Human back

Abstract: This paper presents a tracking vision for human collaborative robot. It tracks human back and shoulder for the robot to follow a person. Obviously it would be very convenient and comfortable for us if a robot could follow us in the real world. But it is not easy to keep tracking human back even if the background image is so complex and cluttered. Thus the authors solve the problem by utilizing their robust pattern detection and identification system. It is robust against fluctuation of pattern location, size, and brightness. It contributes to robustness of the tracking that the authors choose texture of clothes and human shoulder image as template patterns to be detected and identified. Experimental results demonstrate feasibility and effectiveness of the idea.

Abstract: Faulty postures, scoliosis and sagittal plane deformities should be detected as early as possible to apply preventive and treatment measures against major clinical consequences. To support documentation of the severity of deformity and diminish x-ray exposures, several solutions utilizing analysis of back surface topography data were introduced. A novel approach to automatic recognition and localization of anatomical landmarks of the human back is presented that may provide more repeatable results and speed up the whole procedure. The algorithm was designed as a two-step process involving a statistical model built upon expert knowledge and analysis of three-dimensional back surface shape data. Voronoi diagram is used to connect mean geometric relations, which provide a first approximation of the positions, with surface curvature distribution, which further guides the recognition process and gives final locations of landmarks. Positions obtained using the developed algorithms are validated with respect to accuracy of manual landmark indication by experts. Preliminary validation proved that the landmarks were localized correctly, with accuracy depending mostly on the characteristics of a given structure. It was concluded that recognition should mainly take into account the shape of the back surface, putting as little emphasis on the statistical approximation as possible.