DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwang, Sunyou | ko |
dc.contributor.author | Lee, Jaehyun | ko |
dc.contributor.author | Shin, Heemin | ko |
dc.contributor.author | Cho, Sungwook | ko |
dc.contributor.author | Shim, David Hyunchul | ko |
dc.date.accessioned | 2019-04-15T14:38:04Z | - |
dc.date.available | 2019-04-15T14:38:04Z | - |
dc.date.created | 2018-03-27 | - |
dc.date.created | 2018-03-27 | - |
dc.date.issued | 2018-01-10 | - |
dc.identifier.citation | AIAA Information Systems-AIAA Infotech at Aerospace, 2018 | - |
dc.identifier.uri | http://hdl.handle.net/10203/254237 | - |
dc.description.abstract | In this paper, we propose a vision-based aircraft detection method based on a deep convolutional neural network using a single camera sensor. The proposed method detects aircraft even in complex backgrounds under the horizon and can be applied to wide range of environments. We verified our system performance using test videos consisting of a total of 17,000 frames. On the test data, our model achieved over 83% of detection rate and 0.899 precision. Our system operates at over 28 frames per second even on NVIDIA TX1 embedded board that is only 88 grams, so it is suitable for small UAS applications. | - |
dc.language | English | - |
dc.publisher | American Institute of Aeronautics and Astronautics | - |
dc.title | Aircraft Detection using Deep Convolutional Neural Network in Small Unmanned Aircraft Systems | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85141621802 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | AIAA Information Systems-AIAA Infotech at Aerospace, 2018 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Gaylord Palms, Kissimmee, Florida | - |
dc.identifier.doi | 10.2514/6.2018-2137 | - |
dc.contributor.localauthor | Shim, David Hyunchul | - |
dc.contributor.nonIdAuthor | Hwang, Sunyou | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.