Kwangwoon University Industry-academic Collaboration Foundation

Other

5motion Inc.

Yesh Company Co., Ltd.

Young Ho Seo

Byung Seo Park

Kyung Jin Kim

Dong Wook Kim

Eui Seok Hwang

Moon Seok Oh

Provided is a virtual costume fitting system including: a data input unit that receives a three-dimensional (3D) body model and a costume model; a corresponding point matching unit that matches corresponding points between the body model and the costume model; a costume deformation unit that moves a vertex of the costume model; a pose estimation unit that estimates a pose of the body model; a texture mapping unit that maps a texture of the costume model; a crease surface generation unit that generates a crease of a costume; a texture upgrading unit that updates a texture of the crease; a costume model renewal unit that corrects the texture; a mesh separation unit that separates a 3D mesh; and a mesh integrating unit that integrates the body model with the deformed costume model to generate a body model fitted with the costume.

Virtual costume fitting system

Proposed is a full-body integrated motion capture method capable of integrally detecting joints for full-body motion capture by extracting body joints of a body from a low-resolution multiview video, detecting face and hand regions through the body joints, and precisely extracting detailed joints for a face and a hand from a high-resolution video of the face and hand regions. The full-body integrated motion capture method includes: (a) receiving a multiview color-depth video and a high-resolution video; (b) extracting a body skeleton from the low-resolution video; (c) detecting face and hand regions by using joints of a neck and a wrist of the body skeleton; (d) extracting a detailed joint from a region of the high-resolution video corresponding to the face and hand regions; and (e) generating motion data by integrating a body joint and the detailed joint.

Full-body integrated motion capture method

Proposed is a multi-view camera-based iterative calibration method for generation of a 3D volumetric model that performs calibration between cameras adjacent in a vertical direction for a plurality of frames, performs calibration while rotating with the results of viewpoints adjacent in the horizontal direction, and creates a virtual viewpoint between each camera pair to repeat calibration. Thus, images of various viewpoints are obtained using a plurality of low-cost commercial color-depth (RGB-D) cameras. By acquiring and performing the calibration of these images at various viewpoints, it is possible to increase the accuracy of calibration, and through this, it is possible to generate a high-quality real-life graphics volumetric model.

Multi-view camera-based iterative calibration method for generation of 3D volume model

Disclosed is a method of generating a volume hologram using a point cloud and a mesh, in which a weight is given to a brightness of a light source according to a direction of a light in order to record a hologram of better quality. The method includes: (a) acquiring multi-view depth and color images; (b) generating point cloud data of a three-dimensional object from the acquired multi-view depth and color images; (c) generating mesh data of the three-dimensional object from the point cloud data of the three-dimensional object; (d) calculating a normal vector of each mesh from the mesh data of the three-dimensional object; (e) extracting three-dimensional data at a user viewpoint from the mesh data of the three-dimensional object by using the normal vector of the mesh; and (f) generating hologram data from three-dimensional data at the user viewpoint.

Method of generating volume hologram using point cloud and mesh

Disclosed is a skeleton-based dynamic point cloud estimation system for sequence compression, capable of generating a three-dimensional skeleton and a motion vector thereof from a group of point cloud frames to estimate a point cloud of a next frame, and compressing a point cloud sequence by obtaining a residual between the estimated point cloud and an original point cloud. Since the point cloud is estimated by using the motion vector of the skeleton, and the sequence is compressed by using a difference from an original value as the residual, an amount of point clouds to be input to a compressor is significantly reduced, so that compression efficiency is improved.

Skeleton-based dynamic point cloud estimation system for sequence compression

Proposed is a three-dimensional skeleton generation method using calibration based on a joint acquired from a multiview camera, capable of extracting a partial skeleton of each viewpoint from a distributed RGB-D camera, calculating a camera parameter by using a joint of each partial skeleton as a feature point, and integrating each partial skeleton into a three-dimensional skeleton based on the parameter. The three-dimensional skeleton generation method includes: (a) acquiring a multiview color-depth video; (b) generating a three-dimensional skeleton of each viewpoint from a color-depth video of each viewpoint, and generating a joint of the skeleton of each viewpoint as a feature point; (c) performing extrinsic calibration for optimizing an extrinsic parameter by using the joint of the skeleton of each viewpoint; and (d) aligning and integrating the three-dimensional skeleton of each viewpoint by using the extrinsic parameter.

Method for generating 3D skeleton using joint-based calibration acquired from multi-view camera

The present invention relates to a power generating device using an electric furnace, and more particularly, to a power generating device using an electric furnace in which the electric furnace boils water using electricity to produce steam and a turbine is operated using the steam to produce electricity. The power generating device using an electric furnace according to the present invention includes an electric furnace, a steam pipe, a turbine, a power generator, a condenser, and a super-heater. The electric furnace heats water to produce steam. The steam pipe guides the steam ejected from the electric furnace. The turbine is disposed at an inlet of the steam pipe, and is operated with the steam. The power generator is operated by the turbine, and generates electricity. The condenser condenses the steam discharged after the turbine is operated. The super-heater superheats a condensate condensed in the condenser, and supplies the superheated condensate to the electric furnace. According to the present invention, it is possible to generate electricity by boiling water in an electric furnace to produce steam using midnight electric power. Accordingly, it is possible to generate electricity without causing problems such as pollution and environment destruction occurring in thermal power generation or nuclear power generation.

Growing community of inventors

Seoul, South Korea

Young Ho Seo