Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections
In the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/9/3079 |
id |
doaj-eed13f951792404eb6b6cc8fa24bb324 |
---|---|
record_format |
Article |
spelling |
doaj-eed13f951792404eb6b6cc8fa24bb3242020-11-25T03:05:54ZengMDPI AGApplied Sciences2076-34172020-04-01103079307910.3390/app10093079Optimized YOLOv3 Algorithm and Its Application in Traffic Flow DetectionsYi-Qi Huang0Jia-Chun Zheng1Shi-Dan Sun2Cheng-Fu Yang3Jing Liu4Navigation Institute, Jimei University, Xiamen 361021, ChinaSchool of Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Information Engineering, Jimei University, Xiamen 361021, ChinaDepartment of Chemical and Materials Engineering, National University of Kaohsiung, Kaohsiung 811, TaiwanSchool of Information Engineering, Jimei University, Xiamen 361021, ChinaIn the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during traffic flows. Therefore, we propose a single-stage deep neural network YOLOv3-DL, which is based on the Tensorflow framework to improve this problem. The network structure is optimized by introducing the idea of spatial pyramid pooling, then the loss function is redefined, and a weight regularization method is introduced, for that, the real-time detections and statistics of traffic flows can be implemented effectively. The optimization algorithm we use is the DL-CAR data set for end-to-end network training and experiments with data sets under different scenarios and weathers. The analyses of experimental data show that the optimized algorithm can improve the vehicles’ detection accuracy on the test set by 3.86%. Experiments on test sets in different environments have improved the detection accuracy rate by 4.53%, indicating that the algorithm has high robustness. At the same time, the detection accuracy and speed of the investigated algorithm are higher than other algorithms, indicating that the algorithm has higher detection performance.https://www.mdpi.com/2076-3417/10/9/3079intelligent transportationvehicle detectiontraffic flowloss functionYOLOv3 mode |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yi-Qi Huang Jia-Chun Zheng Shi-Dan Sun Cheng-Fu Yang Jing Liu |
spellingShingle |
Yi-Qi Huang Jia-Chun Zheng Shi-Dan Sun Cheng-Fu Yang Jing Liu Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections Applied Sciences intelligent transportation vehicle detection traffic flow loss function YOLOv3 mode |
author_facet |
Yi-Qi Huang Jia-Chun Zheng Shi-Dan Sun Cheng-Fu Yang Jing Liu |
author_sort |
Yi-Qi Huang |
title |
Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections |
title_short |
Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections |
title_full |
Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections |
title_fullStr |
Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections |
title_full_unstemmed |
Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections |
title_sort |
optimized yolov3 algorithm and its application in traffic flow detections |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-04-01 |
description |
In the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during traffic flows. Therefore, we propose a single-stage deep neural network YOLOv3-DL, which is based on the Tensorflow framework to improve this problem. The network structure is optimized by introducing the idea of spatial pyramid pooling, then the loss function is redefined, and a weight regularization method is introduced, for that, the real-time detections and statistics of traffic flows can be implemented effectively. The optimization algorithm we use is the DL-CAR data set for end-to-end network training and experiments with data sets under different scenarios and weathers. The analyses of experimental data show that the optimized algorithm can improve the vehicles’ detection accuracy on the test set by 3.86%. Experiments on test sets in different environments have improved the detection accuracy rate by 4.53%, indicating that the algorithm has high robustness. At the same time, the detection accuracy and speed of the investigated algorithm are higher than other algorithms, indicating that the algorithm has higher detection performance. |
topic |
intelligent transportation vehicle detection traffic flow loss function YOLOv3 mode |
url |
https://www.mdpi.com/2076-3417/10/9/3079 |
work_keys_str_mv |
AT yiqihuang optimizedyolov3algorithmanditsapplicationintrafficflowdetections AT jiachunzheng optimizedyolov3algorithmanditsapplicationintrafficflowdetections AT shidansun optimizedyolov3algorithmanditsapplicationintrafficflowdetections AT chengfuyang optimizedyolov3algorithmanditsapplicationintrafficflowdetections AT jingliu optimizedyolov3algorithmanditsapplicationintrafficflowdetections |
_version_ |
1724676598980935680 |