This carpentries-inspired workshop is targeted at researchers working with video recordings. Even though the workshop will be based on quantitative tools, the aim is to provide solutions for qualitative research. This includes visualization techniques such as motion videos, motion history images, and motiongrams; techniques that in different ways allow for looking at video recordings from different temporal and spatial perspectives. It also includes some basic computer vision analysis, such as extracting quantity and centroid of motion, and using such features in analysis.
The participants will learn to use the Musical Gestures Toolbox for Matlab, which is a collection of high-level modules for easy generating all of the above mentioned visualizations and analyses. This toolbox was originally developed for the analysis of music-related body motion (musicians, dancers and perceivers), but is equally useful for other disciplines working with video recordings of humans, such as linguistics, pedagogics, psychology, and medicine.
This lesson has been developed by Alexander Refsum Jensenius, University of Oslo.
To begin tackling this lesson, you will need to:
- Have an interest in analyzing video recordings
- Have a laptop with (1) Matlab installed or (2) access to a server that you can run Matlab on (many universities have this).
|Setup||Download files required for the lesson|
|00:00||1. Introduction||What is a digital video file?|
|00:15||2. Getting around Matlab||How do you get set up in Matlab?|
|00:30||3. Video visualization||How can you create video visualizations in Matlab?|
|01:00||4. More visualization||Some more visualization techniques?|
|01:30||5. Preprocessing video||How is it possible to improve the video before analysing?|
|01:45||6. Advanced techniques||What more advanced features are there?|
|02:05||7. Combining video, audio and mocap||How is it possible to analyze video, audio and mocap together?|
The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.