Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm
For facing of the problems caused by the YOLOv4 algorithm’s insensitivity to small objects and low detection precision in traffic light detection and recognition, the Improved YOLOv4 algorithm is investigated in the paper using the shallow feature enhancement mechanism and the bounding box uncertain...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/200 |
| _version_ | 1827667633249452032 |
|---|---|
| author | Qingyan Wang Qi Zhang Xintao Liang Yujing Wang Changyue Zhou Vladimir Ivanovich Mikulovich |
| author_facet | Qingyan Wang Qi Zhang Xintao Liang Yujing Wang Changyue Zhou Vladimir Ivanovich Mikulovich |
| author_sort | Qingyan Wang |
| collection | DOAJ |
| description | For facing of the problems caused by the YOLOv4 algorithm’s insensitivity to small objects and low detection precision in traffic light detection and recognition, the Improved YOLOv4 algorithm is investigated in the paper using the shallow feature enhancement mechanism and the bounding box uncertainty prediction mechanism. The shallow feature enhancement mechanism is used to extract features from the network and improve the network’s ability to locate small objects and color resolution by merging two shallow features at different stages with the high-level semantic features obtained after two rounds of upsampling. Uncertainty is introduced in the bounding box prediction mechanism to improve the reliability of the prediction of the bounding box by modeling the output coordinates of the prediction bounding box and adding the Gaussian model to calculate the uncertainty of the coordinate information. The LISA traffic light data set is used to perform detection and recognition experiments separately. The Improved YOLOv4 algorithm is shown to have a high effectiveness in enhancing the detection and recognition precision of traffic lights. In the detection experiment, the area under the PR curve value of the Improved YOLOv4 algorithm is found to be 97.58%, which represents an increase of 7.09% in comparison to the 90.49% score gained in the Vision for Intelligent Vehicles and Applications Challenge Competition. In the recognition experiment, the mean average precision of the Improved YOLOv4 algorithm is 82.15%, which is 2.86% higher than that of the original YOLOv4 algorithm. The Improved YOLOv4 algorithm shows remarkable advantages as a robust and practical method for use in the real-time detection and recognition of traffic signal lights. |
| first_indexed | 2024-03-10T03:21:03Z |
| format | Article |
| id | doaj.art-5d407e66ec554c81b1ce0a23c9438dec |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:21:03Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5d407e66ec554c81b1ce0a23c9438dec2023-11-23T12:18:31ZengMDPI AGSensors1424-82202021-12-0122120010.3390/s22010200Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 AlgorithmQingyan Wang0Qi Zhang1Xintao Liang2Yujing Wang3Changyue Zhou4Vladimir Ivanovich Mikulovich5School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Radio Physics and Electronics, Belarusian State University, 220030 Minsk, BelarusFor facing of the problems caused by the YOLOv4 algorithm’s insensitivity to small objects and low detection precision in traffic light detection and recognition, the Improved YOLOv4 algorithm is investigated in the paper using the shallow feature enhancement mechanism and the bounding box uncertainty prediction mechanism. The shallow feature enhancement mechanism is used to extract features from the network and improve the network’s ability to locate small objects and color resolution by merging two shallow features at different stages with the high-level semantic features obtained after two rounds of upsampling. Uncertainty is introduced in the bounding box prediction mechanism to improve the reliability of the prediction of the bounding box by modeling the output coordinates of the prediction bounding box and adding the Gaussian model to calculate the uncertainty of the coordinate information. The LISA traffic light data set is used to perform detection and recognition experiments separately. The Improved YOLOv4 algorithm is shown to have a high effectiveness in enhancing the detection and recognition precision of traffic lights. In the detection experiment, the area under the PR curve value of the Improved YOLOv4 algorithm is found to be 97.58%, which represents an increase of 7.09% in comparison to the 90.49% score gained in the Vision for Intelligent Vehicles and Applications Challenge Competition. In the recognition experiment, the mean average precision of the Improved YOLOv4 algorithm is 82.15%, which is 2.86% higher than that of the original YOLOv4 algorithm. The Improved YOLOv4 algorithm shows remarkable advantages as a robust and practical method for use in the real-time detection and recognition of traffic signal lights.https://www.mdpi.com/1424-8220/22/1/200traffic lightobject detectionYOLOv4deep learningcomputer vision |
| spellingShingle | Qingyan Wang Qi Zhang Xintao Liang Yujing Wang Changyue Zhou Vladimir Ivanovich Mikulovich Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm Sensors traffic light object detection YOLOv4 deep learning computer vision |
| title | Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm |
| title_full | Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm |
| title_fullStr | Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm |
| title_full_unstemmed | Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm |
| title_short | Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm |
| title_sort | traffic lights detection and recognition method based on the improved yolov4 algorithm |
| topic | traffic light object detection YOLOv4 deep learning computer vision |
| url | https://www.mdpi.com/1424-8220/22/1/200 |
| work_keys_str_mv | AT qingyanwang trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm AT qizhang trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm AT xintaoliang trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm AT yujingwang trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm AT changyuezhou trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm AT vladimirivanovichmikulovich trafficlightsdetectionandrecognitionmethodbasedontheimprovedyolov4algorithm |