Electronics and Telecommunications Research Institute

Other

Industry-university Cooperation Foundation Hanyang University

The Industry & Academic Cooperation in Chungnam National University

Hee Kyung Lee

Gi Mun Um

Seong Yong Lim

Whoi Yul Kim

Jeong Il Seo

Jeongil Seo

Hyun Cheol Kim

Won Sik Cheong

Hyun Uk Park

Yong Ju Cho

Ji Hun Cha

Joo Myoung Seok

Hoon Jo

Joung Il Yun

Sangwoo Ahn

Seung Jun Yang

Soon-heung Jung

Dae-Young Song

Dong Chan Cho

In Jae Lee

Donghyeon Cho

Injae Lee

A deep learning-based image stitching method and apparatus are provided. The deep learning-based image stitching method includes receiving a plurality of images including a first image and a second image stitched to the first image, extracting a feature map of the plurality of images, generating a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map, generating a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively, generating a plurality of weight maps for blending the plurality of warping images, based on the feature map, and generating a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps.

Deep learning-based image stitching method and apparatus

Disclosed herein is a method of creating an image stitching workflow including acquiring 360-degree virtual reality (VR) image parameters necessary to makes a request for image stitching and create the image stitching workflow, acquiring a list of functions applicable to the image stitching workflow, creating the image stitching workflow based on functions selected from the list of functions, determining the number of media processing entities necessary to perform tasks configuring the image stitching workflow and generating a plurality of media processing entities according to the determined number of media processing entities, and allocating the tasks configuring the image stitching workflow to the plurality of media processing entities.

Method and apparatus for providing 360 stitching workflow and parameter

Provided is a parallax minimization stitching method and apparatus using control points in an overlapping region. A parallax minimization stitching method may include defining a plurality of control points in an overlapping region of a first image and a second image received from a plurality of cameras, performing a first geometric correction by applying a homography to the control points, defining a plurality of patches based on the control points, and performing a second geometric correction by mapping the patches.

Parallax minimization stitching method and apparatus using control points in overlapping region

A decorative article comprises a base plate having at least one hanging elongate slot defined therein; and a receiving member including a single first plate, at least two second plates, and a hanger, wherein the first plate is parallel to the base plate, and each of the at least two second plates is non-parallel to the base plate and is coupled to the first plate, to define an inner space and a top opening in the receiving member, wherein the hanger protrudes from the first plate, wherein the hanger is fitted into the hanging elongate slot to secure the receiving member to the base plate.

Decorative article with receiving member

Provided is a gaze tracking apparatus for a user wearing a vision aid, the apparatus including a lighting element unit including a first infrared lighting element and a second infrared lighting element to radiate an infrared light to a user, an image acquirer to acquire an eye image of the user, the eye image including a first corneal reflection light, a second corneal reflection light, a first lens reflection light, and a second lens reflection light, and a processor to turn off the second infrared lighting element when interference occurs between the second lens reflection light and the first corneal reflection light in the acquired eye image, and to compute a gaze position of the user based on user calibration information, and coordinates of the first corneal reflection light.

Method of acquiring gaze information irrespective of whether user wears vision aid and moves

A gaze tracking apparatus and method are provided that may calculate a three-dimensional (3D) position of a user using at least two wide angle cameras, may perform panning, tilting, and focusing based on position information of the user and eye region detection information, using a narrow angle camera, may detect pupil center information and corneal reflected light information from an eye image acquired through an operation of the narrow angle camera, and may finally calculate gaze position information from the pupil center information and the corneal reflected light information.

Apparatus and method for eye tracking

Growing community of inventors

Daejeon, South Korea

Hee Kyung Lee