DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hoon | ko |
dc.contributor.author | Suh, Changho | ko |
dc.contributor.author | Lee, Kangwook | ko |
dc.contributor.author | Hwang, Gyeongjo | ko |
dc.date.accessioned | 2019-02-20T05:06:02Z | - |
dc.date.available | 2019-02-20T05:06:02Z | - |
dc.date.created | 2018-12-11 | - |
dc.date.created | 2018-12-11 | - |
dc.date.created | 2018-12-11 | - |
dc.date.issued | 2019-01-29 | - |
dc.identifier.citation | 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, pp.978 - 985 | - |
dc.identifier.uri | http://hdl.handle.net/10203/250310 | - |
dc.description.abstract | Developing a computer vision-based algorithm for identifying dangerous vehicles requires a large amount of labeled accident data, which is difficult to collect in the real world. To tackle this challenge, we first develop a synthetic data generator built on top of a driving simulator. We then observe that the synthetic labels that are generated based on simulation results are very noisy, resulting in poor classification performance. In order to improve the quality of synthetic labels, we propose a new label adaptation technique that first extracts internal states of vehicles from the underlying driving simulator, and then refines labels by predicting future paths of vehicles based on a well-studied motion model. Via real-data experiments, we show that our dangerous vehicle classifier can reduce the missed detection rate by at least 18.5% compared with those trained with real data when time-to-collision is between 1.6 s and 1.8 s. | - |
dc.language | English | - |
dc.publisher | THE ASSOCIATION FOR THE ADVANCEMENT OF ARTIFICIAL INTELLIGENCE | - |
dc.title | Crash to not crash: Learn to identify dangerous vehicles using a simulator | - |
dc.type | Conference | - |
dc.identifier.wosid | 000485292600121 | - |
dc.identifier.scopusid | 2-s2.0-85082449817 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 978 | - |
dc.citation.endingpage | 985 | - |
dc.citation.publicationname | 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Hilton Hawaiian Village, Honolulu | - |
dc.contributor.localauthor | Suh, Changho | - |
dc.contributor.nonIdAuthor | Kim, Hoon | - |
dc.contributor.nonIdAuthor | Lee, Kangwook | - |
dc.contributor.nonIdAuthor | Hwang, Gyeongjo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.