Kabushiki Kaisha Toshiba

Microsoft Technology Licensing, LLC

Sam Johnson

Bjorn Stenger

Frank Perbet

Minh-Tri Pham

Mattias Nilsson

Roberto Cipolla

Oliver Woodford

Riccardo Gherardi

Pablo Alcantarilla

In a method of generating a three dimensional representation of a human body shape from a depth image of a clothed human subject is disclosed. The method comprises identifying at least one sample from a plurality of pre-calculated representative samples, each pre-calculated representative sample comprising a three dimensional representation of a human body shape and a corresponding depth map, by comparing the depth maps of the pre-calculated representative samples with the depth image of the clothed human subject; determining a neighbourhood of the data space of possible depth images of unclothed human body shapes from the depth map of the at least one representative sample; generating a parametric model for the human body shape from a neighbourhood of the data space of human body shapes, the neighbourhood of the data space of human body shapes corresponding to the neighbourhood of the data space of possible depth images of unclothed human body shapes; and generating the three dimensional representation of the human body shape by fitting the parametric model to the depth image of the clothed human subject.

Methods and systems for generating a three dimensional representation of a human body shape

A method of object recognition and/or registration includes receiving a point cloud, arranging the points of the point cloud into a hierarchical search tree, and determining geometric information of the points located within a region, by identifying a highest level tree nodes where all of descendent leaf nodes are contained within the region and selecting the leaf nodes for the points where no sub-tree is entirely contained within the region, such that the points falling within the region are represented by the smallest number of nodes and performing statistical operations on the nodes representing the points in the region. The geometric information includes descriptors of features in the point cloud. The method further includes comparing the feature descriptors with a database of feature descriptors for a plurality of objects.

Image analysis method by analyzing point cloud using hierarchical search tree

A user's eye gaze is corrected in a video of the user's face. Each of a plurality of templates comprises a different image of an eye of the user looking directly at the camera. Every frame of at least one continuous interval of the video is modified to replace each of the user's eyes with that of a respective template selected for that frame, whereby the user is perceived to be looking directly at the camera in the modified frames. Different templates are selected for different frames of the continuous interval so that the user's eyes exhibit animation throughout the continuous interval.

Eye gaze correction

A user's eye gaze is corrected in a video of the user's face. A facial tracking module is configured, in an active tracking mode, to track at least one angular coordinate of the user's face and to output a current value of the at least one angular coordinated that is within a range of possible values. Frames of the video are modified to correct the eye gaze of the user, whereby the user is perceived to be looking directly at the camera in the modified frames, only when the tracking module is in the active tracking mode and the current value is within a restricted subrange of the range of possible values for which the user's face is oriented towards the camera.

According to one embodiment, a method of generating a three dimensional representation of a subject from a depth image, comprises comparing a depth image of the subject with a plurality of representative images, wherein each representative image is associated with a respective parametric model of a subject; identifying a representative image of the plurality of representative images as a closest representative image to the depth image of the subject; selecting the parametric model associated with the closest representative image to the depth image; and generating a three dimensional representation of the subject by fitting the selected parametric model to the depth image of the subject.

Growing community of inventors

Cambridge, United Kingdom

Sam Johnson