【Instance Segmentation of Outdoor Sports Ground from High Spatial Resolution Remote Sensing Imagery Using the Improved Mask R-CNN】

The detailed information of spectrum, geometry and texture of outdoor stadiums can be reflected in the high spatial resolution remote sensing imagery (#HSRRSI) clearly, which provides a useful data source for land features detection and identification of outdoor stadiums. This paper makes full use of the advantages of HSRRSI and proposes a set of object recognition methods and technical flow based on #Mask_R_CNN, which can be used to recognize four outdoor sports ground of football field, basketball court, tennis court and baseball field.