Comparison of different optical flow methods on optical flow based out-of-distribution detection
In Cyber Physical Systems (CPS), object detection is a crucial aspect that ensures the safe and robust autonomous operation of such systems. However, studies have suggested that these object detection algorithms are susceptible to anomalies that are falsely classified. Consequently, there is a need...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162920 |
| _version_ | 1826128167419510784 |
|---|---|
| author | Chua, Ivan Hao En |
| author2 | Arvind Easwaran |
| author_facet | Arvind Easwaran Chua, Ivan Hao En |
| author_sort | Chua, Ivan Hao En |
| collection | NTU |
| description | In Cyber Physical Systems (CPS), object detection is a crucial aspect that ensures the safe and robust autonomous operation of such systems. However, studies have suggested that these object detection algorithms are susceptible to anomalies that are falsely classified. Consequently, there is a need to develop high-performing Out-of- Distrubution (OOD) detection algorithms for such systems.
The use of optical flow as a motion detection algorithm has historically been well- documented, and works have been done to incorporate optical flow into Variational Autoencoders (VAEs). This project proposes another method of OOD detection by incorporating the Lucas-Kanade model into a VAE. This proposed model is compared against an existing optical flow-basedd VAE that was implemented with the Farneback algorithm, and the performance and accuracy of both models were tested with a dataset that was self-collected. |
| first_indexed | 2024-10-01T07:20:30Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/162920 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:20:30Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1629202022-11-14T03:49:01Z Comparison of different optical flow methods on optical flow based out-of-distribution detection Chua, Ivan Hao En Arvind Easwaran School of Computer Science and Engineering arvinde@ntu.edu.sg Engineering::Computer science and engineering In Cyber Physical Systems (CPS), object detection is a crucial aspect that ensures the safe and robust autonomous operation of such systems. However, studies have suggested that these object detection algorithms are susceptible to anomalies that are falsely classified. Consequently, there is a need to develop high-performing Out-of- Distrubution (OOD) detection algorithms for such systems. The use of optical flow as a motion detection algorithm has historically been well- documented, and works have been done to incorporate optical flow into Variational Autoencoders (VAEs). This project proposes another method of OOD detection by incorporating the Lucas-Kanade model into a VAE. This proposed model is compared against an existing optical flow-basedd VAE that was implemented with the Farneback algorithm, and the performance and accuracy of both models were tested with a dataset that was self-collected. Bachelor of Engineering (Computer Science) 2022-11-14T03:49:01Z 2022-11-14T03:49:01Z 2022 Final Year Project (FYP) Chua, I. H. E. (2022). Comparison of different optical flow methods on optical flow based out-of-distribution detection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/162920 https://hdl.handle.net/10356/162920 en SCSE21-0864 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Chua, Ivan Hao En Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title | Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title_full | Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title_fullStr | Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title_full_unstemmed | Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title_short | Comparison of different optical flow methods on optical flow based out-of-distribution detection |
| title_sort | comparison of different optical flow methods on optical flow based out of distribution detection |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/162920 |
| work_keys_str_mv | AT chuaivanhaoen comparisonofdifferentopticalflowmethodsonopticalflowbasedoutofdistributiondetection |