Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning
The use of night vision systems in vehicles is becoming increasingly common. Several approaches using infrared sensors have been proposed in the literature to detect vehicles in far infrared (FIR) images. However, these systems still have low vehicle detection rates and performance could be improved...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2016-01-01
|
Series: | Journal of Sensors |
Online Access: | http://dx.doi.org/10.1155/2016/3403451 |
id |
doaj-bb44de4325214d53871b0c79a15ae5f2 |
---|---|
record_format |
Article |
spelling |
doaj-bb44de4325214d53871b0c79a15ae5f22020-11-24T22:23:13ZengHindawi LimitedJournal of Sensors1687-725X1687-72682016-01-01201610.1155/2016/34034513403451Night-Time Vehicle Sensing in Far Infrared Image with Deep LearningHai Wang0Yingfeng Cai1Xiaobo Chen2Long Chen3School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaThe use of night vision systems in vehicles is becoming increasingly common. Several approaches using infrared sensors have been proposed in the literature to detect vehicles in far infrared (FIR) images. However, these systems still have low vehicle detection rates and performance could be improved. This paper presents a novel method to detect vehicles using a far infrared automotive sensor. Firstly, vehicle candidates are generated using a constant threshold from the infrared frame. Contours are then generated by using a local adaptive threshold based on maximum distance, which decreases the number of processing regions for classification and reduces the false positive rate. Finally, vehicle candidates are verified using a deep belief network (DBN) based classifier. The detection rate is 93.9% which is achieved on a database of 5000 images and video streams. This result is approximately a 2.5% improvement on previously reported methods and the false detection rate is also the lowest among them.http://dx.doi.org/10.1155/2016/3403451 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hai Wang Yingfeng Cai Xiaobo Chen Long Chen |
spellingShingle |
Hai Wang Yingfeng Cai Xiaobo Chen Long Chen Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning Journal of Sensors |
author_facet |
Hai Wang Yingfeng Cai Xiaobo Chen Long Chen |
author_sort |
Hai Wang |
title |
Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning |
title_short |
Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning |
title_full |
Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning |
title_fullStr |
Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning |
title_full_unstemmed |
Night-Time Vehicle Sensing in Far Infrared Image with Deep Learning |
title_sort |
night-time vehicle sensing in far infrared image with deep learning |
publisher |
Hindawi Limited |
series |
Journal of Sensors |
issn |
1687-725X 1687-7268 |
publishDate |
2016-01-01 |
description |
The use of night vision systems in vehicles is becoming increasingly common. Several approaches using infrared sensors have been proposed in the literature to detect vehicles in far infrared (FIR) images. However, these systems still have low vehicle detection rates and performance could be improved. This paper presents a novel method to detect vehicles using a far infrared automotive sensor. Firstly, vehicle candidates are generated using a constant threshold from the infrared frame. Contours are then generated by using a local adaptive threshold based on maximum distance, which decreases the number of processing regions for classification and reduces the false positive rate. Finally, vehicle candidates are verified using a deep belief network (DBN) based classifier. The detection rate is 93.9% which is achieved on a database of 5000 images and video streams. This result is approximately a 2.5% improvement on previously reported methods and the false detection rate is also the lowest among them. |
url |
http://dx.doi.org/10.1155/2016/3403451 |
work_keys_str_mv |
AT haiwang nighttimevehiclesensinginfarinfraredimagewithdeeplearning AT yingfengcai nighttimevehiclesensinginfarinfraredimagewithdeeplearning AT xiaobochen nighttimevehiclesensinginfarinfraredimagewithdeeplearning AT longchen nighttimevehiclesensinginfarinfraredimagewithdeeplearning |
_version_ |
1725765360892772352 |