Electronics and Telecommunications Research Institute

Michigan State University

Information Technology University (itu)

Yong-Ju Cho

Jin-Woo Hong

Jeong-Il Seo

Jae-Gon Kim

Hayder Radha

Seong-Jun Bae

Rehan Hafiz

Jeong-Ju Yoo

Muhammad Faisal

Mohsen Ali

Kiran Misra

Usama Sadiq

Tabasher Arif

Shirish Krande

Disclosed herein are an apparatus and method for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields. The apparatus for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields includes a feature extractor for extracting a feature from an input image based on a pre-trained deep learning neural network, an information accumulation pyramid module for outputting, from the feature, at least two filter responses corresponding to receptive fields having different scales, an information change detection module for calculating an information change between the at least two filter responses, a keypoint detection module for creating a score map having a keypoint probability of each pixel based on the information change, and a continuous scale estimation module for estimating a scale of a receptive field having a biggest information change for each pixel.

Apparatus and method for detecting keypoint based on deep learning using information change across receptive fields

There is provided a channel capacity estimation method for adaptive video transmission, the method including: estimating a Bit Error Rate (BER) for a received video packet; and estimating channel capacity by using the estimated BER.

Channel capacity estimation and prediction method and apparatus for rate adaptive wireless video

A method of sharing data of a scalable video coding (SVC) file and the SVC file are provided. The SVC file includes: a scalable base track including at least one scalable layer entry each storing metadata of the at least one scalable layer; and at least one sub track generated based on the scalable base track, which includes identification information of the scalable layer that is a basis of generation of a sub track among the scalable layers and identification information of the scalable base track instead of the scalable layer entry. Accordingly, when an SVC coded content is stored as a file, it is possible to reduce a storage capacity by avoiding duplication of common data and to provide convenience when the stored content is reprocessed by allowing a relation of tracks correlated to one another to be represented.

SVC file data sharing method and SVC file thereof

Growing community of inventors

Seoul, South Korea

Yong-Ju Cho