论文部分内容阅读
树冠是预估树木生长量的基本参数之一,树冠的提取在森林资源管理中越来越受到重视,但准确获得树冠的形状和边缘信息比较困难。目前,国内外树冠提取研究主要是利用高分辨率影像、航空像片、数码相机影像以及雷达等介质,以面向对象多尺度分割技术为主,兼有专家分类、三维扫描、BP神经网络等方法。文中介绍了树冠提取技术的主要方法,总结了树冠提取技术中存在的问题及发展前景。
Canopy is one of the basic parameters to predict the growth of trees. The extraction of canopy is getting more and more attention in the management of forest resources. However, it is difficult to obtain the crown shape and edge accurately. At present, the research on canopy extraction at home and abroad mainly uses mediums such as high-resolution images, aerial photos, digital camera images and radars, and mainly focuses on object-oriented multi-scale segmentation techniques, including expert classification, 3D scanning and BP neural network . In this paper, the main methods of canopy extraction are introduced, and the problems and prospects of canopy extraction are summarized.