Building roof identification method and device based on multi-source heterogeneous deep network fusion

• Main Authors: LI LIFENG, RAO ZHI, YANG ZAIMIN, YANG XIONGPING, XI YUNHUA, LI SHUANG, SUN SIYANG, LI JIAMING, MENG WENCHUAN
• Format: Patent
• Language: Chinese; English
• Published: 19.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention relates to a building roof identification method and device based on multi-source heterogeneous deep network fusion, computer equipment, a storage medium and a computer program product, and can be applied to the technical field of image identification. According to the invention, the building roof identification efficiency and accuracy can be improved. The method comprises the steps of obtaining an optical image of a target area and a remote sensing image of the target area; the target area comprises a building roof; inputting the optical image into an optical image segmentation model to obtain an optical segmentation image of the building roof; inputting the remote sensing image into a remote sensing image segmentation model to obtain a remote sensing segmented image of the building roof; performing fusion processing on the optical segmentation image and the remote sensing segmentation image to obtain a fusion segmentation image of the building roof; and identifying the fused segmented image to