(Translated by https://www.hiragana.jp/)
LucasOsco (Lucas Osco) · GitHub
Skip to content
View LucasOsco's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
  • University of Western São Paulo (UNOESTE)
  • SP, Brazil

Block or report LucasOsco

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
LucasOsco/README.md

Lucas Osco

LinkedIn ResearchGate Google Scholar ORCID

About Me

I am an Environmental Engineer and Professor with a doctorate in Engineering, focusing on Environmental Technologies, and a postdoctoral degree in Natural Resources. My passion lies in Remote Sensing and Vegetation Analysis, and I'm interested in how Artificial Intelligence can revolutionize this field.

Projects

  • AI-Remote Sensing - AI-RemoteSensing is a collection of Jupyter and Google Colaboratory notebooks dedicated to leveraging Artificial Intelligence in Remote Sensing applications. This repository serves as an open-source platform for researchers, educators, and professionals to explore, learn, and expand their knowledge in this exciting intersection of technologies.

  • Segment-Geospatial - Segment-Geospatial is a Python package dedicated to segmenting geospatial data with the Segment Anything Model (SAM). Through the segment-anything-py and segment-geospatial Python packages, we aim to simplify the process of leveraging SAM for geospatial data analysis, enabling users to achieve this with minimal coding effort.

Organizations

  • Open Geospatial Solutions - Open Geospatial Solutions is a collective of open-source geospatial software projects, developed and maintained by a community of geospatial software developers and researchers. All projects under Open Geospatial Solutions are free to use, modify, and are licensed under the MIT license. The organization promotes open-source resources and collaboration for researchers, educators, and professionals in the field of geospatial data science.

Published Work

  • The Potential of Visual ChatGPT For Remote Sensing - This paper investigates the potential of Visual ChatGPT in remote sensing. Our findings expose the model's limitations but also forecast its transformative potential in remote sensing image processing. Here we discuss how Visual Large Language Models (LLMs) can be used in the remote sensing domain and assist users with image processing tasks.

  • A Review on Deep Learning in UAV Remote Sensing - This comprehensive review examines 232 papers featuring Deep Learning applications with UAV-acquired data. Our findings underscore Deep Learning's promise in processing UAV-based image data, particularly within environmental, urban, and agricultural contexts.

  • The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot - We examine Meta AI's Segment Anything Model (SAM) for remote sensing. Despite certain limitations, SAM's promising performance across diverse contexts underscores its potential in this domain. We increased SAM's accuracy and reduced manual annotation by combining general examples and one-shot training. We suggest further enhancements and provide our modifications' open-source code for broader SAM adaptations.

See all my publications

Skills

Python R Machine Learning Deep Learning Remote Sensing Spectroscopy Scientific Writing

Contact

Feel free to email me or connect with me on LinkedIn and Research Gate.

Pinned Loading

  1. AI-RemoteSensing AI-RemoteSensing Public

    Jupyter Notebook 173 29

  2. opengeos/segment-geospatial opengeos/segment-geospatial Public

    A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

    Python 3k 312