Electronics and Telecommunications Research Institute

Hanbat National University Industry-academic Cooperation Foundation

Joung-Il Yun

Sang-Woon Kwak

Nam-Ho Hur

Hyoung-Soo Lim

Myung-Sun Baek

Hae-Chan Kwon

Young-Su Kim

Hae-Chul Choi

Won-Sik Cheong

Joon-Soo Kim

Gi-Mun Um

Nam-Shik Kim

Bi-Woong Chung

Hee-Ji Han

Disclosed herein is a method for encoding a feature map. The method may include arranging multiple channels based on similarity therebetween for a feature map having the multiple channels, rearranging the arranged multiple channels so as to be adjacent to each other in a feature map channel having a matrix form, and generating an encoded feature map by converting a feature value corresponding to the feature map channel from a real number to an integer.

Feature-map-encoding method and apparatus for encoding and decoding a feature map for a neural network

Disclosed herein is a method for adaptive image preprocessing and reconstruction. The method includes preprocessing an input image, encoding and decoding the preprocessed image, and reconstructing the encoded and decoded image. Here, preprocessing the input image may be performed using a preprocessing kernel generated based on a control parameter indicating a weight for human vision and machine vision.

Method and apparatus for adaptive image preprocessing and reconstruction

Disclosed herein are an apparatus for encoding and decoding a feature map and a method using the apparatus. The feature map encoding apparatus include a processor for acquiring feature map information corresponding to a feature map, reconstructing the feature map based on the feature map information, and generating an encoded feature map by converting each feature value corresponding to the reconstructed feature map from a real number into an integer, and a memory for storing the feature map information.

Apparatus for encoding and decoding feature map and method using the same

Disclosed herein are an image compression method and apparatus for machine vision. The image compression method includes determining a prediction mode for frames of an input image, generating a prediction frame and a residual image using an input frame, generating a reconstructed frame by adding the prediction frame to the residual image, extracting respective features of the input frame and the reconstructed frame, correcting the reconstructed frame based on a difference value between the extracted features and a bit rate of the residual image, and encoding the corrected frame.

Image compression method and apparatus for machine vision

Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.

Apparatus and method for synthesizing virtual viewpoint images

Disclosed herein are an apparatus and method for providing FTN communication using transmit diversity. A transmission apparatus generates a signal to be output through diversity modulation. A diversity order of diversity modulation may be set based on an FTN parameter, such as a variable for adjusting sampling time or a symbol transmission speed. When the diversity order is set based on the FTN parameter, the FTN parameter and the diversity order may be set so as to satisfy a QoS required of the transmission apparatus, such as a transmission rate and a Bit Error Rate. Depending on the circumstances, the set FTN parameter and diversity order may be provided to a reception apparatus that is to receive the output signal.

Method and apparatus for FTN communication using transmit diversity

Disclosed herein are an apparatus and method for receiving a signal based on FTN. The apparatus for receiving a signal based on FTN includes an equalizer for creating a Log Likelihood Ratio (LLR) sequence by equalizing an FTN signal sequence sampled at an FTN signaling rate; a deinterleaver for deinterleaving the created LLR sequence; a decoder for decoding the LLR sequence by correcting errors in the deinterleaved LLR sequence; an interleaver for interleaving the decoded LLR sequence and providing the interleaved LLR sequence to the equalizer; and an FTN interference estimation unit for providing the FTN signal sequence, from which an FTN interference sequence is eliminated, to the equalizer, using the interleaved LLR sequence.

Apparatus for receiving signal based on faster-than-Nyquist and method for using the same

Disclosed herein are a method and apparatus for iterative interference cancellation and channel estimation in a system based on FTN communication including a pilot. Interference of a pilot symbol on a data symbol is estimated, and the estimated interference is eliminated from a sequence of data symbols. When demodulation and channel decoding are performed on the sequence of data symbols, interference between data symbols and interference of a data symbol on a pilot symbol are estimated. Such estimation is repeatedly performed, and as FTN interference is repeatedly estimated and eliminated, channel estimation performance is improved, and through the improved channel estimation performance, the reception performance of the entire system is improved.

Growing community of inventors

Daejeon, South Korea

Joung-Il Yun