Develop technology to make life better

Develop technology to make life better

Here is my technology repo.
Anyone can use my work.
Feel free to use it to help others.

---

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

---

1. 3D reconstruction
   
   Click the image to watch video clip.
   developed at hexafarms

---

1. Data Science
   
   Click the image to watch video clip.
   • Image Segmentation (Holystic Image Class)
   • Data Processing (Pandas)
   • Visualization (Matplotlib, Seaborn)
     developed at hexafarms

---

1. Image processing
   • Instant Segmentation (Custom-made Holystic Image Class)
   • Image-tabular data combined Classification
   • Time-series analysis for growth
     developed at hexafarms

---

1. Web application: Sensor and User accounts management
   
   • Full-stack dev
     developed at hexafarms

---

1. LLM powered web chatbot
   
   • Natural Language Processing, Word Embedding
   • Design Concurrency Functionality
   • Prompt Engineering
     developed at hexafarms

---

1. MLOPs&HyperParameter Tuning
   
   • Fully Open source-based full MLOps-HyperParameter tuning pipeline

---

1. Time-series Forecast
   
   • Develop domain knowledge-supported custom ML MultiConstrainedLinearRegression
   • Feature based Imputation (Transformer/ML-based, statistic)
   • Feature Engineering
   • XAI (Explainable AI) to understand why model performs better or worse developed at hexafarms

---

II. More Source Codes

1. openHexa
2. MultiConstrainedLinearRegression
3. cvOps
4. Compute pixel’s actual dimension
5. YOLO data generator
6. Image classification & mass estimation based on segmentation mask
7. Image cropping for generating training samples
8. Image Segmentation using Graph-cut
9. Wildfire prediction using timeseires data
10. MLflow+HyperOpt+MMOpenLab wraper
11. 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.