Abstract
Pine wood nematode disease is a very contagious and devastating forest pest. Finding infected trees in time, counting them, and clearing or selective cutting according to different diseased tree densities is the main way to control the spread of the disease. In this paper, threshold segmentation technology is used to reduce the adverse effects of interference factors such as buildings, rocks, and soil in the data set on density estimation, and finally a higher-quality density map is obtained to realize the counting of pine wood nematode diseased trees. Compared with the classic density estimation algorithm, the mean absolute error of this algorithm has dropped by 9.2, the root mean square error has dropped by 7.4, the variance of absolute error has dropped by 65.0, and the counting accuracy has increased by 19.6%.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.