β˜„οΈ RemoteSegTransformer

Teerapong Panboonyuen
Chulalongkorn University

Read Full Thesis PDF PhD Blog & Defense Source Code on GitHub

πŸ“š 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 imagesβ€”pushing the boundaries of geospatial AI research.

πŸŽ“ Academic Journey & Scholarships

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

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

πŸ“– Thesis Works

Ph.D. Thesis

FusionNetGeoLabel: A Deep Learning Framework for Semantic Segmentation in Remote Sensing.
Teerapong Panboonyuen
Chulalongkorn University, 2020

M.Eng. Thesis

High-Resolution Road Extraction: Using Deep Convolutional Neural Networks and CRFs.
Teerapong Panboonyuen
Chulalongkorn University, 2017

πŸ“„ Read M.Eng. Thesis

πŸ“ Selected Publications

Panboonyuen, T., et al.
Transformer-Based Decoder Designs for Semantic Segmentation on Remotely Sensed Images
Remote Sensing, 2021

πŸ“„ Read Paper

Panboonyuen, T., et al.
Feature Fusion-Based Enhanced Global Convolutional Network with Channel Attention for Remote Sensing
Remote Sensing, 2020

πŸ“„ Read Paper

Panboonyuen, T., et al.
Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning
Remote Sensing, 2019

πŸ“„ Read Paper

Panboonyuen, T., et al.
Road Segmentation on Aerial Imagery Using Deep CNNs and Conditional Random Fields
Remote Sensing, 2017

πŸ“„ Read Paper

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

πŸ“„ 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:

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

πŸ“ Key Resources & Publications

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

πŸ“„ Ph.D. Thesis PDF πŸ“ PhD Blog & Defense πŸ’» GitHub Code Repository πŸ“Š ISPRS Vaihingen Dataset πŸ† ISPRS Vaihingen Leaderboard

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

πŸ”§ 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

πŸ“ 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}
}

πŸ“Έ Visual Results

Some highlights of our model's performance:

Graphical Abstract Method Illustration 2 Method Illustration 3

Sample Output 1 Sample Output 2 Sample Output 3

πŸš€ What I Do & My Impact

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

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

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

βš–οΈ License

This project is licensed under the MIT License.