We present a new unsupervised technique to segment 3D Lidar points in outdoor environments. The main idea of this work is to identify artificial objects according to the existence of extruded shapes. Many artificial objects are composed of extruded shapes such as cylinders, planes, cubes, and lines. Therefore, we detect these arbitrarily extruded shapes on the basis of an indicator for repetitive crosssection shapes, and connect the components according to the strength between the overlapping areas in the extruded surfaces. Conventional segmentation methods that use local geometry information may sometimes produce erroneous results in scenes where there are many objects that are very near to and partially in contact with each other. In contrast, our method is more robust against these complex scenes using large scale surface overlapping strength. Experiments show it provides good results in urban environments and expressway scenes.