Skip to main content

A GUI tool for annotating action in video files.

Project description

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

Update log

'1.1.4' Updated the review function. Now you can see the bounding box and corresponding ID, behavior and posture of each pigeon in the video area.

'1.1.3' Add some functionality

  • Support undo when marking, press ctrl+z.

  • Click the annotated area of ​​the status bar to display the annotated information, such as the start frame, end frame, etc.

  • Support annotation review and modification

  • Print annotate operation log to the console

'1.1.2' Modify the behavior list and posture list

'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

Project details


Download files

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

Source Distribution

labelaction-1.1.4.tar.gz (12.1 kB view details)

Uploaded Source

File details

Details for the file labelaction-1.1.4.tar.gz.

File metadata

  • Download URL: labelaction-1.1.4.tar.gz
  • Upload date:
  • Size: 12.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.4

File hashes

Hashes for labelaction-1.1.4.tar.gz
Algorithm Hash digest
SHA256 d47b93339374fa8f71790d0c94052617ba9f25e9a07daf43e77ae1190f9a62de
MD5 39e8763b33e378d75d1b669398598fd1
BLAKE2b-256 f6cb155fa5bf74a63b93525826abf32bf650e828497e948a5b0ad1237a2c3bdd

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