呼吸率测量.ppt

Respiratory rate detection algorithm based on RGB-D camera Introduction 1 System Configuration 2 Respiratory Rate Detection 3 Experimental Results 4 Conclusion 5 Contents CONTENTS INTRODUCTION RGB-D camera 01 Traditional measure devices require a direct contact with the person to be monitored, and may interfere with the natural respiration activity (e.g. stress, unease). To overcome this limitation, non-invasive devices are required instead. BACKGROUND ” “ In this Letter, the RGB-D camera is used as a sensor, which provides the needed information to be processed by the proposed algorithm and to measure the respiratory rate of a sitting person in an indoor environment. THE PRINCIPLE ” “ Based on depth image sensing techniques, the respiratory rate is derived by measuring morphological changes of the chest wall. The algorithm identifies the human chest, computes its distance from the camera and compares this value with the instantaneous distance, discerning if it is due to the respiratory act or due to a limited movement of the person being monitored. ” “ System Configuration Hardware And Software 02 RGB-D Structured Light (SL) cameras are sensing systems that capture RGB images along with per-pixel depth information. In detail, RGB-D SL cameras project a known pattern onto the scene or subject of interest, and the distortion in the project pattern encodes the depth information of the scene or object. HARDWARE ” “ The principle of SL cameras is that, given a specific angle between emitter and sensor, the depth can be recovered from triangulation. An SL camera is composed of an infrared (IR) projector, a diffraction grating and a standard CMOS detector with a band-pass filter centred at the IR light wavelength. HARDWARE ” “ Open Natural Interaction (Open NI) is used to implement further functionalities of the vision sensor. Open NI is a multi-language and multi-platform framework that defines the API for writing applications that use natural interaction, This API h