RoadDamageDetection-DeepLearning
It is intended to detect damage to road images taken by a camera. For this, deep learning technology, a subspace of machine learning, and Convolutional Neural Networks (CNN), one of the most popular types of deep neural networks, are used. The TensorFlow library is trained through the Ssd Inception V2 Coco pre-trained model to detect damage to images. As a result of the tests and trainings, the closest determinations are 86%. In order to increase the accuracy of the training, the use of GPU, the magnification of the data set and the number of iterations were considered.
