The algorithm and software for timber batch measurement by using image analysis

Abstract

This paper is devoted to the investigation and development of the round timber batch measurement technique on the basis of abuts detection and calculation of their diameters. The algorithm of abuts contours detection and refinement relies on the modified radial symmetry object detection. The meanshift clustering, Delaunay triangulation, Boruvka’s minimum spanning tree algorithm, watershed and Boykov-Kolmogorov graph cut algorithm are implemented at the further stages of the algorithm. The testing of the algorithm gives its TPR value at 96.2% which is much higher than other unsupervised training methods. The software for the round timber batch volume measurement was developed on the base of the algorithm. An error of the software measurement in comparison with manual piece-by-piece approach is less than 7.07% with an average error of 4.9%. It meets the requirements of industry standards so the offered technique can be successfully applied in the activity of forest enterprises. © Springer Nature Switzerland AG 2019.