Lane detection algorithm for autonomous vehicle using machine learning
Lane detection has been one of research areas in computer vision for decades. Traditional computer vision algorithms such as Canny edge detector and Hough Transform are commonly used in lane detection model. However, these models only work well under well-conditioned roads with clear lane marks and...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/167291 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-167291 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1672912023-05-27T16:50:50Z Lane detection algorithm for autonomous vehicle using machine learning Wu, Guan Jie Lyu Chen School of Mechanical and Aerospace Engineering lyuchen@ntu.edu.sg Engineering::Mechanical engineering Lane detection has been one of research areas in computer vision for decades. Traditional computer vision algorithms such as Canny edge detector and Hough Transform are commonly used in lane detection model. However, these models only work well under well-conditioned roads with clear lane marks and no occlusion. Hence, there is a need to shift from traditional computer vision algorithms to deep learning method in feature extraction. Convolution neural network (CNN) has been the de facto feature extraction module in computer vision. Spatial CNN (SCNN), the winner of 2017 TuSimple lane detection challenge, propose a special message passing mechanism for long and thin structure. Nonetheless, it can only run at about 20 frames per second (FPS) on NVIDIA GeForce RTX 2080 Ti GPU due to the heavy computational load of the special message passing mechanism. This project explores the possibility of using transformer architecture as the feature extraction module in a lane detection model. This is because the self-attention layers with sufficient heads can express any convolutional layer. The performance of lane detection model based on SegFormer was compared with SCNN in terms of accuracy, F1-measure and FPS. The PyTorch model was converted to TensorRT engine through intermediary ONNX which further boost the FPS of the model during inference. From the experiments, accuracy of SegFormer is higher than SCNN by 0.35% on TuSimple dataset while being 4 times faster than SCNN in inference speed. For CULane dataset, the F1-measure of SegFormer is lower than SCNN by 1.45% but the inference speed of SegFormer is 2 times faster than SCNN in this case. This justifies the trade-off between accuracy and computational load of the model and proven the strong feature representation power of transformer without any incorporation of lane prior. Bachelor of Engineering (Mechanical Engineering) 2023-05-25T07:25:31Z 2023-05-25T07:25:31Z 2023 Final Year Project (FYP) Wu, G. J. (2023). Lane detection algorithm for autonomous vehicle using machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167291 https://hdl.handle.net/10356/167291 en C072 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Mechanical engineering |
spellingShingle |
Engineering::Mechanical engineering Wu, Guan Jie Lane detection algorithm for autonomous vehicle using machine learning |
description |
Lane detection has been one of research areas in computer vision for decades. Traditional computer vision algorithms such as Canny edge detector and Hough Transform are commonly used in lane detection model. However, these models only work well under well-conditioned roads with clear lane marks and no occlusion. Hence, there is a need to shift from traditional computer vision algorithms to deep learning method in feature extraction. Convolution neural network (CNN) has been the de facto feature extraction module in computer vision. Spatial CNN (SCNN), the winner of 2017 TuSimple lane detection challenge, propose a special message passing mechanism for long and thin structure. Nonetheless, it can only run at about 20 frames per second (FPS) on NVIDIA GeForce RTX 2080 Ti GPU due to the heavy computational load of the special message passing mechanism.
This project explores the possibility of using transformer architecture as the feature extraction module in a lane detection model. This is because the self-attention layers with sufficient heads can express any convolutional layer. The performance of lane detection model based on SegFormer was compared with SCNN in terms of accuracy, F1-measure and FPS. The PyTorch model was converted to TensorRT engine through intermediary ONNX which further boost the FPS of the model during inference.
From the experiments, accuracy of SegFormer is higher than SCNN by 0.35% on TuSimple dataset while being 4 times faster than SCNN in inference speed. For CULane dataset, the F1-measure of SegFormer is lower than SCNN by 1.45% but the inference speed of SegFormer is 2 times faster than SCNN in this case. This justifies the trade-off between accuracy and computational load of the model and proven the strong feature representation power of transformer without any incorporation of lane prior. |
author2 |
Lyu Chen |
author_facet |
Lyu Chen Wu, Guan Jie |
format |
Final Year Project |
author |
Wu, Guan Jie |
author_sort |
Wu, Guan Jie |
title |
Lane detection algorithm for autonomous vehicle using machine learning |
title_short |
Lane detection algorithm for autonomous vehicle using machine learning |
title_full |
Lane detection algorithm for autonomous vehicle using machine learning |
title_fullStr |
Lane detection algorithm for autonomous vehicle using machine learning |
title_full_unstemmed |
Lane detection algorithm for autonomous vehicle using machine learning |
title_sort |
lane detection algorithm for autonomous vehicle using machine learning |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/167291 |
_version_ |
1772829179284291584 |