RoadCrack Pro: Intelligent Road Damage Detection and Municipal Monitoring

The RoadCrack Pro system is a way to use Digital Image Processing to find damage on the road. It uses techniques like ROI masking and image filtering to find the damaged areas. The system can also find potholes. Combine all the damage it finds into one map. Then it tells us how bad the damage is and what we should do to fix it. We tested the system on roads that were damaged and roads that were not. On the damaged road the system found that 9.41 percent of the road was damaged. It was also very accurate with a Precision of 86.9 percent a Recall of 69.8 percent an F1-score of 77.4 percent and an IoU of 63.2 percent. On the road that was not damaged the system said the road was in condition, with no damage at all. The new system for watching over the city helps store and look at information from road checks. Gives a basis for making decisions about maintenance. RoadCrack Pro is a way to keep an eye on the condition of roads because it looks at damage to the pavement figures out how bad it is, suggests repairs and manages checks. This system is not perfect because it has problems with light the texture of the pavement and choosing the settings and it needs to be tested more.. It shows that using computers to look at pictures can work for checking the pavement. If we add information use special computer programs add GPS take pictures with phones and use the internet to watch over the roads we can make the system better make it work for more roads and make it easier to use. So RoadCrack Pro shows how we can use computer programs to watch over the pavement and make decisions, about repairs and it is easy to understand and does not need a lot of power.

[1] I. H. Abbas and M. Q. Ismael, “Automated pavement distress detection using image processing techniques,” Engineering, Technology & Applied Science Research, vol. 11, no. 5, pp. 7702–7708, 2021. [2] Y. Safyari, M. Mahdianpari, and H. Shiri, “A review of vision-based pothole detection methods using computer vision and machine learning,” Sensors, vol. 24, no. 17, Art. no. 5652, 2024, doi: 10.3390/s24175652. [3] H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Computer-Aided Civil and Infrastructure Engineering, vol. 33, pp. 1127–1141, 2018, doi: 10.1111/mice.12387. [4] Q. Zou, Z. Zhang, Q. Li, X. Qi, Q. Wang, and S. Wang, “DeepCrack: Learning hierarchical convolutional features for crack detection,” IEEE Transactions on Image Processing, vol. 28, no. 3, pp. 1498–1512, 2019, doi: 10.1109/TIP.2018.2878966. [5] Q. Zou, Y. Cao, Q. Li, Q. Mao, and S. Wang, “CrackTree: Automatic crack detection from pavement images,” Pattern Recognition Letters, vol. 33, no. 3, pp. 227–238, 2012, doi: 10.1016/j.patrec.2011.11.004. [6] H. Oliveira and P. L. Correia, “Automatic road crack detection and characterization,” IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 1, pp. 155–168, 2013, doi: 10.1109/TITS.2012.2208630. [7] H. Oliveira and P. L. Correia, “CrackIT—An image processing toolbox for crack detection and characterization,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2014, pp. 798–802. [8] M. Avila, S. Begot, F. Duculty, and T. S. Nguyen, “2D image based road pavement crack detection by calculating minimal paths and dynamic programming,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2014, pp. 783–787. [9] R. Amhaz, S. Chambon, J. Idier, and V. Baltazart, “A new minimal path selection algorithm for automatic crack detection on pavement images,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2014, pp. 788–792. [10] X. Wang and Z. Hu, “Grid-based pavement crack analysis using deep learning,” in Proc. 4th Int. Conf. Transportation Information and Safety (ICTIS), 2017, pp. 917–924, doi: 10.1109/ICTIS.2017.8047878.