Skip to content
View drkh-n's full-sized avatar
1 follower · 1 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Block or report drkh-n

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
drkh-n/README.md

👋 Hi, I'm drkh-n!

🚀 Projects I'm Currently Working On

  • Band Registration Pipeline: Developing a band registration pipeline in Python for an ongoing satellite mission, utilizing advanced computer vision techniques to align multi-band imagery.
  • Photometry Tool for Crowded Fields: Developing a tool for analyzing Spitzer IRAC archival data, leveraging simulations and PRF/PSF models to determine upper limits for faint sources in crowded fields.
  • Generalization of SatUNet: Improving generalization of Sat-UNet model using different normalization and augmentation techniques for cross-dataset inference. Currently, improved the model with percentile-based normalization and Sat-SlideMix batch-level augmentation adopted from Hopkins et al. (2025).

🌟 Projects I’m Proud Of

  • Deployment Repository for Cloud Segmentation Models (private): Designed and implemented a deployment pipeline using Vitis AI and ONNX Runtime for FPGA & ARM processors, tracking energy consumption and calculating throughput.
  • SatUNet: Collaborated on the development of a lightweight yet state-of-the-art cloud segmentation model, achieving cutting-edge performance in cloud detection tasks.

⚡ Skills & Interests

  • Satellite-based computer vision
  • Optimization for hardware platforms (FPGA, ARM)
  • Low-light and crowded astronomy photometry

Feel free to connect and discuss anything related to satellite imaging, signal processing, or hardware-aware AI!

Pinned Loading

  1. ONNX-for-QNX-7.1 ONNX-for-QNX-7.1 Public

    A guide to compile ONNX Runtime for QNX 7.1 (aarch64le)

    CMake 1

  2. VGT-Pipeline VGT-Pipeline Public

    This pipeline automates calculation process of Velocity Gradients of molecular clouds on JCMT images. It utilizes Lazarian's Julia package tool to use VGT, STARLINK to produce moment-0 maps, and Py…

    Jupyter Notebook 1

  3. SAT-UNet SAT-UNet Public

    Official repository for proposed SAT-UNet architecture from the paper "GhalamClouds: Remote Sensing Images for Kazakhstan and Clouds Segmentation Using SAT-UNet".

    Python 3 1

  4. PhotometryPy PhotometryPy Public

    This is a Python tool for analyzing Spitzer IRAC archival data, leveraging simulations and PRF/PSF models to determine upper limits for faint sources in crowded fields.

    Python

  5. Band-Registration Band-Registration Public

    The band registration pipeline

    Python 1

  6. sat-unet-generalization sat-unet-generalization Public

    This repository contains training setup that uses percentile-based normalization and Sat-SlideMix augmentation adapted from "Data Augmentation Approaches for Satellite Imagery" (Hopkins et al., 202…

    Python 1