A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC
Lane detection plays an important role in improving autopilot’s safety. In this paper, a novel lane-division-lines detection method is proposed, which exhibits good performances in abnormal illumination and lane occlusion. It includes three major components: First, the captured image is co...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/18/4028 |
id |
doaj-ae892aa2dd0441dfbcb1a6cf3b06292b |
---|---|
record_format |
Article |
spelling |
doaj-ae892aa2dd0441dfbcb1a6cf3b06292b2020-11-25T02:09:34ZengMDPI AGSensors1424-82202019-09-011918402810.3390/s19184028s19184028A Lane Detection Method Based on a Ridge Detector and Regional G-RANSACZefeng Lu0Ying Xu1Xin Shan2Licai Liu3Xingzheng Wang4Jianhao Shen5College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaLane detection plays an important role in improving autopilot’s safety. In this paper, a novel lane-division-lines detection method is proposed, which exhibits good performances in abnormal illumination and lane occlusion. It includes three major components: First, the captured image is converted to aerial view to make full use of parallel lanes’ characteristics. Second, a ridge detector is proposed to extract each lane’s feature points and remove noise points with an adaptable neural network (ANN). Last, the lane-division-lines are accurately fitted by an improved random sample consensus (RANSAC), termed the (regional) gaussian distribution random sample consensus (G-RANSAC). To test the performances of this novel lane detection method, we proposed a new index named the lane departure index (LDI) describing the departure degree between true lane and predicted lane. Experimental results verified the superior performances of the proposed method over others in different testing scenarios, respectively achieving 99.02%, 96.92%, 96.65% and 91.61% true-positive rates (TPR); and 66.16, 54.85, 55.98 and 52.61 LDIs in four different types of testing scenarios.https://www.mdpi.com/1424-8220/19/18/4028lane division lines’ detectionridge detectorBP neural networkfeature extractionRANSAC |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zefeng Lu Ying Xu Xin Shan Licai Liu Xingzheng Wang Jianhao Shen |
spellingShingle |
Zefeng Lu Ying Xu Xin Shan Licai Liu Xingzheng Wang Jianhao Shen A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC Sensors lane division lines’ detection ridge detector BP neural network feature extraction RANSAC |
author_facet |
Zefeng Lu Ying Xu Xin Shan Licai Liu Xingzheng Wang Jianhao Shen |
author_sort |
Zefeng Lu |
title |
A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC |
title_short |
A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC |
title_full |
A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC |
title_fullStr |
A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC |
title_full_unstemmed |
A Lane Detection Method Based on a Ridge Detector and Regional G-RANSAC |
title_sort |
lane detection method based on a ridge detector and regional g-ransac |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-09-01 |
description |
Lane detection plays an important role in improving autopilot’s safety. In this paper, a novel lane-division-lines detection method is proposed, which exhibits good performances in abnormal illumination and lane occlusion. It includes three major components: First, the captured image is converted to aerial view to make full use of parallel lanes’ characteristics. Second, a ridge detector is proposed to extract each lane’s feature points and remove noise points with an adaptable neural network (ANN). Last, the lane-division-lines are accurately fitted by an improved random sample consensus (RANSAC), termed the (regional) gaussian distribution random sample consensus (G-RANSAC). To test the performances of this novel lane detection method, we proposed a new index named the lane departure index (LDI) describing the departure degree between true lane and predicted lane. Experimental results verified the superior performances of the proposed method over others in different testing scenarios, respectively achieving 99.02%, 96.92%, 96.65% and 91.61% true-positive rates (TPR); and 66.16, 54.85, 55.98 and 52.61 LDIs in four different types of testing scenarios. |
topic |
lane division lines’ detection ridge detector BP neural network feature extraction RANSAC |
url |
https://www.mdpi.com/1424-8220/19/18/4028 |
work_keys_str_mv |
AT zefenglu alanedetectionmethodbasedonaridgedetectorandregionalgransac AT yingxu alanedetectionmethodbasedonaridgedetectorandregionalgransac AT xinshan alanedetectionmethodbasedonaridgedetectorandregionalgransac AT licailiu alanedetectionmethodbasedonaridgedetectorandregionalgransac AT xingzhengwang alanedetectionmethodbasedonaridgedetectorandregionalgransac AT jianhaoshen alanedetectionmethodbasedonaridgedetectorandregionalgransac AT zefenglu lanedetectionmethodbasedonaridgedetectorandregionalgransac AT yingxu lanedetectionmethodbasedonaridgedetectorandregionalgransac AT xinshan lanedetectionmethodbasedonaridgedetectorandregionalgransac AT licailiu lanedetectionmethodbasedonaridgedetectorandregionalgransac AT xingzhengwang lanedetectionmethodbasedonaridgedetectorandregionalgransac AT jianhaoshen lanedetectionmethodbasedonaridgedetectorandregionalgransac |
_version_ |
1724922965602074624 |