Intelligent Transportation Systems: Real-Time Road Defect Identification with Shape-Based Adaptation

Damaged road surfaces have a significant effect on infrastructure costs, vehicle performance, and public transportation safety. For extensive road monitoring, nations like Bangladesh rely entirely on manual inspection, which is much more time-consuming and unreliable. Every year, a large number of people in Bangladesh lose their lives in traffic accidents. Road degradation is one of the primary causes of these accidents. Roads in Bangladesh suffer significant damage during the rainy season, with deep potholes appearing everywhere and flaws that are difficult for models to see. In this study, an automated method for identifying and categorizing road damage is presented. Road damage comes in numerous forms, including cracks, potholes, surface wear, rutting, and repair. Given how badly damaged Bangladeshi roads are, we divide the damage into two categories: potholes are given special consideration, while cracks are simply called cracks. Due to road quality, we did not use public datasets from other countries in contrast to previous research. Since potholes are the primary issue on Bangladeshi roads, this study contributes a custom data set of 12,650 images that are divided into two classes: pothole and crack. In addition, there are 13,051 images that focus solely on potholes, which are gathered under a variety of lighting conditions, camera angles, and environmental factors. Damages are plainly annotated because each image is manually labeled. In the pothole-only dataset, the model’s mAP@50 was 83.4%, its precision was 85.12%, and its recall was 74.22%. In the two-class data set, it was 50.9%, its precision was 57.6% and its recall was 49.2%.