The quality and reliability of road infrastructure and its equipment play a major role in road safety. This is especially true if we are interested by autonomous cars traffic able to read road marking. This kind of vehicles needs an accurate maintenance strategy to guarantee a road with marking perceptible for a human eye or an autonomous car. To simplify the study of a road and because a maintenance campaign is generally applied for a part of the road, a solution based on an Agglomerative Hierarchical Clustering to cluster all markings is chosen. In the case of no follow-up of the maintenance for markings, a maintenance detector will be introduced and described. Finally, with this classification, it is possible to extract all maintenance cycles and identify the different maintenance actions. This approach is a first step to analyze the useful life of marking with a Weibull analysis. Skip center line of the French National Road 4 is considered to illustrate the proposed approach.