Space-time event clouds-based event processing
Recently developed event cameras demonstrate increasing potential in computer vision applications. There have been a number of techniques to process specially formatted event data. However, to take advantage of existing frameworks for fame-based video analytics, these techniques normally apply space...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/151982 |
| _version_ | 1811677095974141952 |
|---|---|
| author | Wang, Qinyi |
| author2 | LU Yilong |
| author_facet | LU Yilong Wang, Qinyi |
| author_sort | Wang, Qinyi |
| collection | NTU |
| description | Recently developed event cameras demonstrate increasing potential in computer vision applications. There have been a number of techniques to process specially formatted event data. However, to take advantage of existing frameworks for fame-based video analytics, these techniques normally apply space-time disentanglement in the pre-processing stage. This kind of disentanglement does not fully utilize the rich temporal information inherent in the event data. This thesis proposes the Space-time Event Cloud concept to model event data as 3D event clouds, which aims to extract spatiotemporal features from the entangled states directly. With this concept, this thesis solves the event-based hand gesture recognition task with state-of-the-art performance. Furthermore, this thesis proposes a dedicated network, Space-time EventNet, to emphasize the interaction between neighboring events to enhance recognition accuracy. Finally, this thesis designs an ultra-efficient detection-tracking-recognition pipeline. This pipeline is portable enough to achieve success in light-weighted embedded systems. |
| first_indexed | 2024-10-01T02:31:56Z |
| format | Thesis-Doctor of Philosophy |
| id | ntu-10356/151982 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:31:56Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1519822023-07-04T15:06:05Z Space-time event clouds-based event processing Wang, Qinyi LU Yilong School of Electrical and Electronic Engineering EYLU@ntu.edu.sg Engineering::Electrical and electronic engineering Recently developed event cameras demonstrate increasing potential in computer vision applications. There have been a number of techniques to process specially formatted event data. However, to take advantage of existing frameworks for fame-based video analytics, these techniques normally apply space-time disentanglement in the pre-processing stage. This kind of disentanglement does not fully utilize the rich temporal information inherent in the event data. This thesis proposes the Space-time Event Cloud concept to model event data as 3D event clouds, which aims to extract spatiotemporal features from the entangled states directly. With this concept, this thesis solves the event-based hand gesture recognition task with state-of-the-art performance. Furthermore, this thesis proposes a dedicated network, Space-time EventNet, to emphasize the interaction between neighboring events to enhance recognition accuracy. Finally, this thesis designs an ultra-efficient detection-tracking-recognition pipeline. This pipeline is portable enough to achieve success in light-weighted embedded systems. Doctor of Philosophy 2021-07-12T07:48:14Z 2021-07-12T07:48:14Z 2021 Thesis-Doctor of Philosophy Wang, Q. (2021). Space-time event clouds-based event processing. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/151982 https://hdl.handle.net/10356/151982 10.32657/10356/151982 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::Electrical and electronic engineering Wang, Qinyi Space-time event clouds-based event processing |
| title | Space-time event clouds-based event processing |
| title_full | Space-time event clouds-based event processing |
| title_fullStr | Space-time event clouds-based event processing |
| title_full_unstemmed | Space-time event clouds-based event processing |
| title_short | Space-time event clouds-based event processing |
| title_sort | space time event clouds based event processing |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/151982 |
| work_keys_str_mv | AT wangqinyi spacetimeeventcloudsbasedeventprocessing |