Indian intelligent transportation has immense assurance for traffic sign detection, which is a crucial aspect of environment-aware technology. The efficiency of traffic sign detection is crucial and heavily depends on various weather conditions and the challenge of detecting tiny traffic signs. In this paper, a multi-focal YOLOv8n attention model enhances the process of detection more effective in identifying the target traffic sign in various weather conditions, occlusion and far distance sign. In feature extraction stage modified attention model to enhance the spatial and semantic content. Then a probability model was introduced to estimate the partial occluded and tiny sign feature enhancement. Finally, Indian traffic sign in varied environmental conditions samples are trained with multi-focal YOLOv8n attention model. The experimentation result shows the accuracy of proposed model 94.2% precision 93.5%, recall 93.8% and mAP50 is 92.4% which improves the detection process more reliable and effective in Indian challenging scenarios.
Traffic Sign Detection System: Indian Challenging Scenario
2024-09-27
1303470 byte
Conference paper
Electronic Resource
English
Indian Traffic Sign Detection and Recognition
Springer Verlag | 2020
|Indian SUMO traffic scenario-based misbehaviour detection dataset for connected vehicles
DOAJ | 2025
|