DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 공승현 | - |
dc.contributor.author | Sun, Min-Hyeok | - |
dc.contributor.author | 선민혁 | - |
dc.date.accessioned | 2024-08-08T19:30:22Z | - |
dc.date.available | 2024-08-08T19:30:22Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097344&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321812 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 조천식모빌리티대학원, 2024.2,[v, 56 p. :] | - |
dc.description.abstract | In autonomous driving systems, object detection technology identifies the location and type of obstacles around the vehicle. Since autonomous driving systems conduct path plans and behavior decisions based on object detection, reliable object detection technology across various conditions is vital for safety. Recently, 4D Radar sensors have gained interest in object detection studies for their robustness against poor weather conditions such as rain and snow. However, training networks for object detection requires large datasets and manual labeling of vast amounts of sensor data. Moreover, since 4D Radar sensor data is not intuitive for humans, annotating accurate 3D labels is difficult and expensive labor. To address these challenges, this paper addresses an auto-labeling method utilizing pre-trained deep learning networks to effectively train 4D Radar object detection networks. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 객체인식▼a4D 레이다▼a라이다▼a딥러닝▼a오토라벨링 | - |
dc.subject | Object detection▼a4D radar▼aLiDAR▼aDeep-learning▼aAuto-labeling | - |
dc.title | (A) study on efficient auto-labeling leveraging 4d radar dataset properties | - |
dc.title.alternative | 4D 레이다 데이터셋의 특성을 활용한 효율적인 오토라벨링에 관한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :조천식모빌리티대학원, | - |
dc.contributor.alternativeauthor | Kong, Seung-Hyun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.