서브메뉴
검색
Topological Representations for Visual Object Recognition in Unseen Indoor Environments- [electronic resource]
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
Detail Info.
- Reservation
- 캠퍼스간 도서대출
- 서가에 없는 책 신고
- My Folder