DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Jung Uk | ko |
dc.contributor.author | Kwon, Jungsu | ko |
dc.contributor.author | Kim, Hak Gu | ko |
dc.contributor.author | Ro, Yong Man | ko |
dc.date.accessioned | 2020-09-18T04:02:51Z | - |
dc.date.available | 2020-09-18T04:02:51Z | - |
dc.date.created | 2019-02-20 | - |
dc.date.created | 2019-02-20 | - |
dc.date.created | 2019-02-20 | - |
dc.date.created | 2019-02-20 | - |
dc.date.created | 2019-02-20 | - |
dc.date.issued | 2020-04 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, v.30, no.4, pp.1037 - 1050 | - |
dc.identifier.issn | 1051-8215 | - |
dc.identifier.uri | http://hdl.handle.net/10203/276129 | - |
dc.description.abstract | Object detection has received significant interest in the research field of computer vision and is widely used in human-centric applications. The occlusion problem is a frequent obstacle that degrades detection quality. In this paper, we propose a novel object detection framework targeting robust object detection in occlusion. The proposed deep learning-based network consists mainly of two parts: 1) object detection framework, which classifies the object categories and localizes the object location and 2) plug-in bounding-box (BB) estimator, which estimates the object and occlusion region from the feature map of the backbone network and the corresponding critic network for evaluating the predicted BB map. The BB estimator and the critic network are the plug-in modules added to the object detection framework and learned competitively with adversarial manner. As the plug-in BB estimator is learned to estimate the BB map containing the object and occlusion pattern information, the backbone network can embed this information to enable robust detection under occlusion in the test phase. The comprehensive experimental results on the PASCAL VOC, MS COCO, and KITTI dataset showed that the performance is improved with the plug-in BB-Critic network by predicting and criticizing object and occlusion in general generic object detection framework. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | BBC Net: Bounding-Box Critic Network for Occlusion-Robust Object Detection | - |
dc.type | Article | - |
dc.identifier.wosid | 000561099300011 | - |
dc.identifier.scopusid | 2-s2.0-85062656179 | - |
dc.type.rims | ART | - |
dc.citation.volume | 30 | - |
dc.citation.issue | 4 | - |
dc.citation.beginningpage | 1037 | - |
dc.citation.endingpage | 1050 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY | - |
dc.identifier.doi | 10.1109/TCSVT.2019.2900709 | - |
dc.contributor.localauthor | Ro, Yong Man | - |
dc.contributor.nonIdAuthor | Kwon, Jungsu | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Encoding | - |
dc.subject.keywordAuthor | Object recognition | - |
dc.subject.keywordAuthor | Detectors | - |
dc.subject.keywordAuthor | Proposals | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | occlusion | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | actor-critic network | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.