Modern intelligent transportation systems and autonomous driving technologies are quite helpful in light of the population's increasing growth, and they work particularly well when used in conjunction with traffic sign monitoring. By giving drivers accurate and exact traffic signals, such as speed limits, warnings, and directional assistance, this makes transportation much safer. Autonomous vehicles must correctly understand these indicators in order to make wise driving judgments. Accurately identifying and classifying a wide variety of traffic signs in a range of environmental circumstances is a difficulty. A cutting-edge deep learning model created specifically for object recognition tasks is called YOLOv9 (You Only Look Once version 9). In addition to offering respectable speed and accuracy, YOLOv9 expands on the advantages of its predecessors by implementing cutting-edge strategies such as PGI and GELAN. Because of these improvements, YOLOv9 is especially ideal for real-time applications like recognition of traffic signs, where more accuracy and quick and accurate object identification are essential. With an increased accuracy the results demonstrate the model's stability and dependability and show that it is appropriate for real-world uses in autonomous driving and traffic control. Subsequent investigations will concentrate on improving resilience in various situations, utilizing semi-supervised learning, creating more resource-efficient models, broadening the range of datasets, and combining traffic sign recognition with additional autonomous driving tasks. The development of dependable and effective traffic sign detection systems is furthered by this work.
Improving Traffic Sign Recognition with the YOLOv9 Algorithm
06.02.2025
660070 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
YOLOv9 – BASED TRAFFIC SIGN DETECTION UNDER VARYING LIGHTING CONDITIONS
BASE | 2025
|