Cargando…
An Improved YOLOv2 for Vehicle Detection
Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type re...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6308705/ https://www.ncbi.nlm.nih.gov/pubmed/30518140 http://dx.doi.org/10.3390/s18124272 |
_version_ | 1783383251725844480 |
---|---|
author | Sang, Jun Wu, Zhongyuan Guo, Pei Hu, Haibo Xiang, Hong Zhang, Qian Cai, Bin |
author_facet | Sang, Jun Wu, Zhongyuan Guo, Pei Hu, Haibo Xiang, Hong Zhang, Qian Cai, Bin |
author_sort | Sang, Jun |
collection | PubMed |
description | Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type recognition, low detection accuracy, and slow speed, a new vehicle detection model YOLOv2_Vehicle based on YOLOv2 is proposed in this paper. The k-means++ clustering algorithm was used to cluster the vehicle bounding boxes on the training dataset, and six anchor boxes with different sizes were selected. Considering that the different scales of the vehicles may influence the vehicle detection model, normalization was applied to improve the loss calculation method for length and width of bounding boxes. To improve the feature extraction ability of the network, the multi-layer feature fusion strategy was adopted, and the repeated convolution layers in high layers were removed. The experimental results on the Beijing Institute of Technology (BIT)-Vehicle validation dataset demonstrated that the mean Average Precision (mAP) could reach 94.78%. The proposed model also showed excellent generalization ability on the CompCars test dataset, where the “vehicle face” is quite different from the training dataset. With the comparison experiments, it was proven that the proposed method is effective for vehicle detection. In addition, with network visualization, the proposed model showed excellent feature extraction ability. |
format | Online Article Text |
id | pubmed-6308705 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-63087052019-01-04 An Improved YOLOv2 for Vehicle Detection Sang, Jun Wu, Zhongyuan Guo, Pei Hu, Haibo Xiang, Hong Zhang, Qian Cai, Bin Sensors (Basel) Article Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type recognition, low detection accuracy, and slow speed, a new vehicle detection model YOLOv2_Vehicle based on YOLOv2 is proposed in this paper. The k-means++ clustering algorithm was used to cluster the vehicle bounding boxes on the training dataset, and six anchor boxes with different sizes were selected. Considering that the different scales of the vehicles may influence the vehicle detection model, normalization was applied to improve the loss calculation method for length and width of bounding boxes. To improve the feature extraction ability of the network, the multi-layer feature fusion strategy was adopted, and the repeated convolution layers in high layers were removed. The experimental results on the Beijing Institute of Technology (BIT)-Vehicle validation dataset demonstrated that the mean Average Precision (mAP) could reach 94.78%. The proposed model also showed excellent generalization ability on the CompCars test dataset, where the “vehicle face” is quite different from the training dataset. With the comparison experiments, it was proven that the proposed method is effective for vehicle detection. In addition, with network visualization, the proposed model showed excellent feature extraction ability. MDPI 2018-12-04 /pmc/articles/PMC6308705/ /pubmed/30518140 http://dx.doi.org/10.3390/s18124272 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Sang, Jun Wu, Zhongyuan Guo, Pei Hu, Haibo Xiang, Hong Zhang, Qian Cai, Bin An Improved YOLOv2 for Vehicle Detection |
title | An Improved YOLOv2 for Vehicle Detection |
title_full | An Improved YOLOv2 for Vehicle Detection |
title_fullStr | An Improved YOLOv2 for Vehicle Detection |
title_full_unstemmed | An Improved YOLOv2 for Vehicle Detection |
title_short | An Improved YOLOv2 for Vehicle Detection |
title_sort | improved yolov2 for vehicle detection |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6308705/ https://www.ncbi.nlm.nih.gov/pubmed/30518140 http://dx.doi.org/10.3390/s18124272 |
work_keys_str_mv | AT sangjun animprovedyolov2forvehicledetection AT wuzhongyuan animprovedyolov2forvehicledetection AT guopei animprovedyolov2forvehicledetection AT huhaibo animprovedyolov2forvehicledetection AT xianghong animprovedyolov2forvehicledetection AT zhangqian animprovedyolov2forvehicledetection AT caibin animprovedyolov2forvehicledetection AT sangjun improvedyolov2forvehicledetection AT wuzhongyuan improvedyolov2forvehicledetection AT guopei improvedyolov2forvehicledetection AT huhaibo improvedyolov2forvehicledetection AT xianghong improvedyolov2forvehicledetection AT zhangqian improvedyolov2forvehicledetection AT caibin improvedyolov2forvehicledetection |