Evaluation of Removed Quantity for Wall Coating Removing Robot Using Image Processing

Abstract

The surfaces of buildings are covered with various wall coatings for beauty and protection. When a wall surface is to be repainted, its coating has to be removed completely. Almost every worker wants to avoid such work since it is very hard and dangerous. In order to solve this problem, we have developed a ""wall coating removing robot."" This robot has a sucking disk, a rotatable water jet nozzle for removing work, and four driving wheels. Coating-removed wall surfaces can be classified into three states: properly removed surface (P surface); over-removed surface (0 surface); and under-removed surface (U surface). The wall surfaces are classified by using data represented in HLS space. It seems that each surface has the following features: a P surface is a concrete surface which looks like a smooth surface; an 0 surface shows some aggregates in concrete, which presents the appearance of a coarse surface; and a U surface has non-removed coating areas. Images from a CCD camera fixed on the robot can be classified into three groups based on a newly developed method. This method uses the following values: (a) color differences between pixels in HLS space and (b) percentage of nonremoved areas in processed images.