Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 신현철 | - |
dc.date.accessioned | 2018-05-29T07:52:02Z | - |
dc.date.available | 2018-05-29T07:52:02Z | - |
dc.date.issued | 2017-01 | - |
dc.identifier.citation | IET COMPUTER VISION, v. 11, No. 5, Page. 368 – 377 | en_US |
dc.identifier.issn | 1751-9632 | - |
dc.identifier.uri | http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2016.0303 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/71664 | - |
dc.description.abstract | In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d-patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D-patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant-detections around a true-positive is different from that around a false-positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true-positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well-known methods (under partially occluded settings), on KTSD dataset. | en_US |
dc.description.sponsorship | The authors Yawar Rehman and Irfan Riaz are sponsored by 'Higher Education Commission' (HEC) of the Government of Pakistan. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | INST ENGINEERING TECHNOLOGY-IET | en_US |
dc.subject | CLASSIFICATION | en_US |
dc.subject | ECOGNITION | en_US |
dc.subject | Korean TSD dataset | en_US |
dc.subject | object detection | en_US |
dc.subject | driver information systems | en_US |
dc.subject | advanced driver assistance systems | en_US |
dc.subject | traffic signs | en_US |
dc.subject | full object templates | en_US |
dc.subject | discriminative patches | en_US |
dc.subject | d-patches | en_US |
dc.subject | traffic sign detection framework | en_US |
dc.subject | TSD framework | en_US |
dc.subject | occlusion handling capability | en_US |
dc.subject | redundant-detections | en_US |
dc.subject | hypothesis generation scheme | en_US |
dc.subject | true positive candidate | en_US |
dc.subject | confidence-score | en_US |
dc.subject | German TSD benchmark | en_US |
dc.subject | KTSD dataset | en_US |
dc.title | D-patches: effective traffic sign detection with occlusion handling | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1049/iet-cvi.2016.0303 | - |
dc.relation.page | 1-10 | - |
dc.relation.journal | IET COMPUTER VISION | - |
dc.contributor.googleauthor | Rehman, Yawar | - |
dc.contributor.googleauthor | Riaz, Irfan | - |
dc.contributor.googleauthor | Fan, Xue | - |
dc.contributor.googleauthor | Shin, Hyunchul | - |
dc.relation.code | 2017000362 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF ENGINEERING SCIENCES[E] | - |
dc.sector.department | DIVISION OF ELECTRICAL ENGINEERING | - |
dc.identifier.pid | shin | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.