Metadata-Version: 2.1
Name: labelaction
Version: 1.1.1
Summary: A GUI tool for annotating action in video files. 
Author: xie jiefeng
Author-email: p2417822@mpu.edu.mo
Keywords: Action label,Annotation tools,GUI
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: Unix
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Description-Content-Type: text/markdown
Requires-Dist: PyQt5>=5.15.10
Requires-Dist: opencv-python>=4.10.0
Requires-Dist: pandas>=2.2.0


# Animal Behavior Annotation Tool(labelaction)



This is a GUI-based tool for annotating animal behavior in video files. Built using Python and PyQt5, this application allows users to load a video, navigate through frames, and label different behaviors for multiple subjects (referred to as "pigeons" in this tool).



## Features



- **Simultaneous annotation of behaviors and postures**: Users can annotate both behaviors (e.g. feeding, drinking, etc.) and postures (e.g. standing, lying down, etc.) of pigeons during video playback, and each annotation can be done independently.

- **Timeline visualization**: The program provides a visual timeline for each pigeon to show the behavior and posture annotations for quick viewing and editing.



- **Video frame navigation**: the user can use buttons or shortcut keys (such as 'D' and 'S') to quickly advance or rewind video frames for easy and precise labeling.



- **Color coding**: Different behaviors and gestures are identified using different colors, making annotation more intuitive and allowing users to quickly identify information by color.



- **Export function**: Users can export annotation data to CSV file, supporting two formats: original annotation and sorted annotation data, which is convenient for subsequent data analysis and processing.



- **Multi-pigeon support**:  the program allows independent annotation of multiple pigeons for complex experimental scenarios.



## Prerequisites



- **Python** (>= 3.6)

- **Libraries**: The following libraries are required:

  - `PyQt5`

  - `OpenCV`

  - `pandas`



## License



This tool is licensed under the MIT License. Feel free to modify and use it as needed.



## Acknowledgments



- PyQt5 for the GUI and OpenCV for video processing

- GEMlab : https://www.gemlab.site



## Update log

'1.1.1' fix some bugs, add posture "Tail up" and the posture "lying down" was changed to "Squatting"



'1.1.0'    

- Supports simultaneous annotation of actions and gestures in videos.  

- Export similar to mot format, export each frame's information to csv file, replace no behavior or gesture with -1

- Optimize GUI interface and functional details to improve user usability



'1.0.2' automatically install dependent packages



'1.0.1' fix some bugs



'1.0.0' first release
