Arm Muscular Effort Estimation from Images Using Computer Vision and Machine Learning
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
- PDF / 693,080 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 11 Downloads / 200 Views
2
Laboratorio DHARMa, DeSI, Universidad Tecnol´ ogica Nacional, FRM, Mendoza, Argentina {leandro.abraham,fbromberg}@frm.utn.edu.ar CEAL, Universidad Nacional de Cuyo, Facultad de Ingenier´ıa, Mendoza, Argentina 3 Consejo Nacional de Investigaciones Cient´ıficas y T´ecnicas (CONICET), Buenos Aires, Argentina
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: Muscle arm effort histograms
1
· SVM · Random forests · LBP · Color
Introduction
Musculoskeletal system biomechanics is a scientific discipline that aims to study the mechanical structures, laws, models and phenomenons that are important to the balance and movement of humans. The biomechanical variables most studied c Springer International Publishing Switzerland 2015 J. Bravo et al. (Eds.): AmIHEALTH 2015, LNCS 9456, pp. 125–137, 2015. DOI: 10.1007/978-3-319-26508-7 13
126
L. Abraham et al.
when analyzing balance and movement are internal and external muscles forces, and joint torques. The analysis of these variables allows the identification of harmful movements, overexertions, awkward postures, musculoskeletal disorders, optimal movements, among other states of the human body that have high impact in its health and performance. This results in its application in disciplines like occupational medicine [4], ergonomics [28], and sports [16], among others. The estimation of internal muscular forces and joint torques is not made through direct measurement, but indirectly through dynamical models. These are: inverse dynamics, forward dynamics, and electrom
Data Loading...
