Skip to main content

🤖 Galaxy Object Detection Core

Welcome to the Galaxy Object Detection Core — a modular, production-ready object detection library built using YOLO and YOLOWorld 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

  • ✅ 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
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)

Fast-Moving Consumer Goods

  • detect_product_fmcg(image_path: str)
  • 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."

Metadata

Release files for galaxy-object-detection-core 0.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for galaxy-object-detection-core 0.1.5
File Size Uploaded Provenance Actions
galaxy_object_detection_core-0.1.5.tar.gz 25.1 MB Without provenance Details for galaxy_object_detection_core-0.1.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for galaxy-object-detection-core 0.1.5
File Interpreter ABI Platform Actions
galaxy_object_detection_core-0.1.5-py3-none-any.whl Python 3 none any Details for galaxy_object_detection_core-0.1.5-py3-none-any.whl

Total release size: 50.3 MB

Release files / galaxy_object_detection_core-0.1.5.tar.gz

Download URL galaxy_object_detection_core-0.1.5.tar.gz
Size 25.1 MB
Tags Source
SHA-256 checksum
How to use checksums
0b9290120ac562357d45d28ceee9b3fc8a0f6f1ec706ee25e2a1e83b6d729a18
BLAKE2b-256 checksum
How to use checksums
614b1d88758a8d712d758a31ce2cdd4b0afbf908391c844e0505f51f4b48da95
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.10

Release files / galaxy_object_detection_core-0.1.5-py3-none-any.whl

Download URL galaxy_object_detection_core-0.1.5-py3-none-any.whl
Size 25.1 MB
Tags Python 3
SHA-256 checksum
How to use checksums
5842fd7baf9f07d1fa752969ed7ff1809b1b414bc72735190a169641662faa25
BLAKE2b-256 checksum
How to use checksums
487386623c07034dc46adcceb53a79c4bfab4508eae43090b9b735e669df8a01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.10

Security for galaxy-object-detection-core 0.1.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page