In this paper, an accurate long-distance position measurement system using laser range finders (LRFs) is proposed. The system uses cylindrical objects, and can be used for surveys in construction fields. Given data from the LRF are nothing more than the contours of the objects. Therefore, this research aims to estimate accurate center positions of the objects by applying the least square method or the maximum likelihood estimation to their contours based on the shape information of the objects. We adopted cylindrical shaped objects since a circle is invariant against rotation. If we know the radius of the cylindrical object in advance, the aforementioned two methods become non-linear problems. For this reason, we applied the Newton-Raphson method to solve these non-linear equations. Additionally, we implemented a reflected beam intensity filter to compensate for a collapse of the contour's shape and a multiple times scanning algorithm to increase the number of data points belonging to the contour.