Traffic Intersection Re-Identification Using Monocular Camera Sensors
Perception of road structures especially the traffic intersections by visual sensors is an essential task for automated driving. However, compared with intersection detection or visual place recognition, intersection re-identification (intersection re-ID) strongly affects driving behavior decisions...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/22/6515 |
id |
doaj-2dc53d9000514e35994dc9ecd1bb3f84 |
---|---|
record_format |
Article |
spelling |
doaj-2dc53d9000514e35994dc9ecd1bb3f842020-11-25T04:10:02ZengMDPI AGSensors1424-82202020-11-01206515651510.3390/s20226515Traffic Intersection Re-Identification Using Monocular Camera SensorsLu Xiong0Zhenwen Deng1Yuyao Huang2Weixin Du3Xiaolong Zhao4Chengyu Lu5Wei Tian6Institute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaInstitute of Intelligent Vehicles, School of Automotive Studies, Tongji University, Shanghai 201804, ChinaPerception of road structures especially the traffic intersections by visual sensors is an essential task for automated driving. However, compared with intersection detection or visual place recognition, intersection re-identification (intersection re-ID) strongly affects driving behavior decisions with given routes, yet has long been neglected by researchers. This paper strives to explore intersection re-ID by a monocular camera sensor. We propose a Hybrid Double-Level re-identification approach which exploits two branches of Deep Convolutional Neural Network to accomplish multi-task including classification of intersection and its fine attributes, and global localization in topological maps. Furthermore, we propose a mixed loss training for the network to learn the similarity of two intersection images. As no public datasets are available for the intersection re-ID task, based on the work of RobotCar, we propose a new dataset with carefully-labeled intersection attributes, which is called “RobotCar Intersection” and covers more than 30,000 images of eight intersections in different seasons and day time. Additionally, we provide another dataset, called “Campus Intersection” consisting of panoramic images of eight intersections in a university campus to verify our updating strategy of topology map. Experimental results demonstrate that our proposed approach can achieve promising results in re-ID of both coarse road intersections and its global pose, and is well suited for updating and completion of topological maps.https://www.mdpi.com/1424-8220/20/22/6515monocular camera sensordeep learningintersection datasetintersection re-identificationimage matching |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lu Xiong Zhenwen Deng Yuyao Huang Weixin Du Xiaolong Zhao Chengyu Lu Wei Tian |
spellingShingle |
Lu Xiong Zhenwen Deng Yuyao Huang Weixin Du Xiaolong Zhao Chengyu Lu Wei Tian Traffic Intersection Re-Identification Using Monocular Camera Sensors Sensors monocular camera sensor deep learning intersection dataset intersection re-identification image matching |
author_facet |
Lu Xiong Zhenwen Deng Yuyao Huang Weixin Du Xiaolong Zhao Chengyu Lu Wei Tian |
author_sort |
Lu Xiong |
title |
Traffic Intersection Re-Identification Using Monocular Camera Sensors |
title_short |
Traffic Intersection Re-Identification Using Monocular Camera Sensors |
title_full |
Traffic Intersection Re-Identification Using Monocular Camera Sensors |
title_fullStr |
Traffic Intersection Re-Identification Using Monocular Camera Sensors |
title_full_unstemmed |
Traffic Intersection Re-Identification Using Monocular Camera Sensors |
title_sort |
traffic intersection re-identification using monocular camera sensors |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-11-01 |
description |
Perception of road structures especially the traffic intersections by visual sensors is an essential task for automated driving. However, compared with intersection detection or visual place recognition, intersection re-identification (intersection re-ID) strongly affects driving behavior decisions with given routes, yet has long been neglected by researchers. This paper strives to explore intersection re-ID by a monocular camera sensor. We propose a Hybrid Double-Level re-identification approach which exploits two branches of Deep Convolutional Neural Network to accomplish multi-task including classification of intersection and its fine attributes, and global localization in topological maps. Furthermore, we propose a mixed loss training for the network to learn the similarity of two intersection images. As no public datasets are available for the intersection re-ID task, based on the work of RobotCar, we propose a new dataset with carefully-labeled intersection attributes, which is called “RobotCar Intersection” and covers more than 30,000 images of eight intersections in different seasons and day time. Additionally, we provide another dataset, called “Campus Intersection” consisting of panoramic images of eight intersections in a university campus to verify our updating strategy of topology map. Experimental results demonstrate that our proposed approach can achieve promising results in re-ID of both coarse road intersections and its global pose, and is well suited for updating and completion of topological maps. |
topic |
monocular camera sensor deep learning intersection dataset intersection re-identification image matching |
url |
https://www.mdpi.com/1424-8220/20/22/6515 |
work_keys_str_mv |
AT luxiong trafficintersectionreidentificationusingmonocularcamerasensors AT zhenwendeng trafficintersectionreidentificationusingmonocularcamerasensors AT yuyaohuang trafficintersectionreidentificationusingmonocularcamerasensors AT weixindu trafficintersectionreidentificationusingmonocularcamerasensors AT xiaolongzhao trafficintersectionreidentificationusingmonocularcamerasensors AT chengyulu trafficintersectionreidentificationusingmonocularcamerasensors AT weitian trafficintersectionreidentificationusingmonocularcamerasensors |
_version_ |
1724420821057798144 |