Deep learning based approaches for 3D object detection and instance segmentation on point clouds3차원 점구름 기반 객체 탐지 및 분할 기법에서의 딥러닝을 활용한 접근법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 60
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYoo, Changdong-
dc.contributor.advisor유창동-
dc.contributor.authorKim, Kookhoi-
dc.date.accessioned2023-06-26T19:34:24Z-
dc.date.available2023-06-26T19:34:24Z-
dc.date.issued2022-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008331&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/309974-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2022.8,[vi, 60 p. :]-
dc.description.abstractThis dissertation considers a 3D object detection and instance segmentation method based on point clouds. 3D object detection is a task that predicts bounding boxes including objects in point cloud datasets. 3D instance segmentation is a task that segment each pixel or point into a object that the point belongs to. Despite several previous works, these tasks have some limitations : (1) While PointNet-based permutation-invariant network extracts features of point cloud for object detection, independent network are used to extract the feature of grouped points without interaction between grouped points. (2) Bounding box detection is sensitive to rotation error and translation error for flat objects. (3) Incorrect semantic prediction propogates to final instance prediction in one-hot semantic based grouping instance segmentation. To mitigate these problems, we propose (1) Group-Point Attention(GPAN) to enhance feature representation of 3D point clouds, adapting cross-attention between base point and grouped points to encourage interaction. (2) SphereSeg by predicting spheres replacing bounding boxes that are invariant to object orientation and more robust to localization error. (3) SoftGroup to improve the quality of instance proposals, further refine proposals for accurate 3D instance segmentation. Experiments on various 3D point cloud datasets show the efficacy of the proposed methods.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectArtificial intelligence▼aDeep learning▼aObject detection▼aInstance segmentation▼a3D Point Cloud-
dc.subject인공지능▼a심층학습▼a객체탐지▼a객체분할▼a3차원 점구름 데이터-
dc.titleDeep learning based approaches for 3D object detection and instance segmentation on point clouds-
dc.title.alternative3차원 점구름 기반 객체 탐지 및 분할 기법에서의 딥러닝을 활용한 접근법-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthor김국회-
Appears in Collection
EE-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