Show simple item record

dc.contributor.authorYu, L
dc.contributor.authorLuo, C
dc.contributor.authorYu, X
dc.contributor.authorJiang, X
dc.contributor.authorYang, E
dc.contributor.authorLuo, C
dc.contributor.authorRen, P
dc.date.accessioned2019-02-26T12:58:18Z
dc.date.issued2018-05-16
dc.description.abstractVision-based techniques are widely used in micro aerial vehicle autonomous landing systems. Existing vision-based autonomous landing schemes tend to detect specific landing landmarks by identifying their straightforward visual features such as shapes and colors. Though efficient to compute, these schemes only apply to landmarks with limited variability and require strict environmental conditions such as consistent lighting. To overcome these limitations, we propose an end-to-end landmark detection system based on a deep convolutional neural network, which not only easily scales up to a larger number of various landmarks but also exhibit robustness to different lighting conditions. Furthermore, we propose a separative implementation strategy which conducts convolutional neural network training and detection on different hardware platforms separately, i.e. a graphics processing unit work station and a micro aerial vehicle on-board system, subject to their specific implementation requirements. To evaluate the performance of our framework, we test it on synthesized scenarios and real-world videos captured by a quadrotor on-board camera. Experimental results validate that the proposed vision-based autonomous landing system is robust to landmark variability in different backgrounds and lighting situations.en_GB
dc.description.sponsorshipRoyal Society (Government)en_GB
dc.description.sponsorshipNational Natural Science Foundation of Chinaen_GB
dc.description.sponsorshipShandong Provincial Natural Science Foundationen_GB
dc.description.sponsorshipQingdao Applied Fundamental Researchen_GB
dc.description.sponsorshipFundamental Research Funds for Central Universitiesen_GB
dc.identifier.citationVol. 10 (2), pp. 171 - 185en_GB
dc.identifier.doi10.1177/1756829318757470
dc.identifier.grantnumberIE131036en_GB
dc.identifier.grantnumber61671481en_GB
dc.identifier.grantnumber61701541en_GB
dc.identifier.grantnumberZR2017QF003en_GB
dc.identifier.grantnumber16-5-1-11-jchen_GB
dc.identifier.grantnumber6161101383en_GB
dc.identifier.grantnumber15CX05042Aen_GB
dc.identifier.grantnumber16CX05004Ben_GB
dc.identifier.urihttp://hdl.handle.net/10871/36070
dc.language.isoenen_GB
dc.publisherSAGE Publicationsen_GB
dc.rights(c) 2018 The authors. Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License (http://www.creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).en_GB
dc.subjectMicro aerial vehicleen_GB
dc.subjectvision-based autonomous landingen_GB
dc.subjectconvolutional neural networksen_GB
dc.titleDeep learning for vision-based micro aerial vehicle autonomous landingen_GB
dc.typeArticleen_GB
dc.date.available2019-02-26T12:58:18Z
dc.identifier.issn1756-8293
dc.descriptionThis is the final version. Available from SAGE Publications via the DOI in this record.en_GB
dc.identifier.journalInternational Journal of Micro Air Vehiclesen_GB
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_GB
dcterms.dateAccepted2018-01-11
exeter.funder::Royal Society (Government)en_GB
rioxxterms.versionVoRen_GB
rioxxterms.licenseref.startdate2018-01-11
rioxxterms.typeJournal Article/Reviewen_GB
refterms.dateFCD2019-02-26T12:52:02Z
refterms.versionFCDVoR
refterms.dateFOA2019-02-26T12:58:21Z
refterms.panelBen_GB


Files in this item

This item appears in the following Collection(s)

Show simple item record

(c) 2018 The authors. Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License (http://www.creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).
Except where otherwise noted, this item's licence is described as (c) 2018 The authors. Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License (http://www.creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).