Real-time respiration rate measurement from thoracoabdominal movement with a consumer grade camera.

In this paper, we propose a novel computer vision technique to measure respiration rate by counting the periodic thoracoabdominal motion in real-time using an inexpensive consumer grade camera. We compute the component of optical flow parallel to the image gradient at each pixel, which is a computationally inexpensive operation. Then, we find a principal flow field by gathering information over many frames. Subsequently, in each frame, we compute the component of flow along this principal flow field to capture the thoracoabdominal motion. Our method is very simple, easy to implement and needs no specialized hardware. This method is computationally very efficient and can be easily implemented in mobile devices. We demonstrate the efficacy of our method on real world datasets and compare the results with those obtained using impedance pneumography.