Lane detection algorithm for autonomous vehicles using machine learning
Lane detection is a crucial element of any advanced driver assistance system or autonomous driving technology. Developing a robust lane detection system capable of navigating various road conditions, sucis essential. Traditional techniques that rely on image processing and model fitting have demonst...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2024
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/177301 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Lane detection is a crucial element of any advanced driver assistance system or autonomous driving technology. Developing a robust lane detection system capable of navigating various road conditions, sucis essential. Traditional techniques that rely on image processing and model fitting have demonstrated proficiency in detecting lanes through distinct features but often falter under suboptimal conditions.
The evolution of machine learning and enhanced computational capabilities have enabled the creation of self-learning algorithms designed to manage the intricate task of extracting and interpreting relevant features for lane identification. However, these models generally require significant computational resources, leading to extended training and prediction times. In order to be on par or better than the conventional methods, a significant amount of training data is needed for the machine learning model to be efficient and accurate.
Hence this report aims on the machine learning model Efficient Neural Network (Enet) to be able to properly perform lane detection accurately and efficiently |
|---|