An improved traffic lights recognition algorithm for autonomous driving in complex scenarios
Image recognition is susceptible to interference from the external environment. It is challenging to accurately and reliably recognize traffic lights in all-time and all-weather conditions. This article proposed an improved vision-based traffic lights recognition algorithm for autonomous driving, in...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/15501477211018374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849695695807709184 |
|---|---|
| author | Ziyue Li Qinghua Zeng Yuchao Liu Jianye Liu Lin Li |
| author_facet | Ziyue Li Qinghua Zeng Yuchao Liu Jianye Liu Lin Li |
| author_sort | Ziyue Li |
| collection | DOAJ |
| description | Image recognition is susceptible to interference from the external environment. It is challenging to accurately and reliably recognize traffic lights in all-time and all-weather conditions. This article proposed an improved vision-based traffic lights recognition algorithm for autonomous driving, integrating deep learning and multi-sensor data fusion assist (MSDA). We introduce a method to obtain the best size of the region of interest (ROI) dynamically, including four aspects. First, based on multi-sensor data (RTK BDS/GPS, IMU, camera, and LiDAR) acquired in a normal environment, we generated a prior map that contained sufficient traffic lights information. And then, by analyzing the relationship between the error of the sensors and the optimal size of ROI, the adaptively dynamic adjustment (ADA) model was built. Furthermore, according to the multi-sensor data fusion positioning and ADA model, the optimal ROI can be obtained to predict the location of traffic lights. Finally, YOLOv4 is employed to extract and identify the image features. We evaluated our algorithm using a public data set and actual city road test at night. The experimental results demonstrate that the proposed algorithm has a relatively high accuracy rate in complex scenarios and can promote the engineering application of autonomous driving technology. |
| format | Article |
| id | doaj-art-91087c7f2d904085b8c5be2776d5fb7a |
| institution | DOAJ |
| issn | 1550-1477 |
| language | English |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-91087c7f2d904085b8c5be2776d5fb7a2025-08-20T03:19:42ZengWileyInternational Journal of Distributed Sensor Networks1550-14772021-05-011710.1177/15501477211018374An improved traffic lights recognition algorithm for autonomous driving in complex scenariosZiyue Li0Qinghua Zeng1Yuchao Liu2Jianye Liu3Lin Li4National Engineering Laboratory for Integrated Command and Dispatch Technology, Beijing, ChinaNavigation Research Center, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaNational Engineering Laboratory for Integrated Command and Dispatch Technology, Beijing, ChinaNavigation Research Center, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaChina Astronaut Research and Training Center, Beijing, ChinaImage recognition is susceptible to interference from the external environment. It is challenging to accurately and reliably recognize traffic lights in all-time and all-weather conditions. This article proposed an improved vision-based traffic lights recognition algorithm for autonomous driving, integrating deep learning and multi-sensor data fusion assist (MSDA). We introduce a method to obtain the best size of the region of interest (ROI) dynamically, including four aspects. First, based on multi-sensor data (RTK BDS/GPS, IMU, camera, and LiDAR) acquired in a normal environment, we generated a prior map that contained sufficient traffic lights information. And then, by analyzing the relationship between the error of the sensors and the optimal size of ROI, the adaptively dynamic adjustment (ADA) model was built. Furthermore, according to the multi-sensor data fusion positioning and ADA model, the optimal ROI can be obtained to predict the location of traffic lights. Finally, YOLOv4 is employed to extract and identify the image features. We evaluated our algorithm using a public data set and actual city road test at night. The experimental results demonstrate that the proposed algorithm has a relatively high accuracy rate in complex scenarios and can promote the engineering application of autonomous driving technology.https://doi.org/10.1177/15501477211018374 |
| spellingShingle | Ziyue Li Qinghua Zeng Yuchao Liu Jianye Liu Lin Li An improved traffic lights recognition algorithm for autonomous driving in complex scenarios International Journal of Distributed Sensor Networks |
| title | An improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| title_full | An improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| title_fullStr | An improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| title_full_unstemmed | An improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| title_short | An improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| title_sort | improved traffic lights recognition algorithm for autonomous driving in complex scenarios |
| url | https://doi.org/10.1177/15501477211018374 |
| work_keys_str_mv | AT ziyueli animprovedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT qinghuazeng animprovedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT yuchaoliu animprovedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT jianyeliu animprovedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT linli animprovedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT ziyueli improvedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT qinghuazeng improvedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT yuchaoliu improvedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT jianyeliu improvedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios AT linli improvedtrafficlightsrecognitionalgorithmforautonomousdrivingincomplexscenarios |