Fractal dimension supervised learning-based foundation LiDAR branch and leaf point cloud separation method

Abstract

The invention discloses a fractal dimension supervised learning-based foundation LiDAR branch and leaf point cloud separation method. The method comprises the following steps of S1, calculating a fractal dimension feature vector according to a box dimension method; s2, calculating zenith angles and zenith angle variation; and S3, calculating a point distribution feature vector, and separating thetrunk from the leaves by calculating the number of points in the cylinder. According to the method, four new geometric feature vectors are calculated from the three-dimensional coordinates of the point cloud, so that the robustness of the branch and leaf separation method is improved. Firstly, fractal dimensions are applied to branch and leaf separation according to different geometrical characteristics and roughness of leaves and branches; and then, the separation capacity of the leaves and the branches is enhanced by calculating zenith angles and variable quantities; finally, the local pointdensity of the point cloud is calculated by adopting a cylinder with a self-adaptive central axis, and further the separation precision of branches and leaves is improved. Experimental results show that compared with a method based on characteristic values, the method provided by the invention can obtain higher precision and F1 value.

Description

technical field [0001] The present invention relates to the technical field of branch and leaf separation methods, in particular to a ground-based LiDAR branch and leaf point cloud separation method based on fractal dimension supervised learning. Background technique [0002] Three-dimensional laser scanning (LS) technology is an active remote sensing technology that has developed rapidly in recent years. The LS system can actively emit laser pulses to obtain the three-dimensional coordinate information of the target object, making it an important data source for vegetation spatial topology analysis. With the improvement of LS measurement accuracy and sampling rate, this technology has been widely used in forestry, ecology, botany and other related fields. Compared with airborne or spaceborne LS, ground-based LS (TLS) can provide smaller light spots, obtain higher single-light point measurement accuracy, and provide denser point cloud data. Therefore, TLS is widely used in...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of poor robustness and low precision in the prior art, and propose a ground-based LiDAR branch-leaf point cloud separation method based on fractal-dimensional supervised learning

Images