Search for: All records

Natural disasters such as wildfires, landslides, and earthquakes result in obstructions on roads due to fallen trees, landslides, and rocks. Such obstructions can cause significant mobility problems for both evacuees and first responders, especially in the immediate aftermath of disasters. Unmanned Aerial Vehicles (UAVs) provide an opportunity to perform rapid and remote reconnaissance of planned routes and thus provide decision-makers with information relating to a route’s feasibility. However, detecting obstacles on roads manually is a laborious and error-prone task, especially when attention is diverted to needs that are more urgent during disaster scenarios. This paper thus proposes a computer vision and machine-learning framework to detect obstacles on a road automatically to ensure its possibility in the aftermath of disasters. The framework implements the YOLO algorithm to detect and segment roads on images from UAVs and reference images from publicly available datasets. The images retrieved from UAVs and reference images are segmented and counted pixels of the roadway for comparison of the difference in pixels to identify the obstruction on the road. In addition, the method is proposed to automatically detect obstructions found in the region of interest (ROI) only on a roadway with images and videos from UAVs. Preliminary results from test runs are presented along with the future steps for implementing a real-time UAV-based road obstruction system.