An Information Extraction Method for Statistical Thematic Maps Combining YOLO and Syntactic Model

Objectives: With the advancement of artificial intelligence, automatic extraction and interpretation of map information from large-scale statistical thematic maps have become significant research topics in cartography. This study aims to develop a method that combines the YOLOv8 model with a syntactic model to extract structured information from statistical thematic maps, thereby supporting applications such as knowledge graph construction and intelligent cartographic recommendations. Methods: The research employed an improved YOLOv8 model to extract and classify various map elements from a dataset of 133 statistical thematic maps with 3,512 annotated elements. To enhance the performance of YOLOv8 model for this specific application, the model was modified by incorporating Residual Hybrid Attention Groups (RHAG) in the Backbone and replacing the upsampling part with DySample upsampler. Subsequently, pattern recognition techniques were employed to extract the visual variables of graphical elements. Finally, based on a syntactic model, structured descriptions of the map content were generated, which involved analyzing the relationships between graphical elements and reconstructing the hierarchical and syntactic structure of the symbols. Results: The improved YOLOv8 model demonstrated remarkable effectiveness in extracting both map elements and graphical primitives, achieving mean Average Precision (mAP50) values of 92.6% and 99.4%, respectively. This indicates a high level of precision in identifying and classifying various elements within the maps. The method successfully captured the syntactic structure of statistical thematic maps, enabling the extraction of semantic information such as thematic categories, spatial relationships, and quantitative values. Conclusions: The combination of object detection and syntactic modeling can efficiently extract structured information from statistical thematic maps. This approach provides an in-depth interpretation of map content and highlights its practical utility in cartographic analysis. Future research will continue to explore and optimize this method for broader applications.