Welcome to PolyGoneNMS

PolyGoneNMS is an optimized library for performing Non-Maximum Suppression (NMS) on polygons in spatial data. It offers a flexible and efficient solution for handling large numbers of polygons in 1D, 2D, and 3D space.

The library is designed to work with various NMS methods, such as Default, Soft, and Class Agnostic NMS, and supports multiple intersection methods, including Intersection over Union (IOU), Intersection over Self (IOS), and the Dice coefficient. PolyGoneNMS also supports distributed processing using Ray or Dask to speed up computations on large-scale datasets.

The primary use case for PolyGoneNMS is in computer vision and GIS applications, where it can help to filter and cluster overlapping polygons and improve the overall performance of object detection and spatial analysis tasks.

With an easy-to-use API and efficient implementation, PolyGoneNMS is the ideal choice for researchers, developers, and enthusiasts working on projects that involve processing large amounts of spatial polygon data.