Nokia Corporation

Midea Group Co., Ltd.

Seetatech (beijing) Technology Co., Ltd.

Nokia Technologies Oy

Xiujuan Chai

Hao Wang

Kongqiao Wang

Kun Yu

Yikai Fang

Junyang Zhou

Kong Qiao Wang

Zhuang Liu

Shiguang Shan

Zixuan Yang

Dahai Yu

Xilin Chen

Embodiments provide a process to identify one or more areas containing a hand or hands of one or more subjects in an image. The detection process can start with coarsely locating one or more segments in the image that contain portions of the hand(s) of the subject(s) in the image using a coarse CNN. The detection process can then combine these segments to obtain the one or more areas capturing the hand(s) of the subject(s) in the image. The combined area(s) can then be fed to a grid-based deep neural network finely detect area(s) in the image that contain only the hand(s) of the subject(s) captured.

Coarse-to-fine hand detection method using deep neural network

A computer interface may use touch- and non-touch-based gesture detection systems to detect touch and non-touch gestures on a computing device. The systems may each capture an image, and interpret the image as corresponding to a predetermined gesture. The systems may also generate similarity values to indicate the strength of a match between a captured image and corresponding gesture, and the system may combine gesture identifications from both touch- and non-touch-based gesture identification systems to ultimately determine the gesture. A threshold comparison algorithm may be used to apply different thresholds for different gesture detection systems and gesture types.

Interaction using touch and non-touch gestures

A method for providing hand segmentation for gesture analysis may include determining a target region based at least in part on depth range data corresponding to an intensity image. The intensity image may include data descriptive of a hand. The method may further include determining a point of interest of a hand portion of the target region, determining a shape corresponding to a palm region of the hand, and removing a selected portion of the target region to identify a portion of the target region corresponding to the hand. An apparatus and computer program product corresponding to the method are also provided.

Method, apparatus and computer program product for providing hand segmentation for gesture analysis

A method for providing adaptive gesture analysis may include dividing a distance range into a plurality of depth ranges, generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame, determining motion variation between the two image frames for each corresponding depth range, and determining depth of a target based at least in part on the motion variation. An apparatus and computer program product corresponding to the method are also provided.

Method, apparatus and computer program product for providing adaptive gesture analysis

Growing community of inventors

Beijing, China

Xiujuan Chai