galaxy-object-detection-core 0.1.2

YOLO-based object detection system for various industries

🤖 Galaxy Object Detection Core

Welcome to the Galaxy Object Detection Core — a modular, production-ready object detection library built using YOLOv8 and YOLOv11 architectures. This project empowers developers, researchers, and enterprises to detect and analyze a variety of objects across domains like transportation, safety, documentation, and natural resources with high precision and speed.

Developed by @muhammadhaerul.25

---

📚 Table of Contents

• ✨ Key Features
• 🏢 Industry Applications
• 📦 Supported Models
• ⚙️ Installation
• 🚀 Quick Start
• 🧠 Available Detection APIs
• 📁 Project Structure
• 📸 Example Results
• 🛠 Contributing
• 📝 License

---

✨ Key Features

• ✅ Plug-and-play object detection with pretrained YOLO models
• 🎯 Supports 20+ categories including safety gear, documents, vehicles, and minerals
• 🚦 Optimized for real-time inference (30+ FPS)
• 🛠 Simple Python API for both batch and single-image detection
• 📊 Segmentation and detection support with metadata extraction
• 🌍 Indonesian-optimized models for local compliance and recognition
• 📈 Statistical logging and dashboard integration ready

---

🏢 Industry Applications

• Human, Safety, Environment
• Transportation and Infrastructure
• Fast-Moving Consumer Goods
• Office, Legal, Finance
• Nature and Environment

---

📦 Supported Models

🚗 Transportation

• Vehicle Detection
• Vehicle Plate Detection (Indonesia-specific)
• Road Damage Detection

🏗️ Construction & Safety

• Personal Protective Equipment (PPE v1, v2)
• PPE Segmentation (v2)
• Human Head Detection

📌 Documentation

• Indonesian KTP Detection
• QR Code Detection
• Invoice & Receipt Detection
• Meterai (Stamp Duty) v1 & v2

🌋 Minerals

• Mineral Boulder Detection
• Boulder Segmentation
• Mineral Soil Detection

🧪 Coming Soon Models

---

⚙️ Installation

📋 Requirements

• Python >= 3.10
• CUDA-compatible GPU (optional but recommended)
• pip

🔧 Install via PyPI (Recommended)

pip install galaxy-object-detection-core

🧪 Install via GitHub (Latest Development Version)

pip install git+https://github.com/muhammadhaerul/Galaxy-Object-Detection-Core.git

💻 Install via Clone

# Clone the repository
$ git clone https://github.com/muhammadhaerul/Galaxy-Object-Detection-Core.git
$ cd galaxy-object-detection-core

# Install dependencies
$ pip install -r requirements.txt

---

🚀 Quick Start

🔍 Detect a Single Image

from galaxy_object_detection_core.GalaxyObjectDetector import GalaxyObjectDetector

img = "images_sample/sample1.jpg"

# Detect PPE
result = GalaxyObjectDetector.detect_ppe(img, version="v2")
print("Saved at:", result)

# Detect Vehicle
result = GalaxyObjectDetector.detect_vehicle(img)

# Segment PPE
result = GalaxyObjectDetector.segment_ppe(img)

# Detect Custom Objects (YOLO World)
result = GalaxyObjectDetector.detect_custom_object(img, ["helmet", "person"])

---

🧠 Available Detection APIs

Generic

• detect_object(model_path: str, image_path: str)
• segment_object(model_path: str, image_path: str)

Human, Safety, Environment

• detect_human_head(image_path: str)
• detect_ppe(image_path: str, version: Literal['v1', 'v2', 'latest'])
• segment_ppe(image_path: str)

Transportation and Infrastructure

• detect_vehicle(image_path: str)
• detect_vehicle_plate(image_path: str)
• detect_road_damage(image_path: str)

Office, Legal, Finance

• detect_ktp(image_path: str)
• detect_invoice_and_receipt(image_path: str)
• detect_meterai(image_path: str, version: Literal['v1', 'v2', 'latest'])
• detect_qrcode(image_path: str)

Nature and Environment

• detect_mineral_boulder(image_path: str)
• segment_mineral_boulder(image_path: str)
• detect_mineral_soil(image_path: str)

YOLO World

• detect_custom_object(image_path: str, list_object_to_detect: List[str])

---

📁 Project Structure

galaxy-object-detection-core/
├── galaxy_object_detection_core/
│   ├── GalaxyObjectDetector.py       # Main detection API class
│   └── models/                       # YOLO model weights (excluded from PyPI, downloaded externally)
├── images_sample/                   # Example input images
├── images_detected/                 # Detection result outputs
├── main.py                          # Sample runner
├── requirements.txt
└── README.md

---

📸 Example Results

Example	Output Path
Human Head Detection	images_detected/result_of_head_using_model_human_head_detector_yolo8n.jpg
PPE Detection	images_detected/result_of_head_using_model_personal_protective_equipment_detector_yolo8n_v2.jpg
PPE Segmentation	images_detected/result_of_head_using_model_personal_protective_equipment_segmentator_yolo8n_v2.jpg
Vehicle Detection	images_detected/result_of_model_vehicle_detector_yolo11n_v1.jpg
License Plate Detection	images_detected/result_of_model_vehicle_plate_detector_yolo8n_v1.jpg
Road Damage Detection	images_detected/result_of_model_road_damage_detector_yolo8n.jpg
Invoice Detection	images_detected/result_of_invoice_using_model_invoice_and_receipt_detector_yolo8n.jpg
Meterai Detection	images_detected/result_of_meterai_using_model_meterai_detector_yolo8n_v2.jpg
Custom Detection (Fish)	images_detected/result_of_fish_using_custom_detect_plant_fish.jpg
Custom Detection (Helmet/Person)	images_detected/result_of_head_using_custom_detect_helmet_person.jpg

⚠️ Make sure to run inference at least once before using visual outputs.

---

🛠 Contributing

We welcome your contributions to improve this library!

📌 To contribute:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/add-new-detector)
3. Commit your changes (git commit -am 'Add new model support')
4. Push to the branch (git push origin feature/add-new-detector)
5. Create a new Pull Request 🚀

📍 Contribution Ideas

• Add new YOLOv8 detectors (e.g., fire extinguisher, safety signs)
• Improve confidence filtering and logging
• Web UI integration using Streamlit or Flask
• Export results to JSON/CSV/Database

---

📝 License

This project is licensed under the MIT License. See the LICENSE file for more information.

---

Developed by @muhammadhaerul.25 "Build safer, smarter systems with AI."