Date of Award
8-2020
Document Type
Campus Access Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Computer Science
First Advisor
Marc Pomplun
Second Advisor
Dan Simovici
Third Advisor
Duc Tran
Abstract
In the view of the industry, the modeling design process is an overwhelming, non-trivial, and time-consuming task. As a result, creating such a design can take days, months, even several years. In this thesis, we investigate how human designers use human-centric computational-aided modeling design tools to assist the modeling design processes. We investigate:
- how we utilize the perception data obtained from the virtual environments to develop novel computational approaches of the layout designs for human movement comfort, accessibility, and convenience.
- how we utilize the semantic data obtained from real environments to develop novel computational approaches of the sound source assignment for the immersive experience in virtual reality.
- how we utilize the suggested images obtained from a set of annotated images to develop novel computational approaches of gallery design for generating style-unified gallery walls in augmented reality.
We then tackle various challenging computational design problems within our novel approaches. In the visual perception approach, we devise agent-driven optimization methods for the road signs assignment by a given layout, and we devise an adaptive algorithm to design a gallery by a suggestion system. In the auditory perception work, we devise an automatic algorithm to enhance the immersive of the given static panorama images through realistic sound sources assignment.
Recommended Citation
Huang, Haikun, "AI-driven Computational Design Tools For Synthesizing Human-centric Design" (2020). Graduate Doctoral Dissertations. 583.
https://scholarworks.umb.edu/doctoral_dissertations/583
Comments
Free and open access to this Campus Access Dissertation is made available to the UMass Boston community by ScholarWorks at UMass Boston. Those not on campus and those without a UMass Boston campus username and password may gain access to this dissertation through resources like Proquest Dissertations & Theses Global or through Interlibrary Loan. If you have a UMass Boston campus username and password and would like to download this work from off-campus, click on the "Off-Campus UMass Boston Users" link above.