Irak'ta ML kullanılarak yol hasarlarının (çatlakların) tespiti

That research aims to develop road maintenance operations that include the road survey process to determine types of defects, knowing the type of proposed maintenance, solving the problem of reporting road problems, and also seeks to facilitate the process of road maintenance at the lowest possible costs To achieve these goals, a project is being designed that automates road maintenance and uses artificial intelligence to determine kind of defect in the way by using the libraries (tensorflow with Detection Object), (sklearn is considered one of the most famous libraries for the Python programming language, which specializes in The related fields of data science and machine learning. This library includes a set of algorithms, methods and techniques that are used in the machine learning field, and among these Methods are the concept of classification, and this library was built based on various Python libraries such as: Scipy, Numpy, Matplotlib, and many other libraries.). The proposed study will reach a number of results, which are identifying the defect, knowing its type, measuring the area of the defect, and conducting some engineering operations and calculations to determine the state of the roadway, and the type of maintenance proposed as a final output. This study will use a deep learning-based object detection method to identify road cracks under different shooting, weather, and illumination scenarios. This makes it possible to identify any cracks in a very short amount of time and at a low cost. Images will take in different weather conditions, such as the intensity of brightness being high, medium or very low. They will also be taken in foggy, rainy and dark conditions. Pictures are also taken at different distances (such as one meter, half a meter, one and a half meters) to study the behavior of the pictures and the possibility of extracting defects from them in different circumstances.