Paper Details

Detection of road-level cracks is an important procedure for road maintenance and traffic safety.Traditionally, inventory of roads has been conducted through field surveys, and now it is being replaced by theevaluation of images of mobile cartographic systems. The obtained images remain an important source of the temporaryroad condition. The automatization of crack detection is highly necessary because it could decrease workload, andtherefore, maintenance costs. Two methods for automatic crack detection from mobile mapping images were tested: stepby step pixel based image intensity analysis, and deep learning. The objective of this thesis is to develop and test theworkflow for the street view image crack detection and reduce image database by detecting no-crack surfaces. Toexamine the performance of the methods, their classification precision was compared. The best-acquired precision withthe trained deep learning model was 98% that is 3% better than with the other method and it suggests that the deeplearning is the most appropriate for the application. Furthermore, there is a need for faster and more precise detectionmethods, and deep learning holds promise for the further implementation. However, future studies are needed and theyshould focus on full-scale image crack detection, disturbing object elimination and crack severity classification.

Aman Ullah, Muhammad Majid Naeem, Fazle Subhan, “REVIEW PAPER ON AUTOMATIC IMAGE-BASED ROAD CRACK DETECTION METHODS”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 7, Issue 2, pp. 54-59, February 2020.