☄️ RemoteSegTransformer

📚 Overview

RemoteSegTransformer is an advanced deep learning framework designed specifically for semantic segmentation of remotely sensed imagery. Leveraging a novel transformer-based decoder architecture with dynamic 2D positional encoding, this Ph.D. research introduces a powerful alternative to traditional convolutional approaches. By capturing both global context and fine-grained spatial details, it significantly enhances the precision of land cover mapping and scene understanding in satellite and aerial images—pushing the boundaries of geospatial AI research.

🎓 Academic Journey & Scholarships

I received my Ph.D. in Computer Engineering from Chulalongkorn University (2018–2020), supported by two prestigious scholarships:

• The 100th Anniversary Chulalongkorn University Fund for Doctoral Scholarship
• The 90th Anniversary of Chulalongkorn University Scholarship

Prior to this, I received my Master of Engineering in Computer Engineering from Chulalongkorn University (2016–2017), supported by:

• H.M. the King Bhumibol Adulyadej’s 72nd Birthday Anniversary Scholarship

📖 Thesis Works

📝 Selected Publications

My research contributes to the advancement of intelligent systems in geospatial analysis — supporting smart cities, environmental monitoring, disaster response, and geospatial intelligence with more robust and accurate semantic segmentation models.

📄 Abstract

Semantic segmentation plays a crucial role in remote sensing, impacting fields such as agriculture, map updating, and navigation.

While Deep Convolutional Encoder-Decoder networks are widely used, they often struggle to accurately identify fine low-level features such as rivers and vegetation due to architectural limits and scarcity of domain-specific training data.

This dissertation proposes an advanced semantic segmentation framework designed specifically for remote sensing imagery, featuring five key innovations:

• Global Convolutional Network (GCN): Enhances segmentation accuracy for remote sensing images.
• Channel Attention Mechanism: Focuses on the most critical features for better performance.
• Domain-Specific Transfer Learning: Addresses limited training data challenges.
• Feature Fusion (FF): Integrates low-level features effectively.
• Depthwise Atrous Convolution (DA): Refines feature extraction for improved segmentation.

Experiments on Landsat-8 datasets and the ISPRS Vaihingen benchmark demonstrate significant performance improvements over baseline models.

📁 Key Resources & Publications

Explore the core assets underpinning my research and contributions to the field of semantic segmentation on remote sensing imagery:

These resources highlight the rigor, reproducibility, and impact of my work within the computer vision and remote sensing communities.

🔧 How to Use

Training

Clone the repository and install dependencies:

git clone https://github.com/kaopanboonyuen/RemoteSegTransformer.git
cd RemoteSegTransformer
pip install -r requirements.txt

Prepare your dataset and modify config.json as needed, then start training:

python src/train.py --config config.json

Inference

Download pretrained models from the repository and run inference:

python src/inference.py --model path_to_pretrained_model --image path_to_image

📝 Citation

If you use this work in your research, please cite:

@phdthesis{panboonyuen2019semantic,
  title     = {Semantic segmentation on remotely sensed images using deep convolutional encoder-decoder neural network},
  author    = {Teerapong Panboonyuen},
  year      = {2019},
  school    = {Chulalongkorn University},
  type      = {Ph.D. thesis},
  doi       = {10.58837/CHULA.THE.2019.158},
  address   = {Faculty of Engineering},
  note      = {Doctor of Philosophy}
}

📸 Visual Results

Some highlights of our model's performance:

🚀 What I Do & My Impact

I build cutting-edge deep learning models for semantic segmentation of aerial and satellite images — helping computers understand complex scenes like roads, vegetation, and buildings with high precision.

My latest work improves on state-of-the-art by:

• High-Resolution Backbone: Keeps detailed image features at multiple scales.
• Feature Fusion: Combines local & global info for better accuracy.
• Depthwise Atrous Convolution: Smart multi-scale filtering to capture fine details.

Tested on top benchmarks (ISPRS Vaihingen, Landsat-8), my model scores 90%+ F1 — outperforming previous bests and powering smarter remote sensing applications.

⚖️ License

This project is licensed under the MIT License.