Land state monitoring method based on recursive filtering and deep object detection in GIS system

With the acceleration of urbanization and the increasing scarcity of land resources, real-time monitoring and accurate evaluation of land status have become an urgent need. This study aims to address the shortcomings of traditional land status monitoring methods in terms of accuracy and efficiency. By using ArcGIS platform, recursive filtering (RF), and deep object detection technology based on GIS system, the accuracy and real-time performance of land status monitoring can be improved, providing strong support for the rational utilization and protection of land resources. Firstly, recursive filtering is used to denoise the raw data in order to improve data quality; Then, combined with principal component analysis (PCA), key information is extracted from the recursively filtered data, effectively reducing the dimensionality of the data; Finally, the deep object detection method of Regional Convolutional Neural Network (RCNN) is applied to achieve accurate monitoring of land status. The research results indicate that this method can significantly improve the accuracy of land status monitoring, accurately identify different types of land use, change trends, etc. Compared with traditional methods, it has significantly improved monitoring accuracy and efficiency, providing a more reliable basis for land management and decision-making.