A Comparative Analysis Employing Adaptive Layers of RCNN Technique and Transfer Learning Pre-Trained Networks

The study aimed to classify two classes of vehicles, Tuktuk and Motorcycle, using a modified RCNN model. The MAjN_IRAQ Dataset, created from a camera system in Baghdad city, was used for training, detection, and classification of some vehicles to allow them to enter some crowded streets of Baghdad and to prevent others from entering the same streets. New layers were added and the number and size of filters were changed, which led to improve the process of training, detection and classification of vehicles with high accuracy, which leads to improving the proposed model’s performance. The results showed that the modified RCNN model performed better when trained for 80 epochs. It improved performance measures such as precision, recall, and F1 score measure. The model was compared to other transfer learning methods (Alex Net, VGG16, and VGG19) and showed superior results for the Tuktuk class. The training and testing time for the proposed RCNN-modified model was also lower compared to the other models. At 80 epochs, the precision for the Tuktuk class was approximately 0.94, while for the Motorcycle class, it was approximately 0.89. The TPR was higher for the Tuktuk class at approximately 0.93, while the lower value was approximately 0.84 for VGG16. When the VGG16 model was used, the F1 score was better in the Motorcycle category (about 0.95) but worse in the Tuktuk category (0.86%). Both the suggested RCNN-modified model and the Alex Net model worked well in a reasonable amount of time.