Crack detection of external wall insulation materials based on infrared polarization imaging and Otsu threshold segmentation

Due to the multi-texture and multi-objective characteristics of the surface of external wall insulation materials, the existing crack detection methods can not meet the detection needs in real time. Therefore, this paper proposes a crack detection method for external wall insulation materials based on infrared polarization imaging and Otsu threshold segmentation. Under infrared polarization imaging and Otsu threshold segmentation, the characteristics of cracks in external wall insulation materials are extracted, and the cracks are classified according to the extraction results, which are divided into connection cracks between concrete structural columns, connection cracks between insulation boards and boards, vertical cracks in the middle of the whole wall, 45 inclined cracks, cracks on the wall surface, temperature cracks and shortening cracks. Obtain the number of pixels in the crack area, calculate the distribution density of the crack image of the external wall insulation material, set the target area based on the Otsu threshold, and when the data stops iterating, take the current result as the final crack detection result, that is, complete the crack detection of the external wall insulation material. The experimental results show that the method in this paper has high accuracy in detecting cracks, and it shows high crack resistance index and good detection performance when dealing with all types of cracks.