Detection of Real Time Pothole System using Edge Detection

The purpose of streets is to facilitate safe vehicle movement at designated speeds. Surveillance is particularly crucial at intersections, sharp curves, congested areas, accident-prone zones, and other critical points on the road. Various measures are implemented to enhance safety, including mandatory speed limit signs, flashing signals for alerts, and road markings. While speed bumps may be necessary in certain situations, their widespread use is not considered ideal due to potential vehicle damage and risk of injury. Additionally, traffic signs can sometimes distract drivers, especially in low-light conditions, making it challenging to anticipate speed bumps. This research study intends to address these concerns by employing Machine Learning (ML) techniques, specifically edge detection, to identify potholes and bumps on roads. The proposed model achieves an accuracy of 98% in detecting the road hazards. An image-processing system is utilized for pothole detection, while ultrasonic sensors are employed to measure the depth of potholes, providing drivers with crucial information to avoid accidents or vehicle damage.