본문

서브메뉴

Towards Generalized 3D Object Detection for Autonomous Driving: Enhancing Data Efficiency in Novel Domains
Towards Generalized 3D Object Detection for Autonomous Driving: Enhancing Data Efficiency ...
Towards Generalized 3D Object Detection for Autonomous Driving: Enhancing Data Efficiency in Novel Domains

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152029
ISBN  
9798384049968
DDC  
629.8
저자명  
Chen, Xiangyu.
서명/저자  
Towards Generalized 3D Object Detection for Autonomous Driving: Enhancing Data Efficiency in Novel Domains
발행사항  
[Sl] : Cornell University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
159 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
주기사항  
Advisor: Weinberger, Kilian.
학위논문주기  
Thesis (Ph.D.)--Cornell University, 2024.
초록/해제  
요약Robust 3D object detection is fundamental to the advancement of robotics and autonomous driving, allowing autonomous systems to navigate complex environments safely and efficiently. Current 3D object detection algorithms rely on supervised learning using large-scale annotated datasets, which are meticulously designed to reflect diverse real-world scenarios and object variations. Creating and annotating such datasets is notoriously labor-intensive and time-consuming, requiring significant efforts to ensure precision and comprehensiveness.However, due to the rapid development and geographic differences in vehicle designs, deploying these carefully tuned systems in real-world environments still introduces domain gaps that compromise performance. These challenges are often addressed by continuously collecting and annotating additional data, which is unsustainable due to the high costs involved. Consequently, there is a pressing need for more generalized 3D object detection capabilities to ensure consistent and reliable performance across diverse and evolving domains.In this thesis, we identified mis-localization as the primary cause of reduced 3D object detection performance in novel domains. That is, 3D objects (e.g. cars, cyclists, and pedestrians) in novel domains can generally be correctly identified by unadapted 3D object detectors, but their precise sizes, locations, and orientations are often inaccurate. However, previous studies tend to view object detection in novel domains as entirely new tasks, overlooking the fact that objects of the same class often share similar shapes across domains, and that bounding boxes are consistently defined to be tight around the objects.We argue that addressing such mis-localization does not necessarily require extensive data collection and annotation. In fact, successful adaptation can be achieved with minimal or even no prior knowledge of the new domain. Notably, Stat Norm (Chap. 2) significantly enhances domain adaptation performance by simulating new domains using only their object dimension statistics; DRIFT (Chap. 3) markedly improves both the efficiency and performance of unsupervised object discovery in novel domains by aligning 3D object detectors with heuristic reward functions; DiffuBox (Chap. 4) consistently boosts existing domain adaptation methods through domain-agnostic bounding box refinement that operates in the bounding-box-relative view. Through comprehensive experimental results, we demonstrate that incorporating shape knowledge and heuristic priors can effectively mitigate the domain gaps, achieving more robust, efficient, and generalized 3D object detection across diverse environments without the need for extensive domain-specific data collection and annotation. Overall, we offer a more practical and scalable solution for deploying autonomous driving systems in diverse real-world scenarios.
일반주제명  
Robotics
일반주제명  
Computer science
키워드  
3D object detection
키워드  
Autonomous driving
키워드  
Computer vision
키워드  
Data efficiency
키워드  
Domain adaptation
키워드  
Machine learning
기타저자  
Cornell University Computer Science
기본자료저록  
Dissertations Abstracts International. 86-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162582
■00520250211152029
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384049968
■035    ▼a(MiAaPQ)AAI31333906
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aChen,  Xiangyu.▼0(orcid)0000-0002-5632-7120
■24510▼aTowards  Generalized  3D  Object  Detection  for  Autonomous  Driving:  Enhancing  Data  Efficiency  in  Novel  Domains
■260    ▼a[Sl]▼bCornell  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a159  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Weinberger,  Kilian.
■5021  ▼aThesis  (Ph.D.)--Cornell  University,  2024.
■520    ▼aRobust  3D  object  detection  is  fundamental  to  the  advancement  of  robotics  and  autonomous  driving,  allowing  autonomous  systems  to  navigate  complex  environments  safely  and  efficiently.  Current  3D  object  detection  algorithms  rely  on  supervised  learning  using  large-scale  annotated  datasets,  which  are  meticulously  designed  to  reflect  diverse  real-world  scenarios  and  object  variations.  Creating  and  annotating  such  datasets  is  notoriously  labor-intensive  and  time-consuming,  requiring  significant  efforts  to  ensure  precision  and  comprehensiveness.However,  due  to  the  rapid  development  and  geographic  differences  in  vehicle  designs,  deploying  these  carefully  tuned  systems  in  real-world  environments  still  introduces  domain  gaps  that  compromise  performance.  These  challenges  are  often  addressed  by  continuously  collecting  and  annotating  additional  data,  which  is  unsustainable  due  to  the  high  costs  involved.  Consequently,  there  is  a  pressing  need  for  more  generalized  3D  object  detection  capabilities  to  ensure  consistent  and  reliable  performance  across  diverse  and  evolving  domains.In  this  thesis,  we  identified  mis-localization  as  the  primary  cause  of  reduced  3D  object  detection  performance  in  novel  domains.  That  is,  3D  objects  (e.g.  cars,  cyclists,  and  pedestrians)  in  novel  domains  can  generally  be  correctly  identified  by  unadapted  3D  object  detectors,  but  their  precise  sizes,  locations,  and  orientations  are  often  inaccurate.  However,  previous  studies  tend  to  view  object  detection  in  novel  domains  as  entirely  new  tasks,  overlooking  the  fact  that  objects  of  the  same  class  often  share  similar  shapes  across  domains,  and  that  bounding  boxes  are  consistently  defined  to  be  tight  around  the  objects.We  argue  that  addressing  such  mis-localization  does  not  necessarily  require  extensive  data  collection  and  annotation.  In  fact,  successful  adaptation  can  be  achieved  with  minimal  or  even  no  prior  knowledge  of  the  new  domain.  Notably,  Stat  Norm  (Chap.  2)  significantly  enhances  domain  adaptation  performance  by  simulating  new  domains  using  only  their  object  dimension  statistics;  DRIFT  (Chap.  3)  markedly  improves  both  the  efficiency  and  performance  of  unsupervised  object  discovery  in  novel  domains  by  aligning  3D  object  detectors  with  heuristic  reward  functions;  DiffuBox  (Chap.  4)  consistently  boosts  existing  domain  adaptation  methods  through  domain-agnostic  bounding  box  refinement  that  operates  in  the  bounding-box-relative  view.  Through  comprehensive  experimental  results,  we  demonstrate  that  incorporating  shape  knowledge  and  heuristic  priors  can  effectively  mitigate  the  domain  gaps,  achieving  more  robust,  efficient,  and  generalized  3D  object  detection  across  diverse  environments  without  the  need  for  extensive  domain-specific  data  collection  and  annotation.  Overall,  we  offer  a  more  practical  and  scalable  solution  for  deploying  autonomous  driving  systems  in  diverse  real-world  scenarios.
■590    ▼aSchool  code:  0058.
■650  4▼aRobotics
■650  4▼aComputer  science
■653    ▼a3D  object  detection
■653    ▼aAutonomous  driving
■653    ▼aComputer  vision
■653    ▼aData  efficiency
■653    ▼aDomain  adaptation
■653    ▼aMachine  learning
■690    ▼a0800
■690    ▼a0771
■690    ▼a0984
■71020▼aCornell  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0058
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162582▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF11448 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.