An optimized intelligent traffic sign forecasting framework for smart cities

Traffic signs are the globally essential map features for the era of autonomous driving and smart cities. Traffic sign recognition is a difficult task due to their multiple shapes, sizes, color, occlusions and complicated driving scenes. For automatic traffic signs and classification, a robust and efficient system is needed with a highly accurate prediction rate. Therefore, a novel goat-based convolutional neural–Kalman framework (GbCN-KF) is proposed to detect the traffic signs for smart cities. Primarily, the input traffic sign images are noise-filtered by the Kalman function and the relative features for the recognition process were extracted. Further, traffic signs are recognized by matching the features with the trained set and classified using the goat fitness function. The system is tested with the BTSC and GTSRB database. The performance score was evaluated for the datasets and compared with the prevailing recognition models. The model recorded a high accuracy percentage of 99.89% and 99.94% for the tested BTSC and GTSRB datasets.