| Abstrakt: |
Unmanned Aerial Vehicles (UAVs) have been found to have many uses in the maintenance and oversight of civil infrastructure assets. They contribute to scheduled bridge checkups, crisis control, electricity transmission cable oversight and traffic analysis. With more and more uses of UAVs being introduced, a greater focus on individuality and freedom regarding governance of these devices is required to ensure security, competency, and precision. The subject of this study outlines the method and policies to be followed for teaching the principals of the (efficient Neural Network) ENet architecture, machine learning, and using OpenCV to implement semantic segmentation on a collection of images obtained through aerial photography for identification of objects. Possible utilizations of UAVs in the area of transportation are mentioned as well along with the precision and efficiency of training for the application of the ENet architecture, machine learning, and OpenCV to implement semantic segmentation, the optimization selection of operational parameters, and the machine learning and ENet architecture teaching methods and policies drafting process. Through analysis of the object identification results, it was proven that by adhering to a specific set of parameters, the ENet architecture and machine learning procedures can successfully identify objects with an accuracy of 99% when there is no distortion. In addition, using a combination of all three technologies mentioned, it is possible to not only classify objects, but the device is also capable of automated tracking and detection of the objects by real-time processing of streamed videos by the UAVs. The novelty, that the ENET was applied for large class members difference distance among the same objects family. [ABSTRACT FROM AUTHOR] |
