Automatically generating structured information on the as-is status of facilities from visual data
Abstract/Contents
- Abstract
- Despite technological advancements, physical reality and its digital representation are currently two disconnected domains. My vision - the seamless interaction of the two domains - motivates this thesis. We are quickly transitioning into a hybrid world, where we will live with virtual and augmented reality, robots, and automation along physical reality. This requires a seamless interaction between the physical and the digital. A big challenge toward their interaction is an accurate, detailed, consistent, and up-to-date knowledge of the as-is status of facilities in the digital domain, structured in a representation that is interpretable by both humans and machines. State-of-the-art practice attempts to acquire the digital representation with manual, time consuming, non-scalable, and error-prone methods. This has a direct, negative, and quantifiable impact on how architects, engineers, constructors, and facility managers (AEC/FM) design, construct, and use facilities. It is a global and ubiquitous challenge since it applies to the entire built environment, and therefore requires automatic, fast, scalable, accurate, and generalizable solutions. This thesis employs Machine Vision and Learning to contribute a set of methods that receive as input 2D and 3D visual data and automatically produce semantic information on objects (e.g., wall, floor, chair) and rooms within entire buildings, to facilitate four major AEC/FM processes: asset management, building energy modeling, structural stability, and construction progress monitoring. It also contributes a graph-based representation that structures this information in a way that humans can interact with it and machines can directly use and learn from it. Last, it produced and made publicly available a set of semantic datasets that played an important role in this work, as well as in that of other researchers. The results of the thesis bring us a step closer to addressing the aforementioned challenge and provide a foundation to fully understand the interaction of humans (e.g., engineers, managers, and occupants) with the built environment throughout its lifecycle.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2020; ©2020 |
Publication date | 2020; 2020 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Armeni, Iro |
---|---|
Degree supervisor | Fischer, Martin A. (Martin Arthur) |
Thesis advisor | Fischer, Martin A. (Martin Arthur) |
Thesis advisor | Rajagopal, Ram |
Thesis advisor | Savarese, Silvio |
Degree committee member | Rajagopal, Ram |
Degree committee member | Savarese, Silvio |
Associated with | Stanford University, Department of Civil & Environmental Engineering Department |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Iro Armeni. |
---|---|
Note | Submitted to the Department of Civil & Environmental Engineering Department. |
Thesis | Thesis Ph.D. Stanford University 2020. |
Location | electronic resource |
Access conditions
- Copyright
- © 2020 by Iro Armeni
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...