Landslide extraction method, landslide extraction system and terminal

Abstract

The invention is applicable to the field of remote sensing measurement and control, and provides a landslide extraction method, a landslide extraction system and a terminal, and the method comprises the steps: respectively obtaining at least one remote sensing image in a current period and a historical period of a to-be-measured area, and a digital elevation model (DEM) of the to-be-measured area; training a deep convolutional neural network model according to at least one remote sensing image in the historical period and the corresponding historical landslide truth value; based on at least one remote sensing image in the current period, performing landslide extraction through the trained deep convolutional neural network model to obtain a preliminary extraction result; according to the preliminary extraction result and the DEM, counting landslide attribute information, obtaiing a landslide extraction result containing the landslide attribute information. The reliability and precision of landslide extraction are improved, and the speed and automation degree of landslide extraction are improved. 本申请适用于遥感测控领域，提供一种滑坡提取方法、滑坡提取系统及终端，其中方法包括：分别获取待测地区的当前时期和历史时期中至少一个遥感影像，及所述待测地区的数字高程模型DEM；根据所述历史时期中至少一个遥感影像和对应的历史滑坡真值，训练深度卷积神经网络模型；基于所述当前时期中至少一个遥感影像，通过训练后的所述深度卷积神经网络模型进行滑坡提取，得到初步提取结果；根据所述初步提取结果及所述DEM，统计滑坡属性信息，获取包含所述滑坡属性信息的滑坡提取结果，提高滑坡提取的可靠性和精度，提升滑坡提取的速度和自动化程度。