A 3D machine vision method for non-invasive assessment of respiratory function

Background Respiratory function testing is important for detecting and monitoring illness, however, it is difficult for some patients, such as the young and severely ill, to perform conventional tests that require cooperation and/or patient contact. Method A new method was developed for non-contact breathing measurement, employing photometric stereo to capture the surface topography of the torso of an unconstrained subject. The surface is integrated to calculate time-dependent volume changes during respiration. Results The method provides a useful means of continuously measuring volume changes during respiration with high spatial and temporal resolution. The system was tested by comparison with pneumotachometry equipment and a clear periodic signal, of a frequency corresponding to the reference data, was observed. Conclusion The approach is unique in performing breathing monitoring (with potential diagnostic capability) for unconstrained patients in virtually any lighting conditions (including darkness during sleep) and in a noncontact, unobtrusive (i.e. using imperceptible light) fashion. Copyright (C) 2015 John Wiley & Sons, Ltd.