GeoOSAM
Plugin ID: 4007
Advanced segmentation tool with intelligent SAM 2.1/Ultralytics SAM2.1_B selection, exceptional CPU performance (<1s on 24+ cores), GPU acceleration, threading, and professional workflow features
(37) votes
Download latest
GeoOSAM brings Meta's latest Segment Anything Model (SAM 2.1) and Ultralytics SAM2.1_B to QGIS with intelligent hardware optimization. Features automatic model selection: SAM 2.1 for GPU systems (CUDA/Apple Silicon) and Ultralytics SAM2.1_B for CPU-only systems, providing 5-10x performance improvements. Ultralytics automatically handles SAM2.1_B downloads for seamless CPU setup. Includes GPU/CPU acceleration with automatic device detection, multi-threaded processing for responsive UI, Point and BBox segmentation modes, 12 pre-defined classes (Buildings, Roads, Vegetation, Water, Vehicle, Ship, etc.) plus custom class creation, Undo functionality for mistake correction, Custom output folder selection, Optional debug mask saving, Automatic raster layer re-selection, Professional shapefile export with detailed attributes. Perfect for remote sensing analysis, urban planning, environmental monitoring, and geospatial segmentation tasks. Optimized for NVIDIA GPU, Apple Silicon, and multi-core CPU processing with intelligent model selection for optimal performance on any hardware.
python
remote sensing
gis
urban planning
machine learning
segmentation
deep learning
satellite imagery
ai
sam
computer vision
semantic segmentation
sam2.1
pytorch
cuda
performance optimization
geospatial analysis
sam2
apple silicon
environmental monitoring
raster analysis
gpu acceleration
object detection
intelligent model selection
ultralytics
sam2.1_b
