Abstract: A method of real-time tracking of an object includes capturing a first and a second image of the object. The object is detected in the first image and movement of the object is tracked between the images. Tracking of the object includes obtaining an initial pose of the camera; projecting an image of a model object onto the second image; determining a gradient profile of the second image from an edge point of the model object along a first direction that is normal to the edge of the model object; computing a radius on the gradient profile; determining a rank order of the peaks of the gradient profile along the radius; comparing the rank order with a predetermined rank order to generate a feature candidate point; and reducing a distance along the first direction between the feature candidate point and the edge point on the edge of the model object.

Abstract: A method for producing parametric maps using a magnetic resonance imaging (MRI) system is provided. The MRI system is used to acquire k-space data from a field-of-view. A series of images is reconstructed from the acquired k-space data, and a confidence map is produced using the k-space data. The confidence map depicts regions in the field-of-view that are affected by error sources. A parametric map is produced using the reconstructed series of images and the produced confidence map. Values in the parametric map associated with regions in the field-of-view depicted in the confidence map as being affected by error sources are not computed, thereby reducing errors in the parametric map.

Abstract: A system for editing a digital image comprises a low pass filter for receiving a source image and for filtering high spatial frequency components of the source image to generate a smoothed image. An arithmetic operator unit subtracts color values of the smoothed image from color values of the source image to produce a first image value on pixel-by-pixel basis. A gradient reversal analyzer compares gradient values of the smoothed image to gradient values of the source image and generates a control signal. A boost controller generates a new value for each pixel of a boost parameter map according to the control signal. The boost controller applies the boost parameter map to modify the first image value to generate a second image value. The arithmetic operator unit is further configured to generate an edge enhanced image according to color values of the source image and the second image value.

Abstract: A method for image data compression of a to-be-encoded image block includes: determining one of a plurality of preset encoding modes as an encoding mode based upon attributes of pixels of the to-be-encoded image block; and compressing image data of the to-be-encoded image block according to the encoding mode thus determined so as to obtain encoded data.