REVIEW PAPER ON AUTOMATIC IMAGE-BASED ROAD CRACK DETECTION METHODS

Abstract

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 the
evaluation of images of mobile cartographic systems. The obtained images remain an important source of the temporary
road condition. The automatization of crack detection is highly necessary because it could decrease workload, and
therefore, maintenance costs. Two methods for automatic crack detection from mobile mapping images were tested: step
by step pixel based image intensity analysis, and deep learning. The objective of this thesis is to develop and test the
workflow for the street view image crack detection and reduce image database by detecting no-crack surfaces. To
examine the performance of the methods, their classification precision was compared. The best-acquired precision with
the trained deep learning model was 98% that is 3% better than with the other method and it suggests that the deep
learning is the most appropriate for the application. Furthermore, there is a need for faster and more precise detection
methods, and deep learning holds promise for the further implementation. However, future studies are needed and they
should focus on full-scale image crack detection, disturbing object elimination and crack severity classification.