Light-weighted vehicle detection network based on improved YOLOv3-tiny
Vehicle detection is one of the most challenging research works on environment perception for intelligent vehicle. The commonly used object detection network is too large and can only be realized in real-time on a high-performance server. Based on YOLOv3-tiny, the feature extraction was realized usi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-03-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/15501329221080665 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547889020141568 |
|---|---|
| author | Pingshu Ge Lie Guo Danni He Liang Huang |
| author_facet | Pingshu Ge Lie Guo Danni He Liang Huang |
| author_sort | Pingshu Ge |
| collection | DOAJ |
| description | Vehicle detection is one of the most challenging research works on environment perception for intelligent vehicle. The commonly used object detection network is too large and can only be realized in real-time on a high-performance server. Based on YOLOv3-tiny, the feature extraction was realized using light-weighted networks such as DarkNet-19 and ResNet-18 to improve accuracy. The K -means algorithm was used to cluster nine anchor boxes to achieve multi-scale prediction, especially for small targets. For automotive applicable scenarios, the proposed vehicle detection network was executed in an embedded device. The KITTI data sets were trained and tested. Experimental results show that the average accuracy is improved by 14.09% compared with the traditional YOLOv3-tiny, reaching 93.66%, and can reach 13 fps on the embedded device. |
| format | Article |
| id | doaj-art-f9ec110b536848f9a04e8b2ba31de421 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2022-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-f9ec110b536848f9a04e8b2ba31de4212025-02-03T06:43:07ZengWileyInternational Journal of Distributed Sensor Networks1550-14772022-03-011810.1177/15501329221080665Light-weighted vehicle detection network based on improved YOLOv3-tinyPingshu Ge0Lie Guo1Danni He2Liang Huang3College of Mechanical & Electronic Engineering, Dalian Minzu University, Dalian, ChinaNingbo Institute of Dalian University of Technology, Ningbo, ChinaSchool of Automotive Engineering, Dalian University of Technology, Dalian, ChinaSchool of Automotive Engineering, Dalian University of Technology, Dalian, ChinaVehicle detection is one of the most challenging research works on environment perception for intelligent vehicle. The commonly used object detection network is too large and can only be realized in real-time on a high-performance server. Based on YOLOv3-tiny, the feature extraction was realized using light-weighted networks such as DarkNet-19 and ResNet-18 to improve accuracy. The K -means algorithm was used to cluster nine anchor boxes to achieve multi-scale prediction, especially for small targets. For automotive applicable scenarios, the proposed vehicle detection network was executed in an embedded device. The KITTI data sets were trained and tested. Experimental results show that the average accuracy is improved by 14.09% compared with the traditional YOLOv3-tiny, reaching 93.66%, and can reach 13 fps on the embedded device.https://doi.org/10.1177/15501329221080665 |
| spellingShingle | Pingshu Ge Lie Guo Danni He Liang Huang Light-weighted vehicle detection network based on improved YOLOv3-tiny International Journal of Distributed Sensor Networks |
| title | Light-weighted vehicle detection network based on improved YOLOv3-tiny |
| title_full | Light-weighted vehicle detection network based on improved YOLOv3-tiny |
| title_fullStr | Light-weighted vehicle detection network based on improved YOLOv3-tiny |
| title_full_unstemmed | Light-weighted vehicle detection network based on improved YOLOv3-tiny |
| title_short | Light-weighted vehicle detection network based on improved YOLOv3-tiny |
| title_sort | light weighted vehicle detection network based on improved yolov3 tiny |
| url | https://doi.org/10.1177/15501329221080665 |
| work_keys_str_mv | AT pingshuge lightweightedvehicledetectionnetworkbasedonimprovedyolov3tiny AT lieguo lightweightedvehicledetectionnetworkbasedonimprovedyolov3tiny AT dannihe lightweightedvehicledetectionnetworkbasedonimprovedyolov3tiny AT lianghuang lightweightedvehicledetectionnetworkbasedonimprovedyolov3tiny |