Efficient Pavement Crack Detection and Classification Using Custom YOLOv7 Model

Abstract

It is crucial to detect and classify pavement cracks as part of maintaining road safety. The inspection process for identifying and classifying cracks manually is tedious, time-consuming, and potentially dangerous for inspectors. As a result, an efficient automated approach for detecting road cracks is essential for this development. Numerous issues, such as variations in intensity, uneven data availability, the inefficacy of traditional approaches, and others, make it challenging to accomplish. This research has been carried out to contribute towards developing an efficient pavement crack detection and classification system. This study uses state of the art deep learning algorithm, customized YOLOv7 model. Data from two sources, RDD2022, a publicly available online dataset, and the second set of data gathered from the roads of Malaysia have been used in this investigation. In order to have balanced data for training, many image preprocessing techniques have been applied to the data, such as augmentations, scaling, blurring, etc. Experimental results demonstrate that the detection accuracy of the YOLOv7 model is significant, 92% on the RDD2022 dataset and 88% on our custom dataset. This study reports the outcomes of experiments conducted on both datasets. RDD2022 achieved a precision of 0.9523 and a recall of 0.9545. On the custom dataset, the resulting values for precision and recall were 0.93 and 0.9158, respectively. The results of this study were compared to those of other recent studies in the same field in order to establish a benchmark. Results from the proposed system were more encouraging and surpassed the benchmarking ones.