Abstract—This paper investigates the impact of image enhance- ment techniques for road damage detection using the YOLOv8n object detection model. A sample of 2,000 images extracted from the RDD2022 dataset was used to evaluate CLAHE, Gaussian Blur, and Brightness Adjustment. The results showed that CLAHE achieved the best overall performance by improving Precision, F1-Score, mAP@50, and mAP@50-95 compared with the baseline model. Index Terms—Road damage detection, YOLOv8n, image en- hancement, CLAHE, Gaussian Blur, Brightness Adjustment.
Aldossary et al. (Tue,) studied this question.