Optimizing zero-shot segmentation of Remote Sensing imagery using LangRS: A hands-on workshop

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    22 May 2025
    Timeframe
    14:30 - 16:00 CEST Geneva
    Duration
    90 minutes
    Share this session

    LangRS is a Python library designed to enable the use of natural language processing (NLP) and Remote Sensing (RS) imagery segmentation, it is built on top of Segment Anything Geospatial (SamGEO) and deploys techniques that improve upon it. This hands-on workshop introduces LangRS, showcasing its potential to optimize zero-shot segmentation potentials through the pre-processing and post-processing techniques. 

    Participants will explore how to use LangRS to segment RS imagery. The workshop includes interactive demonstrations and practical exercises covering: 

    • Introduction to LangRS: Understand the core functionalities and architecture of LangRS and its applications in geospatial analysis.
    • Data Preparation: Learn to preprocess and structure remote sensing data for seamless integration with LangRS
    • Hands-On with LangRS: Utilize LangRS to segment and analyze satellite imagery through natural language prompts.
    • Advanced Applications: Explore complex use cases such as land cover classification, and object extraction using LangRS.
    • Visualization Techniques: Visualize geospatial outputs and insights derived from LangRS to support data-driven decision-making.

    By the end of the workshop, participants will gain practical experience in using LangRS to enhance geospatial data analysis workflows, making geospatial insights more accessible and actionable. 

    Target Audience 

    This workshop is ideal for geospatial data scientists, remote sensing analysts, computer vision researchers, and professionals interested in integrating AI with geospatial data. 

    Prerequisites 

    • A Google Colab account.
    • Basic understanding of Python programming and geospatial data concepts is recommended.
  • Are you sure you want to remove this speaker?