Calculating real world object dimensions from Kinect RGB-D image using dynamic resolution

摘要: One of the major research directions in robotic vision focuses on calculating real world size objects a scene using stereo imaging. This information can be used while decision making for robots, manipulator localization workspace, path planning and collision prevention, augmented reality, object classification images other areas that require sizes as feature. In this paper we present novel approach to calculate RGB-D image acquired from Microsoft Kinect™, an alternative imaging based approaches. We introduce dynamic resolution matrix estimates each pixel units. The main objective is convert represented pixels; units (such feet, inches etc.).We verify our results available OpenSource datasets. experimental show provides accurate measurements.