I am a Computer Scientist working at the NASA IMPACT - UAH and currently residing in Huntsville, US. I defended my Ph.D. in Geo-informatics as a Prime Minister's Research Fellow (2018) working under the supervision of Prof. Surya S Durbha at the Geocomputational Systems and IoT Group in Centre of Studies in Resources Engineering , IIT Bombay. I have completed my undergraduation in Electronics and Telecommunication Engineering from National Institute of Technology Raipur in 2016.

I love to play flute and save shots on a goal post while playing football.

My research interests lie at the intersection of 3D computer vision, machine learning, embedded systems, Internet of Things, high-performance computing and signal processing. My Masters-PhD topic involves application of deep learning for onboard point cloud processing.

Email | Scholar | ORCID | OSGeo | LinkedIn | Twitter | Github |

News

  • [Apr 2023]: Defended my Ph.D. and joining NASA IMPACT as a Computer Scientist. New location - Huntsville.
  • [Feb 2022]: I would be contributing as a General Program Committee member for the FOSS4G 2022 to be organized in Firenze, Italy.
  • [Dec 2021]: I got elected as an OSGeo Board member for the current cycle. Thanks to the amazing OSGeo community for the trust and support. 😃
  • [Aug 2021]: Our work - "LidarCSNet: A Deep Convolutional Compressive Sensing Reconstruction Framework for 3D Airborne Lidar Point Cloud" has been accepted for publication in the ISPRS Journal of Photogrammetry and Remote Sensing (IF:10.76, #1 ranked journal out of 50 in Geography, Physical).
  • [June 2021]: I recently participated in an invited Science & Technology Open House webinar on the topic - "Young Turks: From Outreach, Research And Science Communication". It was an amazing interaction. Link to the YouTube video.
  • [Apr 2021]: I would be mentoring for the United Nations - OSGeo Open Education Challenge 2021.
  • [Apr 2021]: My talk on EcoViz was broadcast live in the Geo for Good Lightning Talk series hosted by Google Earth Outreach.
  • [Apr 2021]: It was an amazing learning experience attending the Google Graduate Symposium; Made new friends, attended highly insightful talks and lectures.
  • [Apr 2021]: Our Paper got selected for the IEEE STRATUS 2021 conference (virtual conference)
  • [Mar 2021]: 3 Papers selected in the IEEE IGARSS 2021 (virtual conference).
  • [Jan 2021]: Our work on rendering Comprehensive Spatio-Contextual Grounded Natural Language Scene Descriptions from Remote Sensing Scenes has been published in the Special Issue on "Geospatial Artifical Intelligence" in the ISPRS International Journal of Geo-Information.
  • [Jan 2021] Elected as PSC (Project Steering Committee) Member for the ZOO-Project

    • Past news...

Research

  • LidarCSNet: A Deep Convolutional Compressive Sensing Reconstruction Framework for 3D Airborne Lidar Point Cloud
    Rajat Shinde, Surya Durbha, Abhishek Potnis
    Accepted in ISPRS Journal of Photogrammetry and Remote Sensing (IF:8.979, ranking it 1 out of 50 in Geography, Physical | Source )
    pdf | BibTeX
  • Towards Enabling Deep Learning Based Question-Answering for 3D LiDAR Point Clouds
    Rajat Shinde, Surya Durbha, Abhishek Potnis, Pratyush Talreja, Gaganpreet Singh
    Accepted in IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021, virtual conference)
  • Deep Learning based Real-time Building Classification using UAV Imagery
    Pratyush Talreja, Surya Durbha, Rajat Shinde, Abhishek Potnis
    Accepted in IEEE Systems and Technologies for Remote Sensing Applications Through Unmanned Aerial Systems (STRATUS 2021, virtual conference)
  • Towards Visual Exploration of Semantically Enriched Remote Sensing Scene Knowledge Graphs (RSS-KGS)
    Abhishek Potnis, Surya Durbha, Rajat Shinde, Pratyush Talreja
    Accepted in IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021, virtual conference)
  • Real-time Embedded HPC Based Earthquake Damage Mapping Using 3D LiDAR Point Clouds
    Pratyush Talreja, Surya Durbha, Rajat Shinde, Abhishek Potnis
    Accepted in IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021, virtual conference)
  • Semantics-Driven Remote Sensing Scene Understanding Framework for Grounded Spatio-Contextual Scene Descriptions
    Abhishek Potnis, Surya Durbha, Rajat Shinde
    ISPRS International Journal of Geo-Information
    pdf | BibTeX
  • Online Point Cloud Super Resolution Using Dictionary Learning For 3d Urban Perception
    Rajat Shinde, Abhishek Potnis, Surya Durbha
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2020, virtual conference)
    pdf | BibTeX
  • Towards Natural Language Question Answering Over Earth Observation Linked Data Using Attention-based Neural Machine Translation
    Abhishek Potnis, Rajat Shinde, Surya Durbha
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2020, virtual conference)
    pdf | BibTeX
  • Compressive Sensing Based Reconstruction And Pixel-Level Classification of VHR Disaster Satellite Imagery Using Deep Learning
    Rajat Shinde, Abhishek Potnis, Surya Durbha, Prakash Andugula
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Japan
    pdf | BibTeX
  • Multi-class Segmentation of Urban Floods From Multispectral Imagery Using Deep Learning
    Abhishek Potnis, Rajat Shinde, Surya Durbha, Kuldeep Kurte
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Japan
    pdf | BibTeX
  • Rapid Earthquake Damage Detection Using Deep Learning From VHR Remote Sensing Images
    Ujwala Bhangale, Surya Durbha, Abhishek Potnis, Rajat Shinde
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Japan
    pdf | BibTeX
  • Semantic Framework For Spatial Query Reformulation For Disaster Monitoring Applications
    Kuldeep Kurte, Abhishek Potnis, Surya Durbha, Rajat Shinde
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Japan
    pdf | BibTeX
  • Information Table based Decision Approach for Broadcast Storm Suppression in Vehicular Ad-Hoc Networks
    Aditya Om, Rajat Shinde, Sejal Agrawal, A.S. Raghuvanshi
    International Journal of Engineering and Technical Research V5(04), April 2016
    pdf | BibTeX

Projects

  • Google Summer of Earth Engine 2019
    Student developer for Nature Conservation Foundation under the mentorship of Dr. M D Madhusudan
    • Developed EcoViz: A Google Earth Engine based web application for robust visualization of ecological status of selected world heritage sites of the Western Ghats in India

    App | Presentation

  • Earth Engine India Advanced Summit Buildathon 2019
    Worked on "Locating Solar Farms in Selected Sites of India using Google Earth Engine"
    • In a team of 6, implemented random-forest classifier to solve binary classification problem (Solar Farm: 1, Non-Solar farm: 0) with an accuracy of 81%
    • Added Wavelet Kernel-based convolution approach for solar panels texture detection thus improving the accuracy to 83.6%

    Presentation | Code | Buildathon

  • Earthquake Prediction Using Machine Learning Techniques
    • In a team of 4, implemented machine learning models(SVM, ANN, Random Forests & Decision Tree Classifier) obtaining maximum accuracy of 94.5% to predict the earthquake in the Andaman & Nicobar Islands and Sumatra region
    • Extracted features (b-values) from USGS earthquake dataset of the last 26 years to train models

    Report

  • Image Pre-processing using Lee & Gradient-Inverse Kernels
    • Implemented Lee kernel and Gradient-Inverse kernel for satellite image pre-processing
    • Developed a Graphical User Interface (GUI) based application in MATLAB

    Report | Code

Leadership

  • OSGeo Board of Directors - Member (Dec. 2021 - Present)
    Role: Elected as a Board Member by the existing worldwide Charter members for the Open Source Geospatial Foundation (OSGeo)
  • Project Steering Committee Member (Jan. 2021 - Present)
    • Elected as one of the PSC Member for the ZOO-Project
    • Contributing to an active Open Geospatial Consortium (OGC)-Web Processing Service (WPS) standard based open-source project used by various geospatial clients
  • OSGeo Charter Member (Jul. 2018 - Present)
    Nominated as one of the international Charter Member of the Open Source Geospatial Foundation for spreading awareness about the open-source geospatial science and development
  • Company Coordinator (awarded Certificate of Excellence towards work ethics and commitment 2017-18) - Coordinated with the firms and helped ∼ 1600 students during campus placements

Open Source Contributions

Awards

Teaching Assistantship

  • GNR 615 - Principles of Geographic Information Systems Lab 2018 Autumn
  • GNR 615 - Principles of Geographic Information Systems Lab 2017 Autumn
  • GNR 603 - Satellite Image Processing 2017 Autumn
  • GNR 402 - Introduction to Geographic Information Systems 2017 Autumn

Academics