Monocular Road Detection Using Structured Random Forest
Road detection is a key task for autonomous land vehicles. Monocular vision-based road-detection algorithms are mostly based on machine learning approaches and are usually cast as classification problems. However, the pixel-wise classifiers are faced with the ambiguity caused by changes in road appe...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2016-05-01
|
Series: | International Journal of Advanced Robotic Systems |
Online Access: | https://doi.org/10.5772/63561 |
id |
doaj-69be26a0a5144fa080b62f39b0426ae7 |
---|---|
record_format |
Article |
spelling |
doaj-69be26a0a5144fa080b62f39b0426ae72020-11-25T03:39:18ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142016-05-011310.5772/6356110.5772_63561Monocular Road Detection Using Structured Random ForestLiang Xiao0Bin Dai1Daxue Liu2Dawei Zhao3Tao Wu4 College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha, Hunan, China College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha, Hunan, China College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha, Hunan, China College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha, Hunan, China College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha, Hunan, ChinaRoad detection is a key task for autonomous land vehicles. Monocular vision-based road-detection algorithms are mostly based on machine learning approaches and are usually cast as classification problems. However, the pixel-wise classifiers are faced with the ambiguity caused by changes in road appearance, illumination and weather. An effective way to reduce the ambiguity is to model the contextual information with structured learning and prediction. Currently, the widely used structured prediction model in road detection is the Markov random field or conditional random field. However, the random field-based methods require additional complex optimization after pixel-wise classification, making them unsuitable for real-time applications. In this paper, we present a structured random forest-based road-detection algorithm which is capable of modelling the contextual information efficiently. By mapping the structured label space to a discrete label space, the test function of each split node can be trained in a similar way to that of the classical random forests. Structured random forests make use of the contextual information of image patches as well as the structural information of the labels to get more consistent results. Besides this benefit, by predicting a batch of pixels in a single classification, the structured random forest-based road detection can be much more efficient than the conventional pixel-wise random forest. Experimental results tested on the KITTI-ROAD dataset and data collected in typical unstructured environments show that structured random forest-based road detection outperforms the classical pixel-wise random forest both in accuracy and efficiency.https://doi.org/10.5772/63561 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liang Xiao Bin Dai Daxue Liu Dawei Zhao Tao Wu |
spellingShingle |
Liang Xiao Bin Dai Daxue Liu Dawei Zhao Tao Wu Monocular Road Detection Using Structured Random Forest International Journal of Advanced Robotic Systems |
author_facet |
Liang Xiao Bin Dai Daxue Liu Dawei Zhao Tao Wu |
author_sort |
Liang Xiao |
title |
Monocular Road Detection Using Structured Random Forest |
title_short |
Monocular Road Detection Using Structured Random Forest |
title_full |
Monocular Road Detection Using Structured Random Forest |
title_fullStr |
Monocular Road Detection Using Structured Random Forest |
title_full_unstemmed |
Monocular Road Detection Using Structured Random Forest |
title_sort |
monocular road detection using structured random forest |
publisher |
SAGE Publishing |
series |
International Journal of Advanced Robotic Systems |
issn |
1729-8814 |
publishDate |
2016-05-01 |
description |
Road detection is a key task for autonomous land vehicles. Monocular vision-based road-detection algorithms are mostly based on machine learning approaches and are usually cast as classification problems. However, the pixel-wise classifiers are faced with the ambiguity caused by changes in road appearance, illumination and weather. An effective way to reduce the ambiguity is to model the contextual information with structured learning and prediction. Currently, the widely used structured prediction model in road detection is the Markov random field or conditional random field. However, the random field-based methods require additional complex optimization after pixel-wise classification, making them unsuitable for real-time applications. In this paper, we present a structured random forest-based road-detection algorithm which is capable of modelling the contextual information efficiently. By mapping the structured label space to a discrete label space, the test function of each split node can be trained in a similar way to that of the classical random forests. Structured random forests make use of the contextual information of image patches as well as the structural information of the labels to get more consistent results. Besides this benefit, by predicting a batch of pixels in a single classification, the structured random forest-based road detection can be much more efficient than the conventional pixel-wise random forest. Experimental results tested on the KITTI-ROAD dataset and data collected in typical unstructured environments show that structured random forest-based road detection outperforms the classical pixel-wise random forest both in accuracy and efficiency. |
url |
https://doi.org/10.5772/63561 |
work_keys_str_mv |
AT liangxiao monocularroaddetectionusingstructuredrandomforest AT bindai monocularroaddetectionusingstructuredrandomforest AT daxueliu monocularroaddetectionusingstructuredrandomforest AT daweizhao monocularroaddetectionusingstructuredrandomforest AT taowu monocularroaddetectionusingstructuredrandomforest |
_version_ |
1724539738272038912 |