Skip to content
View sakrmtc's full-sized avatar
😍
😍
  • PhD Researcher
  • Egypt

Block or report sakrmtc

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
sakrmtc/README.md

Mohamed Sakr

📡 PhD Researcher · SAR Image Processing · Deep Learning · Remote Sensing

Typing SVG


Profile views GitHub followers


👨‍🔬 About Me

I am a PhD Researcher specialising in SAR image processing, Remote Sensing, and Deep Learning. My work applies state-of-the-art deep learning architectures and signal processing techniques to solve real-world challenges in synthetic aperture radar (SAR) imaging, autofocus, and terrain classification.

  • 🛰️ Research area: SAR image autofocus, mismatched filter design, terrain classification, deep learning for remote sensing
  • 🧠 Expertise: CNN · U-Net · Res-U-Net · Range-Doppler Algorithm · QCQP Optimisation · Image Restoration
  • 📄 2 Published papers in JARS 2024 and ASAT 2024
  • 🎓 MSc: Completed — Remote Sensing & Deep Learning
  • 🔬 PhD: Currently pursuing — SAR & Deep Learning
  • 🌍 Location: Egypt

🗞️ Publications

📰 Paper 1 — JARS 2024

Enhanced synthetic aperture radar image autofocus and classification using 2D SARNet framework Mohamed Sakr, Ahmed Saleh, Fathy AbdElkader, Ghada Amer, Mohamed AboElenean 📰 Journal of Applied Remote Sensing (JARS), 2024 🔗 DOI: 10.1117/1.JRS.18.026507

Key contributions:

  • ResU-Net based SAR image autofocus — replacing traditional post-processing
  • CNN terrain classifier (Mountain / Sand / River) — 100% test accuracy
  • ✅ Near-real-time SAR processing workflow
  • ✅ Quantitative evaluation using SSIM & PSNR metrics
@article{sakr2024sarnet,
  title   = {Enhanced synthetic aperture radar image autofocus and classification using 2D SARNet framework},
  author  = {Sakr, Mohamed and Saleh, Ahmed and AbdElkader, Fathy and Amer, Ghada and AboElenean, Mohamed},
  journal = {Journal of Applied Remote Sensing},
  year    = {2024},
  doi     = {10.1117/1.JRS.18.026507}
}

📰 Paper 2 — ASAT 2024

Optimization of a Mismatched Filter for SAR Imaging Using a QCQP Approach Mohamed Sakr et al. 📰 ASAT Conference, Volume 20, Issue 20, pp. 1–12, 2024

Key contributions:

  • QCQP-based mismatched filter for SAR range compression
  • ✅ Significant range sidelobe reduction vs. matched filter
  • ✅ Modified Range-Doppler Algorithm (RDA) integrating the optimized filter
  • ✅ Point target simulation validated with PSLR & ISLR metrics
@inproceedings{sakr2024qcqp,
  title     = {Optimization of a Mismatched Filter for SAR Imaging Using a QCQP Approach},
  author    = {Sakr, Mohamed and others},
  booktitle = {Proceedings of the ASAT Conference},
  volume    = {20},
  number    = {20},
  pages     = {1--12},
  year      = {2024}
}

📁 Featured Repositories

SAR Autofocus RDA Mismatched Filter Deep Learning Remote Sensing


🛠️ Tech Stack

Languages & Frameworks

Python MATLAB TensorFlow Keras NumPy OpenCV scikit-learn

Research Methods & Models

CNN U-Net ResU-Net RDA QCQP

Tools & Platforms

Jupyter Google Colab Git GitHub


📊 Research Focus Areas

🛰️  SAR Image Processing        ████████████████████  100%
🧠  Deep Learning (CNN/U-Net)   ████████████████████  100%
🗺️  Terrain Classification      ████████████████████  100%
📡  Remote Sensing              ████████████████████  100%
🔬  SAR Autofocus & RDA         ████████████████░░░░   80%
🧮  Signal Optimisation (QCQP)  ██████████████░░░░░░   70%
📈  Evaluation Metrics          ██████████████░░░░░░   70%

📈 GitHub Stats


🎓 Academic Journey

Degree Field Status
🔬 Doctor of Philosophy (PhD) SAR Image Processing & Deep Learning 🔄 In Progress
Master of Science (MSc) Remote Sensing & Deep Learning Completed
Bachelor of Science (BSc) Engineering Completed

📬 Contact & Collaboration

GitHub

💡 Open to academic collaboration in SAR image processing, deep learning for remote sensing, and related research fields.


"Combining the precision of radar technology with the power of deep learning to see the Earth in new ways."

If you find my work useful, please consider starring the repositories!

Pinned Loading

  1. deep-learning-remote-sensing deep-learning-remote-sensing Public

    CNN terrain classifier (100% accuracy) and Residual U-Net for remote sensing - MSc research project by Mohamed Sakr

    Jupyter Notebook

  2. sar-autofocus-resunet-classification sar-autofocus-resunet-classification Public

    SAR autofocus and terrain classification using ResU-Net and CNN - JARS 2024 (PhD/MSc research by Mohamed Sakr)

    Jupyter Notebook