Two-level distribution alignment for unsupervised domain adaptation of LiDAR-based object detector라이다 기반 물체 검출기의 비지도 도메인 적응을 위한 두 단계 분포 정렬 방법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 313
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorKum, Dong Suk-
dc.contributor.advisor금동석-
dc.contributor.authorYoo, Hee-Cheol-
dc.date.accessioned2022-04-15T07:58:24Z-
dc.date.available2022-04-15T07:58:24Z-
dc.date.issued2021-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948597&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/295130-
dc.description학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2021.2,[iv, 45 p. :]-
dc.description.abstractIn autonomous driving, object detection technology is an essential part of recognizing the driving environment, and a high-performance deep learning-based method attracts significant interest. Thus, a vast amount of learning data is essential, and the demand for quality data is also increasing. However, data suitable for various sensor configurations and the purpose of use cannot meet this demand. An adaptation method based on transfer learning that enables heterogeneous data was proposed to solve this problem. In the case of LiDAR, many changes occur in the distribution of the point cloud created according to the number of channels, mounting positions, and beam angles of the product. Due to this change, the training data suitable for the user's LiDAR configuration is more insufficient. Also, in point clouds, there is no standard large scale data set as an image domain, feature vector extraction method, and transfer learning is hardly attempted. Therefore, in this study, we aim to develop a transfer learning method for LiDAR object detection. The developed method is evaluated with two public datasets. Through this, it is expected that a deep learning model can be trained with sufficiently existing heterogeneous data and then adapted with a small amount of homogeneous data to develop an object detection algorithm.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectAutonomous Driving-
dc.subjectObject Detection-
dc.subjectLiDAR-
dc.subjectDomain Adaptation-
dc.subjectFinetuning-
dc.subject자율주행-
dc.subject물체검출-
dc.subject라이다-
dc.subject도메인 적응-
dc.subject미세 조정-
dc.titleTwo-level distribution alignment for unsupervised domain adaptation of LiDAR-based object detector-
dc.title.alternative라이다 기반 물체 검출기의 비지도 도메인 적응을 위한 두 단계 분포 정렬 방법-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :미래자동차학제전공,-
dc.contributor.alternativeauthor유희철-
Appears in Collection
PD-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0