@conference {168, title = {Arm muscular effort estimation from images using Computer Vision and Machine Learning}, booktitle = {1st International Conference on Ambient Intelligence for Health}, year = {2015}, month = {Dec}, address = {Puerto Varas, Chile}, abstract = {

A problem of great interest in disciplines like occupational\ medicine, ergonomics, and sports, is the measurement of biomechanical\ variables involved in human movement and balance such as internal\ muscle forces and joint torques. This problem \ is solved by a two-step process: data capturing using impractical, intrusive and expensive devices\ that is then used as input in \ complex models for obtaining the biomechanical variables of interest. In this work we present a first step towards\ capturing input \ data through a more automated, non-intrusive and economic process, specifically weight held by an arm subject to isometric\ contraction as a measure of muscular effort. We do so, by processing\ RGB images of the arm with computer vision (Local Binary Patterns\ and Color Histograms) and estimating the effort with machine learning\ algorithms (SVM and Random \ Forests). In the best case we obtained an\ FMeasure= 70.68\%, an Accuracy= 71.66\% and a mean absolute error in\ the predicted weights of 554.16 grs (over 3 possible levels of effort). Considering the difficulty of the problem , it is enlightening to achieve over\ random results indicating that, despite the simplicity of the approach,\ it is possible to extract meaningful information for the \ predictive task.\ Moreover, the simplicity of the approach suggests many lines of further\ improvements: on the image capturing \ side with other kind of images;\ on the feature extraction side with more sophisticated algorithms and\ features; and on the\ knowledge extraction side with more sophisticated\ learning algorithms.\ 

}, keywords = {color histograms, LBP, muscle arm effort, random forests, SVM}, author = {Abraham, Leandro and Bromberg, Facundo and Forradellas, Raymundo} }