Remote Sensing🛰️🌐
Collection
Computer vision models for satellite imagery analysis, focusing on semantic segmentation of road networks. • 1 item • Updated
Satellite Road Segmentation UNet
Satellite Road Segmentation UNet is a deep learning model designed for segmenting roads from satellite imagery. It utilizes a U-Net architecture, which is widely used for image segmentation tasks due to its ability to capture both local and global features effectively. Training data from https://www.kaggle.com/datasets/balraj98/massachusetts-roads-dataset?resource=download-directory
Full project file at https://github.com/teohyc/satellite_road_seg
Usage
from road_seg_infer import ConvBlock, UNet, road_seg_infer_main, load_image, predict_mask, visualize_result
road_seg_infer_main(image_path = "infer_satellite_image.tiff") #change this to your image path