%0 Computer Program
%A Butler, Rick
%D 2025
%T Code to detect human actions from history vectors
%U 
%R 10.4121/30e3b03c-6e82-47d1-a952-7dec811e71a6.v1
%K Human 2D poses
%K workflow analysis
%K action recognition
%K Workflow phase recognition
%K Group activity recognition
%K History vectors
%X <p>About 200 coronary angiograms were recorded from a distance in a cardiac catheterisation laboratory at the Reinier de Graaf Gasthuis, Delft, NL.</p><p>The purpose of the video recordings was to analyse workflow during procedures.</p><p>This Python repository aims to recognise workflow phases from human motion.</p><p>It analyses bodypart motion, human posture, and positioning with respect to other persons.</p><p>After encoding all these aspect into history vectors, it builds a mixture model for classification of new motions.</p><p>Additionally, it takes procedure duration into account.</p><p>Unfortunately, this approach proved unable to accurately classify workflow phases, so using this code for that purpose is not recommended.</p>
%I 4TU.ResearchData