The transportation system has drawn attention due to the growing threats of cracks to the roads and bridges. To accurately detect cracks was made possible by the introduction of deep learning. In this paper, we propose the modified LeNet 5 model for detecting cracks in roads and bridges. We summarize our work in the following points: - 1. We worked on the three datasets, i.e., Automated Bridge Crack Detection Dataset, Concrete Crack Images for Classification Dataset, and Asphalt Crack Dataset. 2. We applied a modified version of LeNet-5 model on Automated Bridge Crack Detection Dataset, Concrete Crack Images for Classification Dataset, and Asphalt Crack Dataset. 3. Then, we analyzed our results and compared the same with Principal Component Analysis and without using Principal Component Analysis. The sliding window technique and trained CNN model were used for locating the crack and non-crack regions in input images. Our proposed model takes both the factors of time and accuracy into consideration while producing the output.
Dataset link :- https://data.mendeley.com/datasets/5y9wdsg2zt/2 IEEE Conference Paper Link:- https://ieeexplore.ieee.org/document/9315949