Develop technology to make life better

Develop technology to make life better

Here is my technology repo.
Anyone can use my work.
Use it to help others again.

I. Demo

1. Drone Vision
   
   Click the image to watch video clip.
   • Trajectory planning (Drone control using ROS2)
   • Object detection (Customized YOLOv5)
   • Localization (Drone-Visual SLAM in farming)
   • Structure from Motion (Point Cloud Processing)
     developed at hexafarms

2. 3D reconstruction
   
   Click the image to watch video clip.
   developed at hexafarms

3. Data Science
   
   Click the image to watch video clip.
   • Image Segmentation (Holystic Image Class)
   • Data Processing (Pandas)
   • Visualization (Matplotlib, Seaborn)
     developed at hexafarms
4. Complex image processing
   • Instant Segmentation (Custom-made Holystic Image Class)
   • Image-tabular data combined Classification
   • Time-series analysis for growth
     developed at hexafarms
5. Web application: Sensor and User accounts management
   
   • Database setup
   • Authentification
   • Interaction with external services (Apache Airflow, MLservices, Docker Swarm)
     developed at hexafarms
6. LLM powered web chatbot
   
   • Natural Language Processing, Word Embedding
   • Design Concurrency Functionality
   • Query Optimization
     developed at hexafarms
7. MLOPs&HyperParameter Tuning
   
   • Only Opensource-based full MLOps-HyperParameter tuning pipeline
8. Time-series Forecast
   ![Timeseries][..\img\tsforecast.gif]
   • Feature based Imputation (Transformer/ML-based, statistic)
   • Future forecasting
   • XAI (Explainable AI) to understand why model performs better and worse developed at hexafarms

II. More Source Codes

1. openHexa
2. cvOps
3. Compute pixel’s actual dimension
4. YOLO data generator
5. Image classification & mass estimation based on segmentation mask
6. Image cropping for generating training samples
7. Image Segmentation using Graph-cut
8. Wildfire prediction using timeseires data
9. MLflow+HyperOpt+MMOpenLab wraper
10. Berlin Reservation Bot

III. Research

1. Deep Learning-Based Semiautomatic Generation of HD maps from Aerial Imagery, Master thesis
   Sharing the source code requires approval of the institute, ika. Contact me if you are interested in the algorithm in detail.
2. Deep Aerial Mapper: TBD

IV. Learning

1. Camera Parameter
2. Point Cloud Library
3. 3D Reconstruction
4. Color and Illumination
5. Feature extraction
6. Plant nutrient deficiency
7. Public Leaf dataset
8. Plant biology
9. ROS2, Udemy
10. Advanced C++, Coursera
11. Data Structure
12. Airflow, Udemy
13. Open3d
14. Elixir, Phoenix

I learn hard and apply the knowledge assiduously. But I still relish chill, too.