DisCountNet: Discriminating and counting network for real-time counting and localization of sparse objects in high-resolution UAV imagery

Simple item page
dc.contributor.authorRahnemoonfar, Maryam
dc.contributor.authorDobbs, Dugan
dc.contributor.authorYari, Masoud
dc.contributor.authorStarek, Michael J.
dc.creator.orcidhttps://orcid.org/0000-0001-9358-2836en_US
dc.creator.orcidhttps://orcid.org/0000-0003-3524-4358en_US
dc.creator.orcidhttps://orcid.org/0000-0002-9949-8683en_US
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594en_US
dc.creator.orcidhttps://orcid.org/0000-0001-9358-2836
dc.creator.orcidhttps://orcid.org/0000-0003-3524-4358
dc.creator.orcidhttps://orcid.org/0000-0002-9949-8683
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594
dc.creator.orcidhttps://orcid.org/0000-0001-9358-2836
dc.creator.orcidhttps://orcid.org/0000-0003-3524-4358
dc.creator.orcidhttps://orcid.org/0000-0002-9949-8683
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594https://orcid.org/0000-0001-9358-2836
dc.creator.orcidhttps://orcid.org/0000-0003-3524-4358
dc.creator.orcidhttps://orcid.org/0000-0002-9949-8683
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594
dc.date.accessioned2021-10-27T21:42:28Z
dc.date.available2021-10-27T21:42:28Z
dc.date.issued2019-05-11
dc.description.abstractRecent deep-learning counting techniques revolve around two distinct features of data—sparse data, which favors detection networks, or dense data where density map networks are used. Both techniques fail to address a third scenario, where dense objects are sparsely located. Raw aerial images represent sparse distributions of data in most situations. To address this issue, we propose a novel and exceedingly portable end-to-end model, DisCountNet, and an example dataset to test it on. DisCountNet is a two-stage network that uses theories from both detection and heat-map networks to provide a simple yet powerful design. The first stage, DiscNet, operates on the theory of coarse detection, but does so by converting a rich and high-resolution image into a sparse representation where only important information is encoded. Following this, CountNet operates on the dense regions of the sparse matrix to generate a density map, which provides fine locations and count predictions on densities of objects. Comparing the proposed network to current state-of-the-art networks, we find that we can maintain competitive performance while using a fraction of the computational complexity, resulting in a real-time solution.en_US
dc.description.abstractRecent deep-learning counting techniques revolve around two distinct features of data—sparse data, which favors detection networks, or dense data where density map networks are used. Both techniques fail to address a third scenario, where dense objects are sparsely located. Raw aerial images represent sparse distributions of data in most situations. To address this issue, we propose a novel and exceedingly portable end-to-end model, DisCountNet, and an example dataset to test it on. DisCountNet is a two-stage network that uses theories from both detection and heat-map networks to provide a simple yet powerful design. The first stage, DiscNet, operates on the theory of coarse detection, but does so by converting a rich and high-resolution image into a sparse representation where only important information is encoded. Following this, CountNet operates on the dense regions of the sparse matrix to generate a density map, which provides fine locations and count predictions on densities of objects. Comparing the proposed network to current state-of-the-art networks, we find that we can maintain competitive performance while using a fraction of the computational complexity, resulting in a real-time solution.
dc.identifier.citationRahnemoonfar, M., Dobbs, D., Yari, M. and Starek, M.J., 2019. DisCountNet: Discriminating and counting network for real-time counting and localization of sparse objects in high-resolution UAV imagery. Remote Sensing, 11(9), p.1128.en_US
dc.identifier.citationRahnemoonfar, M., Dobbs, D., Yari, M. and Starek, M.J., 2019. DisCountNet: Discriminating and counting network for real-time counting and localization of sparse objects in high-resolution UAV imagery. Remote Sensing, 11(9), p.1128.
dc.identifier.doihttps://doi.org/10.3390/rs11091128
dc.identifier.urihttps://hdl.handle.net/1969.6/89877
dc.language.isoen_USen_US
dc.language.isoen_US
dc.publisherMDPIen_US
dc.publisherMDPI
dc.rightsAttribution 4.0 International*
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectdeep-learningen_US
dc.subjectautomatic countingen_US
dc.subjectuaven_US
dc.subjectreal-timeen_US
dc.subjectdeep-learning
dc.subjectautomatic counting
dc.subjectuav
dc.subjectreal-time
dc.titleDisCountNet: Discriminating and counting network for real-time counting and localization of sparse objects in high-resolution UAV imageryen_US
dc.titleDisCountNet: Discriminating and counting network for real-time counting and localization of sparse objects in high-resolution UAV imagery
dc.typeArticleen_US
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Rahnemoonfar_Maryam_Remote-Sensing.pdf
Size:
33.11 MB
Format:
Adobe Portable Document Format
Description:
Article
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

COE Faculty Works