Remote sensing image planar ground object extraction method based on object-oriented segmentation

• Main Authors: XU GAOCHENG, LIU XIAOFEI, SUN XIAOYUE, MI SUJUAN, LUO LUN, CAI HONGYUE
• Format: Patent
• Language: Chinese; English
• Published: 02.03.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The embodiment of the invention provides a remote sensing image planar ground object extraction method, device and equipment based on object-oriented segmentation and a computer readable storage medium. The method comprises the following steps: acquiring a regional image; based on the user interaction information, performing object-oriented image segmentation on the regional image to obtain a segmentation edge pixel set; performing ground object edge tracking on the segmentation edge pixel set to obtain an initial tracking edge; and carrying out closed communication on the initial tracking edge to form a closed communication region to obtain a planar ground object boundary. In this way, semi-automatic extraction of any planar ground object can be completed, and the method is suitable for an application scene of ground object extraction in a complex geographical environment in a remote sensing image. 本公开的实施例提供了一种基于面向对象分割的遥感影像面状地物提取方法、装置、设备和计算机可读存储介质。所述方法包括获取区域图像；基于用户交互信息，对所述区域图像进行面向对象影像分割，得到分割边缘像素集合；对所述分割边缘像素集