A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video

Vehicle detection is expected to be robust and efficient in various scenes. We propose a multivehicle detection method, which consists of YOLO under the Darknet framework. We also improve the YOLO-voc structure according to the change of the target scene and traffic flow. The classification training...

Full description

Saved in:
Bibliographic Details
Main Authors: Xun Li, Yao Liu, Zhengfan Zhao, Yue Zhang, Li He
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2018/7075814
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849307848127807488
author Xun Li
Yao Liu
Zhengfan Zhao
Yue Zhang
Li He
author_facet Xun Li
Yao Liu
Zhengfan Zhao
Yue Zhang
Li He
author_sort Xun Li
collection DOAJ
description Vehicle detection is expected to be robust and efficient in various scenes. We propose a multivehicle detection method, which consists of YOLO under the Darknet framework. We also improve the YOLO-voc structure according to the change of the target scene and traffic flow. The classification training model is obtained based on ImageNet and the parameters are fine-tuned according to the training results and the vehicle characteristics. Finally, we obtain an effective YOLO-vocRV network for road vehicles detection. In order to verify the performance of our method, the experiment is carried out on different vehicle flow states and compared with the classical YOLO-voc, YOLO 9000, and YOLO v3. The experimental results show that our method achieves the detection rate of 98.6% in free flow state, 97.8% in synchronous flow state, and 96.3% in blocking flow state, respectively. In addition, our proposed method has less false detection rate than previous works and shows good robustness.
format Article
id doaj-art-2a4b50e7f5044f72a3fb6435097055f5
institution Kabale University
issn 0197-6729
2042-3195
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-2a4b50e7f5044f72a3fb6435097055f52025-08-20T03:54:37ZengWileyJournal of Advanced Transportation0197-67292042-31952018-01-01201810.1155/2018/70758147075814A Deep Learning Approach of Vehicle Multitarget Detection from Traffic VideoXun Li0Yao Liu1Zhengfan Zhao2Yue Zhang3Li He4School of Electronic Information, Xi'an Polytechnical University, Xi’an 710048, ChinaSchool of Electronic Information, Xi'an Polytechnical University, Xi’an 710048, ChinaBeijing Special Electromechanical Technology Research Institute, Beijing 10012, ChinaSchool of Electronic Information, Xi'an Polytechnical University, Xi’an 710048, ChinaGuangdong University of Technology, Guangzhou 510006, ChinaVehicle detection is expected to be robust and efficient in various scenes. We propose a multivehicle detection method, which consists of YOLO under the Darknet framework. We also improve the YOLO-voc structure according to the change of the target scene and traffic flow. The classification training model is obtained based on ImageNet and the parameters are fine-tuned according to the training results and the vehicle characteristics. Finally, we obtain an effective YOLO-vocRV network for road vehicles detection. In order to verify the performance of our method, the experiment is carried out on different vehicle flow states and compared with the classical YOLO-voc, YOLO 9000, and YOLO v3. The experimental results show that our method achieves the detection rate of 98.6% in free flow state, 97.8% in synchronous flow state, and 96.3% in blocking flow state, respectively. In addition, our proposed method has less false detection rate than previous works and shows good robustness.http://dx.doi.org/10.1155/2018/7075814
spellingShingle Xun Li
Yao Liu
Zhengfan Zhao
Yue Zhang
Li He
A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
Journal of Advanced Transportation
title A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
title_full A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
title_fullStr A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
title_full_unstemmed A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
title_short A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video
title_sort deep learning approach of vehicle multitarget detection from traffic video
url http://dx.doi.org/10.1155/2018/7075814
work_keys_str_mv AT xunli adeeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT yaoliu adeeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT zhengfanzhao adeeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT yuezhang adeeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT lihe adeeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT xunli deeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT yaoliu deeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT zhengfanzhao deeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT yuezhang deeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo
AT lihe deeplearningapproachofvehiclemultitargetdetectionfromtrafficvideo