Application of local region-growing method based on normalized cross — Correlation to TBM rock slag identification and measurement

This study aims to meet requirement of rapid detection of the TBM (tunnel boring machine) tool's wear state. To this end, the local region-growing method based on normalized cross-correlation was proposed to detect the block slag on belt conveyor and the least-square method for ellipse fitting was employed to measure the size. Firstly, the monocular color image was decomposed into two gray-scale images with uniform size by the chromatic aberration transformation method, and the two gray images are used as the reference map and the search map respectively. Then the normalized crosscorrelation method was applied to locate the basic area of slag; Secondly, in order to obtain the seeds for region growing method, the belt, gravel and other interference areas were removed, and the complete area of rock ballast was got by local region-growing method eventually; Finally, the ellipse was fitted by the least-square method for the segmented region, and the size of the block slag was measured. The experimental results showed that the proposed method can quickly and accurately identify the rock slag and complete the slag size measurement. Overall, the algorithm is stable and meets the demand of detection.