Show simple item record

dc.contributor.authorGao, Xin
dc.date.accessioned2019-03-12T19:48:19Z
dc.date.available2019-03-12T19:48:19Z
dc.date.issued2018
dc.identifier.citationGao, X. (2018). Vehicle detection in wide-area aerial imagery: cross-association of detection schemes with post-processings. International Journal of Image Mining, 3(2), 106-116.en_US
dc.identifier.issn2055-6039
dc.identifier.issn2055-6047
dc.identifier.doi10.1504/IJIM.2018.10017603
dc.identifier.urihttp://hdl.handle.net/10150/631838
dc.description.abstractPost-processing schemes are crucial for object detection algorithms to improve the performance of detection in wide-area aerial imagery. We select appropriate parameters for three algorithms (variational minimax optimisation (Saha and Ray, 2009), feature density estimation (Gleason et al., 2011) and Zheng's scheme by morphological filtering (Zheng et al., 2013)) to achieve the highest average F-score on random sample frames, and then follow the same procedure to implement five post-processing schemes on each algorithm. Two low-resolution aerial videos are used as our datasets to compare automatic detection results with the ground truth objects on each frame. The performance analysis of post-processing schemes on each algorithm are presented under two sets of evaluation metrics.en_US
dc.language.isoenen_US
dc.publisherINDERSCIENCE ENTERPRISES LTDen_US
dc.relation.urlhttp://www.inderscience.com/link.php?id=10017603en_US
dc.rightsCopyright © 2018 Inderscience Enterprises Ltd.en_US
dc.subjectpost-processingen_US
dc.subjectobject detectionen_US
dc.subjectwide-area aerial imageryen_US
dc.titleVehicle detection in wide-area aerial imagery: cross-association of detection schemes with post-processingsen_US
dc.typeArticleen_US
dc.contributor.departmentUniv Arizona, Dept Elect & Comp Engnen_US
dc.identifier.journalInternational Journal of Image Miningen_US
dc.description.note12 month embargo; available online: 18 Nov 2018en_US
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en_US
dc.eprint.versionFinal accepted manuscripten_US
dc.source.journaltitleInternational Journal of Image Mining
dc.source.volume3
dc.source.issue2
dc.source.beginpage106


Files in this item

Thumbnail
Name:
IJIM2018Vehicle_Paper.pdf
Size:
407.5Kb
Format:
PDF
Description:
Final Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record