2026-09-18T21:13:41Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1230532026-06-06T00:54:44Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Boris Katz. Mata, Cristina(Christina Florica) Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2019-11-22T00:04:28Z 2019-11-22T00:04:28Z 2019 2019 https://hdl.handle.net/1721.1/123053 1128024162 This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 107-111). This thesis explores hand pose estimation through the use of two methods. We first investigate the use of segmentation networks within pose estimation pipelines with a focus on fine parts segmentation. We present two implementations of a novel method for fine parts segmentation employing a higher-order Conditional Random Field (CRF) that measures attachment and containment of fine parts. The first implementation is of the CRF as a post-processing module on top of a Convolutional Neural Network (CNN). The second addresses efficiency bottlenecks in the first by implementing the CRF as a Recurrent Neural Network (RNN) and allowing for end-to-end training with the CNN. Limited by the accuracy of fine parts segmentation and wishing to avoid propagation of segmentation errors through a pipeline, we turn to generative modeling methods for hand pose estimation and present an inverse-graphics approach implemented in a probabilistic programming language. Spurred by the lack of occlusion in hand image datasets, we present the MIT Partially Occluded Hands Dataset, a large-scale dataset of single RGB images, half of which feature natural hand-object interactions, and evaluate several baselines on this dataset. by Cristina Mata. M.Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 111 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Two approaches to robust hand pose estimation : generative modeling and semantic relations 2 approaches to robust hand pose estimation : generative modeling and semantic relations Thesis application/pdf 2019-11-22T00:04:27Z Publication Master EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="75548473-567e-4055-8de3-114058b131cc"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Two approaches to robust hand pose estimation : generative modeling and semantic relations</Title> <Subtitle>2 approaches to robust hand pose estimation : generative modeling and semantic relations</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Mata, Cristina(Christina Florica)</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>This thesis explores hand pose estimation through the use of two methods. We first investigate the use of segmentation networks within pose estimation pipelines with a focus on fine parts segmentation. We present two implementations of a novel method for fine parts segmentation employing a higher-order Conditional Random Field (CRF) that measures attachment and containment of fine parts. The first implementation is of the CRF as a post-processing module on top of a Convolutional Neural Network (CNN). The second addresses efficiency bottlenecks in the first by implementing the CRF as a Recurrent Neural Network (RNN) and allowing for end-to-end training with the CNN. Limited by the accuracy of fine parts segmentation and wishing to avoid propagation of segmentation errors through a pipeline, we turn to generative modeling methods for hand pose estimation and present an inverse-graphics approach implemented in a probabilistic programming language. Spurred by the lack of occlusion in hand image datasets, we present the MIT Partially Occluded Hands Dataset, a large-scale dataset of single RGB images, half of which feature natural hand-object interactions, and evaluate several baselines on this dataset.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>