Abstract
Abstract. Development of laser scanning technologies has promoted tree monitoring studies to a new level, as the laser scanning point clouds enable accurate 3D measurements in a fast and environmental friendly manner. In this paper, we introduce a probability matrix computation based algorithm for automatically classifying laser scanning point clouds into ’tree’ and ’non-tree’ classes. Our method uses the 3D coordinates of the laser scanning points as input and generates a new point cloud which holds a label for each point indicating if it belongs to the ’tree’ or ’non-tree’ class. To do so, a grid surface is assigned to the lowest height level of the point cloud. The grids are filled with probability values which are calculated by checking the point density above the grid. Since the tree trunk locations appear with very high values in the probability matrix, selecting the local maxima of the grid surface help to detect the tree trunks. Further points are assigned to tree trunks if they appear in the close proximity of trunks. Since heavy mathematical computations (such as point cloud organization, detailed shape 3D detection methods, graph network generation) are not required, the proposed algorithm works very fast compared to the existing methods. The tree classification results are found reliable even on point clouds of cities containing many different objects. As the most significant weakness, false detection of light poles, traffic signs and other objects close to trees cannot be prevented. Nevertheless, the experimental results on mobile and airborne laser scanning point clouds indicate the possible usage of the algorithm as an important step for tree growth observation, tree counting and similar applications. While the laser scanning point cloud is giving opportunity to classify even very small trees, accuracy of the results is reduced in the low point density areas further away than the scanning location. These advantages and disadvantages of two laser scanning point cloud sources are discussed in detail.
Highlights
Trees do vital job for well-being of all species on the planet
We test the algorithm on mobile laser scanning (MLS) and airborne laser scanning (ALS) point clouds
For classifying the points in the input point cloud as tree points, we introduce a new approach based on the following steps; 1- Generating a probability matrix 2- Selecting maxima which indicate the locations having high probability to have a tree trunk 3- Assign points to the ’tree’ or the ’non-tree’ class 4- Filter the ground points In the following parts, we explain each step in detail
Summary
Trees do vital job for well-being of all species on the planet They do increase beauty, prove food and living space for animals, but they absorb carbon dioxide and give oxygen which contributes to the environmental circulations. When the point cloud is from an urban region, it might contain points of many different objects such as building facades, cars, light poles, traffic signs, etc. In this case, algorithms need to segment the point clouds of different objects in order to control their 3D shapes. The algorithms decide if the points are coming from a tree or another object These algorithms generally depend on either voxel space creation or fitting pre-defined geometrical models to the point clouds. The methods which are using geometrical models need specific parameter selection and they have a risk of missing trees which have trunk shapes different from the pre-defined models
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
