Show simple item record

dc.contributor.authorMotorcu, Hakkı
dc.contributor.authorAteş, Hasan Fehmi
dc.contributor.authorUğurdağ, Hasan Fatih
dc.contributor.authorGüntürk, Bahadır Kürşat
dc.date.accessioned2022-01-13T07:14:39Z
dc.date.available2022-01-13T07:14:39Z
dc.date.issued2022en_US
dc.identifier.citationMotorcu, H., Ateş, H. F., Uğurdağ, H. F. ve Güntürk, B. K. (2022). HM-net: A regression network for object center detection and tracking on wide area motion imagery. IEEE Access, 10, 1346-1359. https://doi.org/10.1109/ACCESS.2021.3138980en_US
dc.identifier.issn2169-3536
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2021.3138980
dc.identifier.urihttps://hdl.handle.net/20.500.12511/8793
dc.description.abstractWide Area Motion Imagery (WAMI) yields high resolution images with a large number of extremely small objects. Target objects have large spatial displacements throughout consecutive frames. This nature of WAMI images makes object tracking and detection challenging. In this paper, we present our deep neural network-based combined object detection and tracking model, namely, Heat Map Network (HM-Net). HM-Net is significantly faster than state-of-the-art frame differencing and background subtraction-based methods, without compromising detection and tracking performances. HM-Net follows object center-based joint detection and tracking paradigm. Simple heat map-based predictions support unlimited number of simultaneous detections. The proposed method uses two consecutive frames and the object detection heat map obtained from the previous frame as input, which helps HM-Net monitor spatio-temporal changes between frames and keep track of previously predicted objects. Although reuse of prior object detection heat map acts as a vital feedback-based memory element, it can lead to unintended surge of false positive detections. To increase robustness of the method against false positives and to eliminate low confidence detections, HM-Net employs novel feedback filters and advanced data augmentations. HM-Net outperforms state-of-the-art WAMI moving object detection and tracking methods on WPAFB dataset with its 96.2% F1 and 94.4% mAP detection scores, while achieving 61.8 % mAP tracking score on the same dataset. This performance corresponds to an improvement of 2.1% for F1, 6.1% for mAP scores on detection, and 9.5% for mAP score on tracking over state-of-the-art.en_US
dc.language.isoengen_US
dc.publisherIEEE-Institute of Electrical and Electronics Engineers Inc.en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution 4.0 International*
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/*
dc.subjectTrackingen_US
dc.subjectObject Detectionen_US
dc.subjectHeating Systemsen_US
dc.subjectTarget Trackingen_US
dc.subjectDistortionen_US
dc.subjectConvolutional Neural Networksen_US
dc.subjectCamerasen_US
dc.subjectDeep Neural Networksen_US
dc.titleHM-net: A regression network for object center detection and tracking on wide area motion imageryen_US
dc.typearticleen_US
dc.relation.ispartofIEEE Accessen_US
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümüen_US
dc.authorid0000-0002-6842-1528en_US
dc.authorid0000-0003-0779-9620en_US
dc.identifier.volume10en_US
dc.identifier.startpage1346en_US
dc.identifier.endpage1359en_US
dc.relation.tubitakinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/118E891
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.doi10.1109/ACCESS.2021.3138980en_US
dc.identifier.wosqualityQ2en_US
dc.identifier.scopusqualityQ1en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess