نوع مقاله : مقاله پژوهشی
نویسندگان
1 استاد- دانشکده مهندسی عمران-دانشگاه علم و صنعت ایران
2 گروه حمل و نقل، دانشکده مهندسی عمران، دانشگاه علم و صنعت ایران، تهران، ایران
3 دانشکده مهندسی عمران، دانشگاه علم و صنعت ایران
4 دانشکده عمران-دانشگاه علم و صنعت ایران
چکیده
کلیدواژه‌ها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
The main goal of this research is to implement an artificial intelligence system based on deep learning to detect and determine the distance between traffic lights and the self-driving car and the proper performance of the car in yellow light conditions. To implement the model, the data set specific to the lights of Tehran city was used, and the model works in the framework of the Tensorflow library. To evaluate the performance of the model in different conditions, including the width of the intersection and the speed of the vehicle, the images of the training section were used, which enables the car to decide to cross the intersection or stop at the intersection using the four scenarios presented in this research. The analysis of the model results by checking the output of the model such as correctness, accuracy, recall, F1 score and speed of the models were evaluated with the results of past studies and showed that the results are correct and have higher accuracy than the existing models. Also, the best model presented in this research has an accuracy of 96% and an accuracy of 98%. Based on the traffic light data of Tehran city, this system is able to calculate the distance of the car to the traffic light with an error of less than one percent (0.8 percent), which shows the high accuracy of the model that can provide a proper performance in yellow light conditions.
کلیدواژه‌ها [English]
)