Emergency vehicles classification for traffic signal system using optimized transfer DenseNet201 model

<p>As a result of the rapid growth of the world population, traffic signaling systems for monitoring and controlling the roads have  turned to be an important issue facing  humanity. To effectively overcome this problem, an accurate method for congestion reduction on the roads should be used which has a direct relation between the population and the cars’ usage. Various approaches derived from deep and transfer learning have been investigated in this context. This research implemented an optimized  transfer  learning approach for densely connected convolutional neural network (DenseNet201) models for multiple classifications (non-emergency cars, ambulance, police, and firefighter). Due to the non-availability of public datasets, a customizeddataset has been  created. This paper  aims  to  improve  the  performance accuracy of vehicle classification using certain preprocessing algorithms on the input images and testing various optimization methods. The performance accuracy of the proposed model is evaluated  using k-folds cross-validation 20:80 for the test and training, respectively. The metrics which are used for comparison with other deep learning techniques are based on exactness, recall, accuracy and F1-score. Test outcomes  specify  that  the  proposed  transfer model-basedoptimization outperforms  alternative deep learning  algorithms regarding vehicle accuracy in classifying and reaches 98.6%.</p&gt