Urban space entity recognition method and device

• Main Authors: FENG SHUNTIAN, YANG YAN, ZHANG DONG
• Format: Patent
• Language: Chinese; English
• Published: 11.06.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides an urban space entity recognition method and device. The urban space entity recognition device segments the aerial image according to a predetermined size to obtain a plurality of raster images; for each raster image, inquiring a POI category corresponding to the position information of the raster image from a preset POI list; querying a spatial entity training set associated with the POI category from the spatial model set; utilizing the space entity training set to train a machine learning model; and recognizing the raster image by using the trained machine learning model to obtain the type of the urban space entity in the raster image. According to the invention, the recognition efficiency of the urban space entity can be effectively improved, and the operation overhead of a machine is effectively reduced. 本公开提供一种城市空间实体识别方法和装置。城市空间实体识别装置对航拍图像按照预定大小进行分割，以得到多个栅格图像；针对每个栅格图像，从预设的POI列表中查询与栅格图像的位置信息相对应的POI类别；从空间模型集中查询出与POI类别相关联的空间实体训练集；利用空间实体训练集对机器学习模型进行训练；利用经过训练的机器学习模型对栅格图像进行识别，以得到栅格图像中的城