Visual understanding of human activity : towards ambient intelligence in AI-assisted hospitals
Abstract/Contents
- Abstract
- Ambient intelligence infused in the physical space of buildings and structures aims to make them perceptive and reactive, able to dynamically provide assistance to humans in environments ranging from homes to hospitals. A key requirement towards this is visual interpretation of human activity captured by visual sensors embedded in the physical spaces. In order to provide humans with appropriate assistance, we must develop the computer vision algorithms that can recognize what humans are doing at every moment in time, across diverse and fine-grained activities and despite challenging viewpoints and computational constraints. In this thesis, I present computer vision algorithms that push our capabilities towards ambient intelligence. In the first part of the thesis, I tackle major technical challenges of contextual awareness, embedded vision, and adaptivity, in the context of recognizing human activities. I introduce methods for dense and detailed interpretation of human activity, for efficient detection of actions, and for learning about new human actions from few labeled training examples. Then in the second part of the thesis, I present my work on a real-world prototype of ambient intelligence: AI-Assisted Hospitals where computer vision algorithms are used to provide continuous awareness of clinical activities. I describe two proof-of-concepts, monitoring hand hygiene and documenting patient mobility care activities. These reflect the potential of computer vision and ambient intelligence to assist clinicians and healthcare workers across rich and diverse use cases.
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 | 2018; ©2018 |
| Publication date | 2018; 2018 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Yeung, Serena |
|---|---|
| Degree supervisor | Li, Fei Fei, 1976- |
| Degree supervisor | Milstein, Arnold |
| Thesis advisor | Li, Fei Fei, 1976- |
| Thesis advisor | Milstein, Arnold |
| Thesis advisor | Nishimura, Dwight George |
| Thesis advisor | Wetzstein, Gordon |
| Degree committee member | Nishimura, Dwight George |
| Degree committee member | Wetzstein, Gordon |
| Associated with | Stanford University, Department of Electrical Engineering. |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Serena Yeung. |
|---|---|
| Note | Submitted to the Department of Electrical Engineering. |
| Thesis | Thesis Ph.D. Stanford University 2018. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2018 by Serena Yu-Ching Yeung
- 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...