The beam is projected onto objects, which distort it according to their distance away from the IR source. The IR source emits a single beam that is split into a pseudo-random pattern of speckles by a diffraction grating. This technology works in a way similar to passive stereo depth sensing, but instead of using two cameras with known position and orientation, one of the cameras is replaced by an IR emitter. Kinect I evaluates distances (depth) based on structured light. → Δ t = 2 h c (time shift for incident and reflected signals)
sin π 2 - a r c t a n p f sin α + π 2 - a r c t a n p f. Π 2 - β = a r c t a n p f → β = π 2 - a r c t a n p f P-speckle location observed by the IR sensor H-unknown distance of measured point from sensor origin A comparison of the first- and second-generation devices is given, and then the influence of imaging distance, angle, and object color on sensor performance is examined to assess suitability for various medical imaging applications. This paper gives a brief overview of the latest research on healthcare imaging using Kinect. In the summer of 2014, the second generation of Kinect (Kinect II) was released, but to date most publications describe the first-generation device (Kinect I). Besides its original application in gaming, this sensor has found use in retail, education, and training, with healthcare and therapy applications under evaluation. It uses a color camera, infrared (IR) emitter, and IR sensor to compose a three-dimensional (3D) image comprising a “cloud” of over 200,000 points describing object position and surface as x, y, z coordinates. The sensor enables the user to interact in virtual reality by means of body movement, hand gestures, and spoken commands. Kinect is an input device designed for computer gaming with the XBox ® video game console. Systems such as Microsoft Kinect are significantly less expensive than most medical sensing devices, but have the potential to provide accuracy sufficient for clinical practice. Commercially available gaming systems, which provide advanced technology made available for the mass market at low cost, have thus received growing interest. Kinect I is more appropriate for short-range imaging and Kinect II is more appropriate for imaging highly curved surfaces such as the face or breast.Ĭreative approaches to healthcare are needed to cope with ageing populations and increasing economic pressure. Although Kinect is not a medical imaging device, both sensor generations show performance adequate for a range of healthcare imaging applications. The choice of object color can influence measurement range and precision. Kinect II showed significantly higher precision and Kinect I showed significantly higher resolution (both p < 0.001). Kinect I is capable of imaging at shorter measurement distances, but Kinect II enables structures angled at over 60° to be evaluated. Both sensors demonstrated high accuracy (majority of measurements <2 mm) and precision (mean point to plane error <2 mm) at an average resolution of at least 390 points per cm 2. #Xbox kinect sensor skin#
The accuracy, precision, and resolution of 3D images generated with Kinect I and Kinect II are evaluated using flat cardboard models representing different skin colors (pale, medium, and dark) at distances ranging from 0.5 to 1.2 m and measurement angles of up to 75°. The performance of Kinect I, based on structured light technology, is compared with that of the more recent Kinect II, which uses time-of-flight measurement, under conditions relevant to healthcare applications. The suitability of available technologies for healthcare imaging applications is assessed. Recent applications of Kinect in health monitoring, screening, rehabilitation, assistance systems, and intervention support are reviewed here.
Microsoft Kinect is a three-dimensional (3D) sensor originally designed for gaming that has received growing interest as a cost-effective and safe device for healthcare imaging.
0 kommentar(er)
