Comparison of RGB-D Mapping Solutions for Application to Food Intake Monitoring

Food intake behaviours are strictly correlated to health, especially for elderly people. Dietary habits monitoring is one of the most challenging activity for researchers in AAL scenario. RGB-D sensors, such as Kinect, provide multiple useful data to perform behavioural analysis in an unobtrusive way. Unfortunately, when using the Kinect sensor, depth and RGB data are not available with the same point of view, and a mapping algorithm is required in order to associate a 3D point to the same pixel in both the RGB and depth frames. In this paper, some techniques for RGB-D mapping of Kinect sensor data are compared, and a proposed implementation is described. Some experimental results in specific conditions are finally provided.

[1]  Ennio Gambi,et al.  Quality of Kinect Depth Information for Passive Posture Monitoring , 2014 .

[2]  Takuya Maekawa,et al.  A sensor device for automatic food lifelogging that is embedded in home ceiling light: A preliminary investigation , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[3]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[4]  Gary E Fraser,et al.  Water, other fluids, and fatal coronary heart disease: the Adventist Health Study. , 2002, American journal of epidemiology.

[5]  C. Savina,et al.  Nutrition, longevity and behavior. , 2009, Archives of gerontology and geriatrics.

[6]  Juho Kannala,et al.  Joint Depth and Color Camera Calibration with Distortion Correction , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Stephen J. McKenna,et al.  User-adaptive models for recognizing food preparation activities , 2013, CEA '13.

[8]  Dieter Fox,et al.  Fine-grained kitchen activity recognition using RGB-D , 2012, UbiComp.

[9]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Janne Heikkilä,et al.  Geometric Camera Calibration Using Circular Control Points , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Quasim H. Mehdi,et al.  Monitoring of patient fluid intake using the Xbox Kinect , 2013, Proceedings of CGAMES'2013 USA.

[12]  Ennio Gambi,et al.  A Depth-Based Fall Detection System Using a Kinect® Sensor , 2014, Sensors.

[13]  Denise L. Stone,et al.  Improving the monitoring and assessment of fluid balance. , 2004, Nursing times.

[14]  Engin Mendi,et al.  Food intake monitoring system for mobile devices , 2013, 5th IEEE International Workshop on Advances in Sensors and Interfaces IWASI.

[15]  Cynthia S. Johnson,et al.  Using a mobile application to self-monitor diet and fluid intake among adults receiving hemodialysis. , 2013, Research in nursing & health.

[16]  Katie Scales,et al.  The importance of fluid balance in clinical practice. , 2008, Nursing standard (Royal College of Nursing (Great Britain) : 1987).

[17]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[18]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[19]  T. Sørensen,et al.  Food intake patterns and body mass index in observational studies , 2001, International Journal of Obesity.