Traffic sign detection system with efficient and low-bit neural network compression in computer vision
In a traffic setting, traffic sign detection is a critical task. It is becoming even more important as the number of vehicles on the road grows, increasing the accident rate. Object detection in embedded devices can be used to alert distracted drivers to traffic signs so that the signs can direct t...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/158549 |
| _version_ | 1811697370415497216 |
|---|---|
| author | Thin Lat Han |
| author2 | Loke Yuan Ren |
| author_facet | Loke Yuan Ren Thin Lat Han |
| author_sort | Thin Lat Han |
| collection | NTU |
| description | In a traffic setting, traffic sign detection is a critical task. It is becoming even more important as the number of vehicles on the road grows, increasing the accident rate.
Object detection in embedded devices can be used to alert distracted drivers to traffic signs so that the signs can direct them on the road. Object identification on images can have a high level of accuracy and speed, which is required by a traffic sign detection system to recognize traffic signs quickly and precisely so that road safety can be ensured. However, to achieve the high accuracy and speed requirements, it usually requires a high-performing Graphics Processing Unit (GPU) and considerable internal storage. Unfortunately, most embedded devices do not have high performing GPU and huge internal storage.
Thus, this project proposes the use of efficient and low-bit neural network compression to make the existing object detection model deployable on embedded devices, while ensuring that the accuracy and speed are not too compromised. |
| first_indexed | 2024-10-01T07:54:11Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/158549 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:54:11Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1585492022-06-05T06:02:40Z Traffic sign detection system with efficient and low-bit neural network compression in computer vision Thin Lat Han Loke Yuan Ren School of Computer Science and Engineering yrloke@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision In a traffic setting, traffic sign detection is a critical task. It is becoming even more important as the number of vehicles on the road grows, increasing the accident rate. Object detection in embedded devices can be used to alert distracted drivers to traffic signs so that the signs can direct them on the road. Object identification on images can have a high level of accuracy and speed, which is required by a traffic sign detection system to recognize traffic signs quickly and precisely so that road safety can be ensured. However, to achieve the high accuracy and speed requirements, it usually requires a high-performing Graphics Processing Unit (GPU) and considerable internal storage. Unfortunately, most embedded devices do not have high performing GPU and huge internal storage. Thus, this project proposes the use of efficient and low-bit neural network compression to make the existing object detection model deployable on embedded devices, while ensuring that the accuracy and speed are not too compromised. Bachelor of Engineering (Computer Engineering) 2022-06-05T06:02:40Z 2022-06-05T06:02:40Z 2022 Final Year Project (FYP) Thin Lat Han (2022). Traffic sign detection system with efficient and low-bit neural network compression in computer vision. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158549 https://hdl.handle.net/10356/158549 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Thin Lat Han Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title | Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title_full | Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title_fullStr | Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title_full_unstemmed | Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title_short | Traffic sign detection system with efficient and low-bit neural network compression in computer vision |
| title_sort | traffic sign detection system with efficient and low bit neural network compression in computer vision |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/158549 |
| work_keys_str_mv | AT thinlathan trafficsigndetectionsystemwithefficientandlowbitneuralnetworkcompressionincomputervision |