본문

서브메뉴

Topological Representations for Visual Object Recognition in Unseen Indoor Environments- [electronic resource]
Topological Representations for Visual Object Recognition in Unseen Indoor Environments - ...
Topological Representations for Visual Object Recognition in Unseen Indoor Environments- [electronic resource]

상세정보

Material Type  
 학위논문
 
0016934827
Date and Time of Latest Transaction  
20240214101658
ISBN  
9798380333818
DDC  
621
Author  
Samani, Ekta Umesh.
Title/Author  
Topological Representations for Visual Object Recognition in Unseen Indoor Environments - [electronic resource]
Publish Info  
[S.l.] : University of Washington., 2023
Publish Info  
Ann Arbor : ProQuest Dissertations & Theses, 2023
Material Info  
1 online resource(162 p.)
General Note  
Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
General Note  
Advisor: Banerjee, Ashis G.
학위논문주기  
Thesis (Ph.D.)--University of Washington, 2023.
Restrictions on Access Note  
This item must not be sold to any third party vendors.
Abstracts/Etc  
요약Object recognition is an essential component of visual perception tasks that help robots build a semantic-level understanding of their environment. Although deep learning methods achieve extraordinary recognition performance in previously seen environments, they are insufficient for deployment in complex and continually-changing environments due to their sensitivity to environmental variations. To realize the goal of long-term autonomy in robots, we need perception methods that go beyond statistical correlation. Therefore, this dissertation focuses on developing robust object recognition methods using topological methods and human-like reasoning mechanisms.We begin by using topologically persistent features, which capture the objects' 2D shape information for recognition in unseen environments. In particular, we present two kinds of representations, namely, sparse persistence image (PI) and amplitude, computed by applying persistent homology to multi-directional height function-based filtrations (nested sequences of cubical complexes) representing the objects' segmentation maps. Using a benchmark dataset, we demonstrate that sparse PI features show better recognition performance in unseen environments than the features from widely-used deep learning-based feature extractors. On a new dataset, the UW Indoor Scenes (UW-IS) dataset, designed to test object recognition performance in unseen environments, the performance of sparse PI features remains relatively unchanged in an unseen test environment, unlike a state-of-the-art domain-adaptive object detection method.Next, we propose a new descriptor, TOPS, to capture the 3D shape information of point clouds generated from depth images, and an accompanying recognition framework, THOR, inspired by human reasoning. The descriptor employs a novel slicing-based approach to compute topological features from filtrations of simplicial complexes using persistent homology, and facilitates reasoning-based recognition using object unity. Apart from a benchmark dataset, we report performance on a new dataset, the UW Indoor Scenes (UW-IS) Occluded dataset, curated using commodity hardware to reflect real-world scenarios with different environmental conditions and degrees of object occlusion. THOR outperforms state-of-the-art methods on both the datasets and achieves substantially higher recognition accuracy for all the scenarios of the UW-IS Occluded dataset.Subsequently, we extend the TOPS descriptor to incorporate object color information via color embeddings and obtain the TOPS2 descriptor. The color embeddings are computed by leveraging the similarity and connectivity between colors in a color network generated using the Mapper algorithm. The accompanying THOR2 framework, trained entirely on synthetic RGB-D images of unoccluded objects, witnesses considerable performance improvements over the shape-based THOR framework on both the OCID and UW-IS Occluded datasets. THOR2 also achieves substantially higher accuracy than a state-of-the-art vision transformer adapted for RGB-D object recognition on the OCID and UW-IS Occluded dataset, regardless of the camera orientation and environmental conditions, respectively. Therefore, the approaches presented in this work, which have also been successfully implemented on a low-cost robot, lay the foundation for achieving robust object recognition in unseen environments using computational topology tools.
Subject Added Entry-Topical Term  
Mechanical engineering.
Subject Added Entry-Topical Term  
Robotics.
Subject Added Entry-Topical Term  
Computer engineering.
Index Term-Uncontrolled  
AI-enabled robotics
Index Term-Uncontrolled  
Object recognition
Index Term-Uncontrolled  
RGB-D perception
Index Term-Uncontrolled  
Topological data analysis
Added Entry-Corporate Name  
University of Washington Mechanical Engineering
Host Item Entry  
Dissertations Abstracts International. 85-03B.
Host Item Entry  
Dissertation Abstract International
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
소장사항  
202402 2024
Control Number  
joongbu:639239

MARC

 008240219s2023        ulk                      00        kor
■001000016934827
■00520240214101658
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380333818
■035    ▼a(MiAaPQ)AAI30635362
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621
■1001  ▼aSamani,  Ekta  Umesh.
■24510▼aTopological  Representations  for  Visual  Object  Recognition  in  Unseen  Indoor  Environments▼h[electronic  resource]
■260    ▼a[S.l.]▼bUniversity  of  Washington.  ▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a1  online  resource(162  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
■500    ▼aAdvisor:  Banerjee,  Ashis  G.
■5021  ▼aThesis  (Ph.D.)--University  of  Washington,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aObject  recognition  is  an  essential  component  of  visual  perception  tasks  that  help  robots  build  a  semantic-level  understanding  of  their  environment.  Although  deep  learning  methods  achieve  extraordinary  recognition  performance  in  previously  seen  environments,  they  are  insufficient  for  deployment  in  complex  and  continually-changing  environments  due  to  their  sensitivity  to  environmental  variations.  To  realize  the  goal  of  long-term  autonomy  in  robots,  we  need  perception  methods  that  go  beyond  statistical  correlation.  Therefore,  this  dissertation  focuses  on  developing  robust  object  recognition  methods  using  topological  methods  and  human-like  reasoning  mechanisms.We  begin  by  using  topologically  persistent  features,  which  capture  the  objects'  2D  shape  information  for  recognition  in  unseen  environments.  In  particular,  we  present  two  kinds  of  representations,  namely,  sparse  persistence  image  (PI)  and  amplitude,  computed  by  applying  persistent  homology  to  multi-directional  height  function-based  filtrations  (nested  sequences  of  cubical  complexes)  representing  the  objects'  segmentation  maps.  Using  a  benchmark  dataset,  we  demonstrate  that  sparse  PI  features  show  better  recognition  performance  in  unseen  environments  than  the  features  from  widely-used  deep  learning-based  feature  extractors.  On  a  new  dataset,  the  UW  Indoor  Scenes  (UW-IS)  dataset,  designed  to  test  object  recognition  performance  in  unseen  environments,  the  performance  of  sparse  PI  features  remains  relatively  unchanged  in  an  unseen  test  environment,  unlike  a  state-of-the-art  domain-adaptive  object  detection  method.Next,  we  propose  a  new  descriptor,  TOPS,  to  capture  the  3D  shape  information  of  point  clouds  generated  from  depth  images,  and  an  accompanying  recognition  framework,  THOR,  inspired  by  human  reasoning.  The  descriptor  employs  a  novel  slicing-based  approach  to  compute  topological  features  from  filtrations  of  simplicial  complexes  using  persistent  homology,  and  facilitates  reasoning-based  recognition  using  object  unity.  Apart  from  a  benchmark  dataset,  we  report  performance  on  a  new  dataset,  the  UW  Indoor  Scenes  (UW-IS)  Occluded  dataset,  curated  using  commodity  hardware  to  reflect  real-world  scenarios  with  different  environmental  conditions  and  degrees  of  object  occlusion.  THOR  outperforms  state-of-the-art  methods  on  both  the  datasets  and  achieves  substantially  higher  recognition  accuracy  for  all  the  scenarios  of  the  UW-IS  Occluded  dataset.Subsequently,  we  extend  the  TOPS  descriptor  to  incorporate  object  color  information  via  color  embeddings  and  obtain  the  TOPS2  descriptor.  The  color  embeddings  are  computed  by  leveraging  the  similarity  and  connectivity  between  colors  in  a  color  network  generated  using  the  Mapper  algorithm.  The  accompanying  THOR2  framework,  trained  entirely  on  synthetic  RGB-D  images  of  unoccluded  objects,  witnesses  considerable  performance  improvements  over  the  shape-based  THOR  framework  on  both  the  OCID  and  UW-IS  Occluded  datasets.  THOR2  also  achieves  substantially  higher  accuracy  than  a  state-of-the-art  vision  transformer  adapted  for  RGB-D  object  recognition  on  the  OCID  and  UW-IS  Occluded  dataset,  regardless  of  the  camera  orientation  and  environmental  conditions,  respectively.  Therefore,  the  approaches  presented  in  this  work,  which  have  also  been  successfully  implemented  on  a  low-cost  robot,  lay  the  foundation  for  achieving  robust  object  recognition  in  unseen  environments  using  computational  topology  tools.
■590    ▼aSchool  code:  0250.
■650  4▼aMechanical  engineering.
■650  4▼aRobotics.
■650  4▼aComputer  engineering.
■653    ▼aAI-enabled  robotics
■653    ▼aObject  recognition
■653    ▼aRGB-D  perception
■653    ▼aTopological  data  analysis
■690    ▼a0548
■690    ▼a0771
■690    ▼a0464
■71020▼aUniversity  of  Washington▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-03B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0250
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934827▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    Detail Info.

    • Reservation
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • My Folder
    Material
    Reg No. Call No. Location Status Lend Info
    TQ0025171 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    * Reservations are available in the borrowing book. To make reservations, Please click the reservation button

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치