Overview of Features

  Content-Aware Scene Detection

    Detects breaks in-between content, not only when the video fades to black (although a threshold mode is available as well for those cases).

  Compatible With Many External Tools

    The detected scene boundaries/cuts can be exported in a variety of formats, with the default type (comma-separated HH:MM:SS.nnn values) being ready to copy-and-paste directly into other tools (such as ffmpeg, mkvmerge, etc...) for splitting and/or re-encoding the video.

  Statistical Video Analysis

    Can output a spreadsheet-compatible file for analyzing trends in a particular video file, to determine the optimal threshold values to use with specific scene detection methods/algorithms.

  Extendible and Embeddable

    Written in Python, and designed with an easy-to-use and extendable API, PySceneDetect is ideal for embedding into other programs, or to implement custom methods/algorithms of scene detection for specific applications (e.g. analyzing security camera footage).

Features in Current Release

  • exports list of scenes to .CSV file (both timecodes and frame numbers) (-o scenelist.csv)
  • exports timecodes in mkvmerge format: HH:MM:SS.nnnnn, comma-separated
  • statistics/analysis mode to export frame-by-frame video metrics (-s statsfile.csv)
  • output-suppression (quiet) mode for better automation with external scripts/programs
  • user-selectable subsampling for improved performance (-df)
  • user-selectable frame skipping for improved performance (-fs)
  • save an image of the first and last frame of each detected scene (-si)
  • ability to specify starting/ending times (-st/-et), and/or set duration for processing (-dt)
  • user-definable fade bias (-fb) to shift scenes between fade in/out points (threshold mode only)

List of Scene Detection Methods

  • threshold scene detection (-d threshold): analyzes video for changes in average frame intensity/brightness
  • content-aware scene detection (-d content): based on changes between frames in the HSV color space

For a detailed explanation of how a particular scene detection method/algorithm works, see the Scene Detection Method Details Section in the Documentation & Reference.


Version Roadmap

Features in Development for Next Version

The following are features being planned or developed after the release of v0.3.5:

  • additional timecode formats
  • adaptive bias for fade in/out interpolation
  • multithreaded implementation of detection algorithms for improved performance

Planned Features for Future Releases

The following are features being planned or developed for future releases of PySceneDetect (v0.4 and onwards):

  • export scenes in chapter/XML format
  • improve robustness of content-aware detection by combining with edge detection (similar to MATLAB-based scene change detector)
  • automatic threshold detection for the current scene detection methods (can be done in pre-pass if necessary)
  • standalone distribution/build for Windows (x86/64)
  • GUI for easier previewing and threshold setting (will be GTK+ 3 based via PyGObject)