The use of Light Detection And Ranging (LiDAR) for archaeological purposes is becoming more prevalent in order to detect and to document remains located in forested areas. One of the main interests of airborne laser scanning is to put the archaeological information in their context, and to allow a better understanding of the relation between each item and its environment. This concept of archaeological landscape generally results in a too large amount of data to permit a manual analysis. This paper describes an approach for the automatic detection of elementary archaeological grazing structures, found in high concentration in some places of Auvergne (France). These elementary structures are generally connected, creating complex archaeological grazing sets. The detection process is based on the design of a model of an elementary grazing structure. The automatic detection is then carried out, based on the evaluation of the matching degree of each element with the model and on their belonging to complex archaeological grazing structures. The efficiency of the method is tested, by comparison with the manual digitalisation of an expert, on a restricted zone, and the results show that the success rate of the automatic detection reaches higher values than classical template matching approaches. The additional criterion, based on the belonging of each elementary structure to a more complex one, improves the detection success: In a complementary way, this approach offers new opportunities: it is also possible to detect complex structures with a template matching approach, if they contain some simple forms, that can be modelled.