Smartphone Image-Based Road Damage Detection in Low-Light Conditions

Road damage occurs due to various factors and can cause negative impacts such as increased accidents, vehicle operating costs, decreased transportation efficiency, and reduced access to critical services. In this work, a novel dataset with a total of one thousand one hundred seventy samples was developed using a smartphone camera in order to create an object detection model for detecting road damage such as potholes, unpaved and normal in low light conditions. Image preprocessing techniques were used to enhance the low-light images. The dataset has been categorized into before and after enhancement for comparison with results obtained from both methods. YOLOv7 object detection model is more capable of handling the challenges present in on-site images of road damage at low light conditions. The proposed method has demonstrated high performance in detecting multiple damages on roads. The results indicated a mean average precision (mAP) of 0.672 before enhancement and results with mAP of 0.764, with an IoU threshold of 50% after enhancement.