TentNet: Deep Learning Tent Detection Algorithm Using A Synthetic Training Approach
Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public health agencies would like to solve. For instance, it is important for the policy makers to know where homeless populations live so that they...
Saved in:
Published in | 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) pp. 860 - 867 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
11.10.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public health agencies would like to solve. For instance, it is important for the policy makers to know where homeless populations live so that they can provide necessary services accordingly. This article presents a satellite image tent-detection solution with three deep learning methods that utilize transfer learning from the ResNetV2, InceptionV3, and MobileNetV2 models, trained on ImageNet, attached to a unique architecture referred to as "TentNet". The performance of these models are first shown in detecting planes and ships within satellite imagery in previously defined datasets as a baseline. Then, a new dataset is created from a compilation of tents from the xView project to use for testing, along with another dataset of synthetic images from the generative adversarial networks StyleGAN2 and DCGAN for training. After training on a dataset containing only synthetic images for the tents class, the ResNetV2 architecture achieved the highest accuracy of 73.68% when testing on the real satellite imagery. |
---|---|
AbstractList | Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public health agencies would like to solve. For instance, it is important for the policy makers to know where homeless populations live so that they can provide necessary services accordingly. This article presents a satellite image tent-detection solution with three deep learning methods that utilize transfer learning from the ResNetV2, InceptionV3, and MobileNetV2 models, trained on ImageNet, attached to a unique architecture referred to as "TentNet". The performance of these models are first shown in detecting planes and ships within satellite imagery in previously defined datasets as a baseline. Then, a new dataset is created from a compilation of tents from the xView project to use for testing, along with another dataset of synthetic images from the generative adversarial networks StyleGAN2 and DCGAN for training. After training on a dataset containing only synthetic images for the tents class, the ResNetV2 architecture achieved the highest accuracy of 73.68% when testing on the real satellite imagery. |
Author | Mago, Vijay Fisher, Andrew Mohammed, Emad A. |
Author_xml | – sequence: 1 givenname: Andrew surname: Fisher fullname: Fisher, Andrew email: afisher3@lakeheadu.ca organization: Lakehead University,Dept. of Computer Science,Thunder Bay,Canada – sequence: 2 givenname: Emad A. surname: Mohammed fullname: Mohammed, Emad A. email: emohamme@lakeheadu.ca organization: Lakehead University,Dept. of Software Engineering,Thunder Bay,Canada – sequence: 3 givenname: Vijay surname: Mago fullname: Mago, Vijay email: vmago@lakeheadu.ca organization: Lakehead University,Dept. of Computer Science,Thunder Bay,Canada |
BookMark | eNotUMlOwzAUNAgk2tIvQEj-gQQvcWxzi0pZpACHpOfKsV9ao9aJEl_696TQ00izaTRzdBO6AAg9UpJSSvRT9bnKmJYiZYSRVDPFuZRXaKmlopIpqgTL2TWaMSFlQnMh7tB8HH_I5M6omqGqhhC_ID7jF4Ael2CG4MMOn-mJimCj7wIuDrtu8HF_xJvxLBe4OoW4h-gtrgfj_zJF3w-dsft7dNuawwjLCy7Q5nVdr96T8vvtY1WUiWeEx0Rw2TqpiJOcGiu5aKyeZjrROAaOGOdcmzmdO0JVLmne8FxzY5Wx3LWKtXyBHv57PQBs-8EfzXDaXj7gvwWtUuY |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/SMC42975.2020.9283377 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Xplore IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Statistics Sciences (General) |
EISBN | 9781728185262 1728185262 |
EISSN | 2577-1655 |
EndPage | 867 |
ExternalDocumentID | 9283377 |
Genre | orig-research |
GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI JC5 M43 OCL RIE RIL RIO RNS |
ID | FETCH-LOGICAL-i203t-537fd780d731ac735bc9257d5bd2ed0adddf4d96d0186716b3693ac8ac3df82f3 |
IEDL.DBID | RIE |
IngestDate | Wed Jun 26 19:26:38 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i203t-537fd780d731ac735bc9257d5bd2ed0adddf4d96d0186716b3693ac8ac3df82f3 |
PageCount | 8 |
ParticipantIDs | ieee_primary_9283377 |
PublicationCentury | 2000 |
PublicationDate | 2020-Oct.-11 |
PublicationDateYYYYMMDD | 2020-10-11 |
PublicationDate_xml | – month: 10 year: 2020 text: 2020-Oct.-11 day: 11 |
PublicationDecade | 2020 |
PublicationTitle | 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) |
PublicationTitleAbbrev | SMC |
PublicationYear | 2020 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0020418 |
Score | 2.2059355 |
Snippet | Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 860 |
SubjectTerms | Convolutional Neural Networks Deep learning Generative Adversarial Networks (GAN) Homelessness Public healthcare Satellites Sociology Statistics Synthetic Dataset Testing Training |
Title | TentNet: Deep Learning Tent Detection Algorithm Using A Synthetic Training Approach |
URI | https://ieeexplore.ieee.org/document/9283377 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED6VTmWBPhBveWAAiaROnMQJW1WoKqRWSG2lbpVfKRWQViUd4NdjJ6Y8xMCWnGQnsuN8d_Z93wFc6KAnTaUQji8ZM7tV3OEB07cqiFKNYIJGhu88GEb9SXA_DacVuN5yYZRSRfKZcs1lcZYvl2JjtsraicZCQukO7MTYL7la2-AKB15sGToeTtqjQTcwpFEdAfrYtQ1_VFApAKS3B4PPR5d5I0_uJueueP-lyvjfd9uH1hdVDz1sQagOFZU1YPebymAD6nb9vqJLKzJ91YCa8TJLkeYmjMa676HKb9CtUitkNVfnyJi1KS_StTLUeZ4v14v88QUViQaog0ZvmXYgdSdobEtNoI4VKW_BpHc37vYdW23BWfiY5E5IaCppjCUlHhOUhFwkej3LkEtfSaz_gzINZBJJXGjiRZxECWEiZoLINPZTcgDVbJmpQ0CCcSZV7LNU0UAFHpfaC9ATEZJEt4nJETTNAM5WpaDGzI7d8d_mE6iZSTSA4XmnUM3XG3WmPYGcnxefwAcURrQL |
link.rule.ids | 310,311,786,790,795,796,802,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8JAEJ4gHsSLghrf7sGDJhbabp_eCGpQgZiAiTeyryJRC8Fy0F_vbLviIx68tdPsttnt9pvZzvcNwDEGPUkihbBcyZjereIW9xieKi9IEMFEGGi-c7cXtO-9mwf_oQRnCy6MUipPPlN1fZj_y5cTMddbZY0YsZCG4RIsI87bccHWWoRXtudEhqODFxv9bsvTtFGMAV27bpr-qKGSQ8jVGnQ_b15kjjzV5xmvi_dfuoz_fbp12Pwi65G7BQxVoaTSGqx-0xmsQdWs4FdyYmSmT2tQ0X5mIdO8Af0B9t1T2Tm5UGpKjOrqiGgzmrI8YSslzefRZDbOHl9InmpAmqT_lqILiZ2QgSk2QZpGpnwT7q8uB622ZeotWGPXppnl0zCRYWTLkDpMhNTnIsYVLX0uXSVt_BLKxJNxIO1cFS_gNIgpExETVCaRm9AtKKeTVG0DEYwzqSKXJSr0lOdwiX4AToRPY2wT0R3Y0AM4nBaSGkMzdrt_m49gpT3odoad697tHlT0hGr4cJx9KGezuTpAvyDjh_nr8AHCvrdh |
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%3Abook&rft.genre=proceeding&rft.title=2020+IEEE+International+Conference+on+Systems%2C+Man%2C+and+Cybernetics+%28SMC%29&rft.atitle=TentNet%3A+Deep+Learning+Tent+Detection+Algorithm+Using+A+Synthetic+Training+Approach&rft.au=Fisher%2C+Andrew&rft.au=Mohammed%2C+Emad+A.&rft.au=Mago%2C+Vijay&rft.date=2020-10-11&rft.pub=IEEE&rft.eissn=2577-1655&rft.spage=860&rft.epage=867&rft_id=info:doi/10.1109%2FSMC42975.2020.9283377&rft.externalDocID=9283377 |