Skip to main content

Short description of your package

Project description

🧭 S.A.M.P.A.H.

Spatial Annotation Mapping Platform for Alignment & Heading
A general-purpose image annotation tool with support for directional labeling.


📝 Overview

S.A.M.P.A.H. is a lightweight image labeling application built for annotating not just the presence of objects — but their orientation. It enables annotators to label an object's heading direction using an 8D compass-style system, in addition to bounding boxes or segmentation.

Whether you're labeling vehicles, humans, animals, or other directional objects, S.A.M.P.A.H. provides an intuitive interface to mark both position and direction with precision.


🧭 8D Compass Annotation

S.A.M.P.A.H. introduces a novel directional labeling system based on 8 compass directions:

          N
       NW   NE
     W    ●    E
       SW   SE
          S

Each object annotation can be tagged with one of the following directions:

  • N (North) back B
  • NE (Northeast) Back-Right BR
  • E (East) right R
  • SE (Southeast) front-right FR
  • S (South) front F
  • SW (Southwest) front-left FL
  • W (West) left L
  • NW (Northwest) back-left BL

This is ideal for tasks involving:

  • Object orientation (e.g., which way a person or vehicle is facing)
  • Motion prediction
  • Pose estimation (simplified)

🚀 Features

  • 📦 Label images with bounding boxes or masks
  • 🧭 Add an 8-direction compass heading to each object
  • 🧠 Supports class-based object labeling
  • 💾 Saves annotations in Pascal VOC format (XML), with added direction tag
  • 🌐 Simple Flask + HTML interface — run locally with no installation overhead

📂 Annotation Format

S.A.M.P.A.H. saves annotations in a modified Pascal VOC XML format, with an extra <direction> tag inside each object block:

<object>
    <name>front</name>
    <bndbox>
        <xmin>123</xmin>
        <ymin>85</ymin>
        <xmax>200</xmax>
        <ymax>160</ymax>
    </bndbox>
</object>

🛠️ Getting Started git

git clone https://github.com/yourname/sampah
cd sampah
pip install -r requirements.txt
python app.py

Then, open your browser to http://127.0.0.1:5000.

🛠️ Getting Started via PIP

pip install sampah sampah

Then, open your browser to http://127.0.0.1:5000.


🔮 Coming Soon

  • Multi-object tracking
  • Custom compass (16D ~ Deg)
  • Export to COCO format with direction support
  • Integrated model-assisted annotation (YOLO/ViT)

🧑‍💻 Author

Built by [Your Name]
For questions, email [you@example.com]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sampah-0.1.2-py3-none-any.whl (14.5 kB view details)

Uploaded Python 3

File details

Details for the file sampah-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: sampah-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 14.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.8

File hashes

Hashes for sampah-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 8816e11801d461530078004a3df722743d21490e898984f054f613e8bca1e125
MD5 2e6007ac71820ad712d09ebd90f3cddf
BLAKE2b-256 53385693184cda01059102ee2a21f7cfaa3a9179200043da5aef49131f046412

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page