Novel deep learning model for vehicle and pothole detection

The most important aspect of automatic driving and traffic surveillance is vehicle detection. In addition, poor road conditions caused by potholes are the cause accidents damage. proposed work uses deep learning models. method can detect vehicles using images. faster region-based convolutional neural network (CNN) inception V2 model used to implement model. compares performance, accuracy numbers, detection time, advantages disadvantages convolution (Faster R-CNN) with single shot detector (SSD) you only look once (YOLO) algorithms. shows good progress than existing methods such as SSD YOLO. measure performance evaluation Accuracy. an improvement 5% compared previous