Seiko Epson Corporation

Mirza Tahir Ahmed

Dibyendu Mukherjee

Yang Yang

Jie Wang

Andrei Mark Rotenstein

Qadeer Baig

Yan He

A method of using both object features and scene features to track an object in a scene is provided. In one embodiment, the scene motion is compared with the object motion and if the motions differ greater than a threshold, then the pose from object tracker is used; otherwise, the pose from scene tracker is used. In another embodiment, the pose of an object is tracked by both scene tracker and object tracker and these poses are compared. If these comparison results in a difference greater than a threshold, the pose from object tracker is used; otherwise, the pose from scene tracker is used.

Moving object tracking using object and scene trackers

A non-transitory computer readable medium storing instructions to cause one or more processors to acquire an image data sequence containing images of an object in a scene along time and track a pose of the object through an object pose tracking algorithm. The processor may further, acquire a first pose of the object in a first image of the image data sequence, the first pose being a result of tracking a pose of the object through an object pose tracking algorithm, verify the first pose, extract 2D features of the object from the first image when the first pose is verified, and store a training dataset containing the extracted 2D features and the corresponding verified first pose in the one or more memories or other one or more memories.

Online learning for 3D pose estimation using simplified constellations

An operation detection method of detecting an operation of a pointing element with respect to an operation surface includes converting first and second taken image obtained by imaging the operation surface into first and second converted taken image calibrated with respect to the operation surface respectively, determining whether or not the pointing element contacts with the operation surface and is in a resting state based on the first and second converted taken image, selecting the first and second converted taken image at when it was determined that the pointing element contacts and to be in the resting state as first and second reference image, calculating a first difference in position between the pointing element in the first reference image and the pointing element in the first converted taken image, calculating a second difference in position between the pointing element in the second reference image selected and the pointing element in the second converted taken image, and determining whether or not the pointing element separated from the operation surface based on the first difference and the second difference.

Two camera touch operation detection method, device, and system

A non-transitory computer readable medium embodies instructions that cause one or more processors to perform a method. The method includes: (A) receiving, in one or more memories, a 3D model corresponding to an object, and (B) setting a depth sensor characteristic data set for a depth sensor for use in detecting a pose of the object in a real scene. The method also includes (C) generating blurred 2.5D representation data of the 3D model for at least one view around the 3D model based on the 3D model and the depth sensor characteristic data set, to generate, on the basis of the 2.5D representation data, training data for training an object detection algorithm, and (D) storing the training data in one or more memories.

Growing community of inventors

Vaughan, Canada

Mirza Tahir Ahmed