ASPHALT ROAD DAMAGE DETECTION SYSTEM USING CANNY EDGE DETECTION

Abstract

Road is a means of access for humans to move from one place to another, connecting one place to another, and serving as transportation infrastructure. At all times, asphalt roads are passed by road users, including small, medium, and large vehicles. However, road conditions are not always smooth and often there are damages in certain parts of the road. Factors such as water, weather, temperature changes, unstable soil conditions, air temperature, poor compaction process on the base layer, and the weight or overload of heavy vehicles that exceed capacity, as well as the increasing volume of vehicles, can cause road damage. Road damage can reduce economic revenue and increase accident rates. Some types of asphalt road damage include undulating, potholes, cracking, and asphalt puddles on the road surface. Potholes are the most common type of damage that cause accidents for road users. This study uses the Canny edge detection method to detect asphalt road damage. The minimum object size that can be detected as road damage is 15x15 pixels and the maximum is 290x540 pixels. Testing was conducted on 65 primary data and 35 secondary data, and the average accuracy obtained were 90.5% and 88%, respectively.