In construction projects, inspection of structural components mostly relies on typical measurements (e.g. measuring tapes, levelling or total stations). Additionally, with those methods, only a few points on the structure can be measured, and resulted inspection may not fully reflect the actual, detailed condition. Laser scanning is emerging a remote sensing technology to capture the structures' surfaces in high details accurately and quickly. However, because of complex, massive data points acquired from the construction project, in practice, data processing is still manual work with support of computer aided program. To improve current workflows, this paper proposes a method automatically extracting structural components of the concrete building and subsequently inspects them in a term of deformation. The proposed method explores both spatial information of a point cloud and contextual knowledge of structures (e.g. orientation or shape). Additionally, based on the fundamental design of the structures, component's boundaries are automatically extracted to establish un-deformed surfaces of the components for deformation measurement.