국내 도심에서 자율주행을 위한 신호등 인식 모듈 및 데이터 셋 구축 프로세스 설계
Design of Building Dataset and Traffic Light Recognition Module for Domestic Urban Autonomous Driving
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In the context of urban autonomous driving, where various types of traffic lights are encountered, traffic light recognition technology is of paramount importance. We have designed a high-performance traffic light recognition module tailored to scenarios encountered in domestic urban driving and devised a dataset construction process. In this paper, we focus on minimizing the camera's dependency to enhance traffic light recognition performance. The camera is used solely to distinguish the color information of traffic lights, while accurate location information of the traffic lights is obtained through localization and a map. Based on the information from these components, camera RoIs (Region of Interest) are extracted and transmitted to the embedded board. The transmitted images are then sent back to the main system for autonomous driving control. The processing time for one traffic light RoI averages 43.2 ms. We achieve processing times of average 93.4 ms through batch inference to meet real-time requirements. Additionally, we design a data construction process for collecting, refining, and storing traffic light datasets, including semi-annotation-based corrections.
Abstract
In the context of urban autonomous driving, where various types of traffic lights are encountered, traffic light recognition technology is of paramount importance. We have designed a high-performance traffic light recognition module tailored to scenarios encountered in domestic urban driving and devised a dataset construction process. In this paper, we focus on minimizing the camera's dependency to enhance traffic light recognition performance. The camera is used solely to distinguish the color information of traffic lights, while accurate location information of the traffic lights is obtained through localization and a map. Based on the information from these components, camera RoIs (Region of Interest) are extracted and transmitted to the embedded board. The transmitted images are then sent back to the main system for autonomous driving control. The processing time for one traffic light RoI averages 43.2 ms. We achieve processing times of average 93.4 ms through batch inference to meet real-time requirements. Additionally, we design a data construction process for collecting, refining, and storing traffic light datasets, including semi-annotation-based corrections.
참고문헌 (15)
- C. Jung, "V2X-communication-aided Autonomous Driving : System Design and Experimental Validation", Sensors, 20(10), pp.2903~ (2020)
- M. Weber, "DeepTLR: A Single Deep Convolutional Network for Detection and Classification of Traffic Lights", 2016 IEEE Intelligent Vehicles Symposium (IV), pp.342~348 (2016), IEEE
- J. Redmon, "You Only Look Once:Unified, Real-time Object Detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- Q. Wang, "Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm", Sensors, 22(1), pp.200~ (2021)
- M. Mostafa, "A Yolo Based Approach for Traffic Light Recognition for Adas Systems", 2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), pp.225~229 (2022), IEEE
- M. Hirabayashi, "Traffic Light Recognition Using High-definition Map Features", Robotics and Autonomous Systems, 111, pp.62~72 (2019)
- S. Kato, "An Open Approach to Autonomous Vehicles", IEEE Micro, 35(6), pp.60~68 (2015)
- W. Liu, "Ssd: Single Shot Multibox Detector", Computer Vision–ECCV 2016: 14th European Conference, pp.21~37 (2016), Springer International Publishing
- Z. Li, "An Improved Traffic Lights Recognition Algorithm for Autonomous Driving in Complex Scenarios", International Journal of Distributed Sensor Networks, 17(5) (2021)
- K. He, "Deep Residual Learning for ImageRrecognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 34, pp.770~778 (2016)
- S. Liu, "Path Aggregation Network for Instance Segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.8759~8768 (2018)
- M. B. Jensen, "Vision for Looking at Traffic Lights : Issues, Survey, and Perspectives", IEEE Transactions on Intelligent Transportation Systems, 17(7), pp.1800~1815 (2016)
- Korean National Police Agency, "Traffic Signal Installation and Operation Manual", ~ (2022)
- T. Y. Lin, "Focal Loss for Dense Object Detection", Proceedings of the IEEE International Conference on Computer Vision, pp.2980~2988 (2017)
- J. H. Lee, "Construction and Effectiveness Evaluation of Multi Camera Dataset Specialized for Autonomous Driving in Domestic Road Environment", IEMEK J. Embed. Sys. Appl, 17(5), pp.273~280 (2022)