Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos
This thesis presents new methods for incorporating multi-stream networks into the driver fatigue detection system. For the depth video-based method, a two-stream CNN architecture is proposed to incorporate spatial information of the current depth frame and temporal information of neighboring depth f...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/164796 |
| _version_ | 1826124060940042240 |
|---|---|
| author | Ma, Xiaoxi |
| author2 | Yap Kim Hui |
| author_facet | Yap Kim Hui Ma, Xiaoxi |
| author_sort | Ma, Xiaoxi |
| collection | NTU |
| description | This thesis presents new methods for incorporating multi-stream networks into the driver fatigue detection system. For the depth video-based method, a two-stream CNN architecture is proposed to incorporate spatial information of the current depth frame and temporal information of neighboring depth frames which is represented by motion vectors. For the infrared video-based method, a convolutional three-stream network is proposed to incorporate current-infrared-frame-based spatial information, optical-flow-based short-term temporal information of two consecutive infrared frames, and optical flow-motion history image-based temporal information within the infrared video sequence. |
| first_indexed | 2024-10-01T06:14:47Z |
| format | Thesis-Doctor of Philosophy |
| id | ntu-10356/164796 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:14:47Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1647962023-03-06T07:30:04Z Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos Ma, Xiaoxi Yap Kim Hui School of Electrical and Electronic Engineering EKHYap@ntu.edu.sg Engineering::Computer science and engineering This thesis presents new methods for incorporating multi-stream networks into the driver fatigue detection system. For the depth video-based method, a two-stream CNN architecture is proposed to incorporate spatial information of the current depth frame and temporal information of neighboring depth frames which is represented by motion vectors. For the infrared video-based method, a convolutional three-stream network is proposed to incorporate current-infrared-frame-based spatial information, optical-flow-based short-term temporal information of two consecutive infrared frames, and optical flow-motion history image-based temporal information within the infrared video sequence. Doctor of Philosophy 2023-02-20T02:11:13Z 2023-02-20T02:11:13Z 2022 Thesis-Doctor of Philosophy Ma, X. (2022). Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/164796 https://hdl.handle.net/10356/164796 10.32657/10356/164796 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Ma, Xiaoxi Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title | Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title_full | Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title_fullStr | Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title_full_unstemmed | Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title_short | Multi-stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| title_sort | multi stream spatiotemporal networks for driver fatigue detection from infrared and depth videos |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/164796 |
| work_keys_str_mv | AT maxiaoxi multistreamspatiotemporalnetworksfordriverfatiguedetectionfrominfraredanddepthvideos |