DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kweon, In-So | - |
dc.contributor.advisor | 권인소 | - |
dc.contributor.author | Tooba, Imtiaz | - |
dc.date.accessioned | 2021-05-13T19:39:45Z | - |
dc.date.available | 2021-05-13T19:39:45Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925242&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285078 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.8,[iv, 39 p. :] | - |
dc.description.abstract | For efficiently exploiting the bulk of information obtained from city-wide CCTV systems, object (pedestrians, vehicles) tracking and re-identification across multiple cameras are essential tasks. Object re-identification (ReID) has extensive utility for analyzing and accurately merging objects' trajectories across multiple non-overlapping cameras. Despite being a very fertile ground for research which attracted growing attention in the past decades, re-identification is still considered a very challenging problem. Moreover, most available datasets contain unoccluded target images and thus the networks trained on them fail to generalize to practical examples where occlusions and various artifacts are common. In this work, we propose an adversarial training strategy to robustify re-identification for occluded person and vehicle images in intelligent surveillance systems. Our method adversarially learns to generate occlusion masks that diminish the re-identification network performance, thus challenging its adversary, the re-identification network, to enhance re-ID performance against physical occluders. Extensive experiments performed on public datasets as well as a personally collected dataset verify the effectiveness of the proposed approach. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Person re-identification▼aVehicle re-identification▼aGenerative Adversarial Networks▼aOcclusions in re-identification▼aFeature Embedding | - |
dc.subject | 사람 재확인▼a차량 재확인▼a생산-대립적 네트워크▼a가리어진 환경에서의 재확인▼a특징점 추출 및 구축 | - |
dc.title | Occlusion robust re-identification | - |
dc.title.alternative | 강력한 객체 재 식별 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 임티아즈 투바 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.