Map geographic information road extraction method based on generative adversarial network and U-Net.

In today's rapidly developing remote sensing technology, accurately extracting geographic information from maps is crucial for many key areas such as urban planning, environmental monitoring, and traffic management. However, due to the complexity and variability of remote sensing images, effectively extracting road information from multi-scale geographic images remains a technical challenge. Therefore, the study innovatively proposes a fusion model for panchromatic and multi-spectral images and a fusion map geographic information extraction model from the perspectives of image fusion and road segmentation. Structural similarity and spatial correlation coefficients are crucial for assessing the effectiveness of model image fusion. The experimental results show that in the panchromatic and multispectral remote sensing image datasets, the structural similarity of the model reached 0.023, which was very close to the target value of 0, indicating that the model had excellent image fusion ability. Meanwhile, the spatial correlation coefficient value was also as high as 0.99, close to the target value of 1, further confirming the efficiency of the model in image fusion. Compared with other methods, the designed method had significant advantages in maintaining the continuity of road structure, which could more accurately identify and reproduce the continuity of roads and reduce errors in the extraction process. In summary, the research results are of great significance to improve the accuracy and efficiency of remote sensing image analysis, which not only can provide strong technical support for the application in the above related fields, but also can contribute to the further development and application of remote sensing technology in geographic information extraction.