Video-based traffic analysis
Detecting lane markers reliably and accurately is a crucial yet challenging task. While modern deep-learning-based lane detection has achieved remarkable performance addressing complex topologies of traffic lines and diverse driving scenarios, it is often at the expense of real-time efficiency. Con...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/153491 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-153491 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1534912021-12-06T05:32:35Z Video-based traffic analysis Fong, Hao Wei Miao Chun Yan School of Computer Science and Engineering Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Wang Di ASCYMiao@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Detecting lane markers reliably and accurately is a crucial yet challenging task. While modern deep-learning-based lane detection has achieved remarkable performance addressing complex topologies of traffic lines and diverse driving scenarios, it is often at the expense of real-time efficiency. Conventional detection of lane markers uses deep segmentation approaches involving pixel-level dense prediction representation to detect lane instances. However, the dense prediction property often bottlenecks the efficiency of identifying lane markers. In this final year project, lane detection is formulated as a row-wise classification problem. I formulate row-wise classification using predefined row anchors and grid cells that are smaller than the size of an image. The computation complexity can be reduced considerably because lane markers are computed by classifying each grid instead of each pixel. Experimentation with the viability of improved loss calculation strategies is also proposed. Loss calculation strategies like focal loss allow training to focus on misclassified examples, specifically complex scenarios, allowing the model to address no visual clues scenarios better. In this context, no-visual-clues of lanes markers are a result of challenging scenarios such as severe occlusion and poor illumination conditions. When used in conjunction during model training, preliminary results have seen positive results and show additional performance gain on top of row-wise classification formulation. This project has been evaluated extensively on two widely used lane detection datasets. The lightweight model can achieve 220+frames per second while having a performance gain of 1.14% from the previous UFAST method. Finally, an ablation study is performed to present the performance gains for our improvement strategy Bachelor of Engineering (Computer Engineering) 2021-12-06T05:32:35Z 2021-12-06T05:32:35Z 2021 Final Year Project (FYP) Fong, H. W. (2021). Video-based traffic analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153491 https://hdl.handle.net/10356/153491 en SCSE20-1077 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::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Fong, Hao Wei Video-based traffic analysis |
description |
Detecting lane markers reliably and accurately is a crucial yet challenging task. While modern deep-learning-based lane detection has achieved remarkable performance addressing complex topologies of traffic lines and diverse driving scenarios, it is often at the expense of real-time efficiency. Conventional detection of lane markers uses deep segmentation approaches involving pixel-level dense prediction representation to detect lane instances. However, the dense prediction property often bottlenecks the efficiency of identifying lane markers. In this final year project, lane detection is formulated as a row-wise classification problem. I formulate row-wise classification using predefined row anchors and grid cells that are smaller than the size of an image. The computation complexity can be reduced considerably because lane markers are computed by classifying each grid instead of each pixel. Experimentation with the viability of improved loss calculation strategies is also proposed. Loss calculation strategies like focal loss allow training to focus on misclassified examples, specifically complex scenarios, allowing the model to address no visual clues scenarios better. In this context, no-visual-clues of lanes markers are a result of challenging scenarios such as severe occlusion and poor illumination conditions. When used in conjunction during model training, preliminary results have seen positive results and show additional performance gain on top of row-wise classification formulation. This project has been evaluated extensively on two widely used lane detection datasets. The lightweight model can achieve 220+frames per second while having a performance gain of 1.14% from the previous UFAST method. Finally, an ablation study is performed to present the performance gains for our improvement strategy |
author2 |
Miao Chun Yan |
author_facet |
Miao Chun Yan Fong, Hao Wei |
format |
Final Year Project |
author |
Fong, Hao Wei |
author_sort |
Fong, Hao Wei |
title |
Video-based traffic analysis |
title_short |
Video-based traffic analysis |
title_full |
Video-based traffic analysis |
title_fullStr |
Video-based traffic analysis |
title_full_unstemmed |
Video-based traffic analysis |
title_sort |
video-based traffic analysis |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/153491 |
_version_ |
1718928707583737856 |