzUSI3T-YL87MYF8mciat12lT1kOXVqUtZVVDZxBPUsYKtDsK0YxKZgBaAZoBhFwX6MNUDPaVNk1sG-a3uY4CmFVWBXqdZT6NhMlE9KqgtVrThrWhrpe0F-c9hzfMFRrS6u3_mNw79JgmFU58n3QXbXeL27AHWKlz73sDeACxpRNZ priority: 102 providerName: Scholars Portal |
Title | Curriculum learning-based strategy for low-density archaeological mound detection from historical maps in India and Pakistan |
URI | https://www.ncbi.nlm.nih.gov/pubmed/37438385 https://www.proquest.com/docview/2836139915/abstract/ https://search.proquest.com/docview/2836874301 https://pubmed.ncbi.nlm.nih.gov/PMC10338521 https://doaj.org/article/f437ad95033d497a8024585f3b998233 |
Volume | 13 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3da9swEBdtx2AvY9_z1gUN9jbU2JYsyY9raOkGKWWskDehD6sNNEpoUrbA_vid5A-Ssae9-MGSLeE7-X6nO_0OoU-eeuc508SaUhPGXU7AjeDECy1taXUtEk_39JJfXLNvs2p2gHh_FiYl7VszPwl3i5Mwv025lauFHfd5YuOr6aTIwbECuzM-RIeC0h0fvWX0LmtW1N0JmZzK8RqsVDxJVlISHZScRPZpKiJLZ6yhvGOQEm__v8Dm3zmTO0bo_Bl62qFH_KWd5XN00IQX6HFbT3L7Ev2eDBt6uCsHcUOinXJ43bLQbjGAVHy3_ElczFzfbHEiS2r6XyBexDJL2DWblKIVcDx-gm8HLhG80Ks1ngf8NYBiYQ19OwwaXqHr87MfkwvSlVcgltViQ-roq1SlqcADY5zVAF1Eba3Tmhc-1yW3hufSc864d8yJwnvmtaa2ZKYxntPX6CgsQ_MWYSYkLTRvhK4NvLsxvHJMGvB-jPSemgx97r-xWrUsGipFv6lUrXAUCEcl4ahfGTqNYhh6RgbsdGN5f6M6PVCeUaFdHaOwDobUMsaQZQWDgQNZUpqh416IqluWawVYCuALQOIqQx-HZlhQMUqiQ7N8aPtI0I28yNCbVubDTHqdyZDc04a9qe63gA4n0u5eZ9_9_6Pv0ZNY7D7uLBflMTra3D80HwASbcwI1sFMjNCj07PLq--jtLEA1ymTo7Q2_gDTExFN |
link.rule.ids | 230,315,733,786,790,870,891,2115,12083,21416,24346,27957,27958,31754,31755,33779,33780,43345,43840,53827,53829,74102,74659 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwELagCMEF8SZQwEjckNUkdmznhKCi2kLbUyvtzbLjuK3UJks3FV2JH8-M4w0sQlxjO3YyY8_T3xDyPvDggxSWNa60TEifMzAjJAvK6qZsbK0iTvfhkZydiK_zap4cbsuUVrk-E-NB7fsGfeQ7IAZB8oA2U31cfGdYNQqjq6mExm1yR3AuMKVPzdXkY8EolijqdFcm53pnCfIK75SVnKGpkrObDXkUYfv_pWv-nTL5hwzae0geJOWRfhqp_YjcarvH5O5YTnL1hPzcnfx5NFWDOGUopjxdjiC0Kwo6Kr3ofzCPievDikaspHZ9AtJLrLJEfTvEDK2O4u0TejZBidBLu1jS847ud8BX1ELfpIJ2T8nJ3pfj3RlL1RVYI2o1sBpNlap0FRhgQooaNBdVN423VhYht6VsnMx1kFLI4IVXRQgiWMubUrjWBcmfka2u79oXhAqleWFlq2zt4N2tk5UX2oHx43QI3GXkw_ofm8UIomFi8JtrM1LEAEVMpIi5ychnJMPUEwGw44P-6tSk_WSC4Mr6GoOwHqa0GkPIuoLJwH4sOc_I9pqIJu3KpfnNQxl5NzXDfsIgie3a_nrso0GtyouMPB9pPq2EKwR21TBab3DDxlI3W7rzs4jZDd8KA8vi5f_X9Zbcmx0fHpiD_aNvr8h9rG2PjuSi3CZbw9V1-xo0oMG9iWz-C2zTBqI |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwELagFagXxLMEChiJG7I2iR3bOSFaump5rCpEpd4sO47bSjTZdlPRlfjxzCTewCLENbZjJzP2PP0NIW8CDz5IYVnlcsuE9CkDM0KyoKyu8sqWqsfp_jKTB8fi40lxEvOfFjGtcnUm9ge1byv0kU9ADILkAW2mmISYFnH0YfpufsmwghRGWmM5jdtkUwlZAIdv7u7Pjr6OHheMaYmsjDdnUq4nC5BeeMMs5wwNl5TdrEmnHsT_X5rn3wmUf0ik6X1yL6qS9P1A-wfkVt08JHeG4pLLR-Tn3ujdo7E2xClDoeXpYoCkXVLQWOn39gfzmMbeLWmPnFSvzkN6gTWXqK-7Pl-roXgXhZ6NwCL0ws4X9Lyhhw1wGbXQNyqkzWNyPN3_tnfAYq0FVolSdaxEw6XIXQHmmJCiBD1GlVXlrZVZSG0uKydTHaQUMnjhVRaCCNbyKheudkHyJ2SjaZv6KaFCaZ5ZWStbOnh37WThhXZgCjkdAncJebv6x2Y-QGqYPhTOtRkoYoAipqeIuUnILpJh7Ilw2P2D9urUxN1lguDK-hJDsh6mtBoDyrqAycCazDlPyM6KiCbu0YX5zVEJeT02w-7CkIlt6vZ66KNByUqzhGwPNB9XwhXCvGoYrde4YW2p6y3N-VmP4A3fCgPz7Nn_1_WK3AUeN58PZ5-eky0sdI9e5SzfIRvd1XX9AtShzr2MfP4LLTgMRQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Curriculum+learning-based+strategy+for+low-density+archaeological+mound+detection+from+historical+maps+in+India+and+Pakistan&rft.jtitle=Scientific+reports&rft.au=Iban+Berganzo-Besga&rft.au=Hector+A.+Orengo&rft.au=Felipe+Lumbreras&rft.au=Aftab+Alam&rft.date=2023-07-12&rft.pub=Nature+Portfolio&rft.eissn=2045-2322&rft.volume=13&rft.issue=1&rft.spage=1&rft.epage=15&rft_id=info:doi/10.1038%2Fs41598-023-38190-x&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_f437ad95033d497a8024585f3b998233 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2045-2322&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2045-2322&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2045-2322&client=summon |