Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods

This thesis is written based on two main topics: Scene semantic recognition and road lane marks recognition. The thesis first reviews the studies of general scene understanding or recognition method using semantic segmentation approaches, and then focuses on a more specific topic of analyzing roa...

Full description

Saved in:
Bibliographic Details
Main Author: Zhou, Xiaosong
Other Authors: Huang Guangbin
Format: Theses and Dissertations
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/82854
http://hdl.handle.net/10220/46658
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-82854
record_format dspace
spelling sg-ntu-dr.10356-828542023-07-04T16:26:00Z Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods Zhou, Xiaosong Huang Guangbin School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering This thesis is written based on two main topics: Scene semantic recognition and road lane marks recognition. The thesis first reviews the studies of general scene understanding or recognition method using semantic segmentation approaches, and then focuses on a more specific topic of analyzing road scene images for detecting road lane marks. Semantic segmentation has been a popular topic in the field of computer vision research. The main purpose of semantic segmentation is to label pixels of interest in an image with corresponding categories of the objects. This thesis mainly focuses on scene recognition, a branch of semantic segmentation which takes more contextual information into consideration. This thesis presents an experimental study in which a multi-task method for scene recognition is proposed. In this method, edge information is used in enhancing recognition performance. A network which outputs both edge detection map and pixel-wise segmentation is designed. The network is based on FCN and the prediction branches of the two outputs are parallel. Each branch uses multi-scale features concatenation as the image representations. The method expects that the information from edge detection could contribute to the ability of extracting image features for pixel-wise segmentation. Modern approaches on multiple road lane marks detection are facing several problems. First, insufficient database make related solutions with machine learning technique difficult to train a robust model for application; second, current researches focus on single lane marks detection, which pays less attention to entire roads’ condition. To solve the problems, a database with proper ground truth of marks’ label set is constructed and a method is developed for detecting and classifying road lane marks of entire roads with Extreme Learning Machines (ELM). The implementation result shows promising performance and further improvement could be expected. Master of Engineering 2018-11-19T01:47:13Z 2019-12-06T15:06:55Z 2018-11-19T01:47:13Z 2019-12-06T15:06:55Z 2018 Thesis Zhou, X. (2018). Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/82854 http://hdl.handle.net/10220/46658 10.32657/10220/46658 en 119 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Zhou, Xiaosong
Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
description This thesis is written based on two main topics: Scene semantic recognition and road lane marks recognition. The thesis first reviews the studies of general scene understanding or recognition method using semantic segmentation approaches, and then focuses on a more specific topic of analyzing road scene images for detecting road lane marks. Semantic segmentation has been a popular topic in the field of computer vision research. The main purpose of semantic segmentation is to label pixels of interest in an image with corresponding categories of the objects. This thesis mainly focuses on scene recognition, a branch of semantic segmentation which takes more contextual information into consideration. This thesis presents an experimental study in which a multi-task method for scene recognition is proposed. In this method, edge information is used in enhancing recognition performance. A network which outputs both edge detection map and pixel-wise segmentation is designed. The network is based on FCN and the prediction branches of the two outputs are parallel. Each branch uses multi-scale features concatenation as the image representations. The method expects that the information from edge detection could contribute to the ability of extracting image features for pixel-wise segmentation. Modern approaches on multiple road lane marks detection are facing several problems. First, insufficient database make related solutions with machine learning technique difficult to train a robust model for application; second, current researches focus on single lane marks detection, which pays less attention to entire roads’ condition. To solve the problems, a database with proper ground truth of marks’ label set is constructed and a method is developed for detecting and classifying road lane marks of entire roads with Extreme Learning Machines (ELM). The implementation result shows promising performance and further improvement could be expected.
author2 Huang Guangbin
author_facet Huang Guangbin
Zhou, Xiaosong
format Theses and Dissertations
author Zhou, Xiaosong
author_sort Zhou, Xiaosong
title Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
title_short Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
title_full Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
title_fullStr Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
title_full_unstemmed Experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
title_sort experimental study on scene recognition and multiple road lane marks detection based on machine learning methods
publishDate 2018
url https://hdl.handle.net/10356/82854
http://hdl.handle.net/10220/46658
_version_ 1772827183296806912