Abstract: Assessment of upper extremity motor skills often involves object manipulation, drawing or writing using a pencil, or performing specific gestures. Traditional assessment of such skills usually requires a trained person to record the time and accuracy resulting in a process that can be labor intensive and costly. Automating the entire assessment process will potentially lower the cost, produce electronically recorded data, broaden the implementations, and provide additional assessment infor-mation. This paper presents a low-cost, versatile, and easy-to-use algorithm to automatically detect and track single or multiple well-defined geometric shapes or markers. It therefore can be applied to a wide range of assessment protocols that involve object manipulation or hand and arm gestures. The algorithm localizes the objects using color thresholding and morphological operations and then estimates their 3-dimensional pose. The utility of the algorithm is demonstrated by implementing it for automating the following five protocols: the sport of Cup Stacking, the Soda Pop Coordination test, the Wechsler Block Design test, the visual-motor integration test, and gesture recognition.

Beatrice Floyd and Kiju Lee. “Implementation of Vision-based Object Tracking Algorithms for Motor Skill Assessments”. International Journal of Advanced Computer Science and Applications (IJACSA) 6.6 (2015). http://dx.doi.org/10.14569/IJACSA.2015.060639

@article{Floyd2015,
title = {Implementation of Vision-based Object Tracking Algorithms for Motor Skill Assessments},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2015.060639},
url = {http://dx.doi.org/10.14569/IJACSA.2015.060639},
year = {2015},
publisher = {The Science and Information Organization},
volume = {6},
number = {6},
author = {Beatrice Floyd and Kiju Lee}
}