Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment
Mixed traffic is a common phenomenon in urban environment. For the mixed traffic situation, the detection of traffic obstacles, including motor vehicle, non-motor vehicle, and pedestrian, is an essential task for intelligent and connected vehicles (ICVs). In this paper, an improved YOLO model is pro...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2022/2259113 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545937268932608 |
|---|---|
| author | Luyao Du Xiongjie Chen Zhonghui Pei Donghua Zhang Bo Liu Wei Chen |
| author_facet | Luyao Du Xiongjie Chen Zhonghui Pei Donghua Zhang Bo Liu Wei Chen |
| author_sort | Luyao Du |
| collection | DOAJ |
| description | Mixed traffic is a common phenomenon in urban environment. For the mixed traffic situation, the detection of traffic obstacles, including motor vehicle, non-motor vehicle, and pedestrian, is an essential task for intelligent and connected vehicles (ICVs). In this paper, an improved YOLO model is proposed for traffic obstacle detection and classification. The YOLO network is used to accurately detect the traffic obstacles, while the Wasserstein distance-based loss is used to improve the misclassification in the detection that may cause serious consequences. A new established dataset containing four types of traffic obstacles including vehicles, bikes, riders, and pedestrians is collected under different time periods and different weather conditions in urban environment in Wuhan, China. Experiments are performed on the established dataset on Windows PC and NVIDIA TX2, respectively. From the experimental results, the improved YOLO model has higher mean average precision than the original YOLO model and can effectively reduce intolerable misclassifications. In addition, the improved YOLOv4-tiny model has a detection speed of 22.5928 fps on NVIDIA TX2, which can basically realize the real-time detection of traffic obstacles. |
| format | Article |
| id | doaj-art-9af9c9df708c4406a3338d9bba0c9613 |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-9af9c9df708c4406a3338d9bba0c96132025-02-03T07:24:17ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/2259113Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic EnvironmentLuyao Du0Xiongjie Chen1Zhonghui Pei2Donghua Zhang3Bo Liu4Wei Chen5School of AutomationDepartment of Computer ScienceSchool of Information EngineeringWuhan Zhongyuan Electronics Group Co., Ltd.Wuhan Zhongyuan Electronics Group Co., Ltd.School of AutomationMixed traffic is a common phenomenon in urban environment. For the mixed traffic situation, the detection of traffic obstacles, including motor vehicle, non-motor vehicle, and pedestrian, is an essential task for intelligent and connected vehicles (ICVs). In this paper, an improved YOLO model is proposed for traffic obstacle detection and classification. The YOLO network is used to accurately detect the traffic obstacles, while the Wasserstein distance-based loss is used to improve the misclassification in the detection that may cause serious consequences. A new established dataset containing four types of traffic obstacles including vehicles, bikes, riders, and pedestrians is collected under different time periods and different weather conditions in urban environment in Wuhan, China. Experiments are performed on the established dataset on Windows PC and NVIDIA TX2, respectively. From the experimental results, the improved YOLO model has higher mean average precision than the original YOLO model and can effectively reduce intolerable misclassifications. In addition, the improved YOLOv4-tiny model has a detection speed of 22.5928 fps on NVIDIA TX2, which can basically realize the real-time detection of traffic obstacles.http://dx.doi.org/10.1155/2022/2259113 |
| spellingShingle | Luyao Du Xiongjie Chen Zhonghui Pei Donghua Zhang Bo Liu Wei Chen Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment Journal of Advanced Transportation |
| title | Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment |
| title_full | Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment |
| title_fullStr | Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment |
| title_full_unstemmed | Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment |
| title_short | Improved Real-Time Traffic Obstacle Detection and Classification Method Applied in Intelligent and Connected Vehicles in Mixed Traffic Environment |
| title_sort | improved real time traffic obstacle detection and classification method applied in intelligent and connected vehicles in mixed traffic environment |
| url | http://dx.doi.org/10.1155/2022/2259113 |
| work_keys_str_mv | AT luyaodu improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment AT xiongjiechen improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment AT zhonghuipei improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment AT donghuazhang improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment AT boliu improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment AT weichen improvedrealtimetrafficobstacledetectionandclassificationmethodappliedinintelligentandconnectedvehiclesinmixedtrafficenvironment |