公开(公告)号：US20230035307A1

公开(公告)日：2023-02-02

申请号：US17565901

申请日：2021-12-30

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  INFORMATION TECHNOLOGY UNIVERSITY (ITU)

Inventor： Yong-Ju CHO ,  Jeong-Il SEO ,  Rehan HAFIZ ,  Mohsen ALI ,  Muhammad FAISAL ,  Usama SADIQ ,  Tabasher ARIF

IPC: G06V10/77 ,  G06V10/82 ,  G06V10/44 ,  G06T3/40

Abstract: 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.

公开(公告)号：US20220207672A1

公开(公告)日：2022-06-30

申请号：US17318828

申请日：2021-05-12

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jeong-Il SEO ,  Hyon-Gon CHOO

IPC: G06T5/20 ,  H04N5/235 ,  G06T5/00 ,  G06T5/50

Abstract: Disclosed herein are an apparatus and method for sensing an image based on an event. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform acquiring at least one of brightness information and color information from an input image signal, performing conversion including at least one of filtering of at least one of the acquired brightness information and color information, color conversion, and brightness conversion, calculating a quantized difference between a first converted image converted from the currently input image signal and a second converted image converted from a previously input image signal, and generating event information for the input image signal as a bitstream based on the quantized difference.

公开(公告)号：US20130132098A1

公开(公告)日：2013-05-23

申请号：US13732682

申请日：2013-01-02

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung-Kwon BEACK ,  Jeong-Il SEO ,  Tae-Jin LEE ,  Yong-Ju LEE ,  Dae-Young JANG ,  Jin-Woo HONG ,  Jin-Woong KIM ,  Kyeong-Ok KANG

IPC: G10L19/008

CPC classification number: G10L19/008 ,  G10L19/0017 ,  G10L19/173 ,  H04S3/002 ,  H04S7/30 ,  H04S2400/11 ,  H04S2420/03

Abstract: Provided is an apparatus and method for coding and decoding multi-object audio signals with various channels and providing backward compatibility with a conventional spatial audio coding (SAC) bitstream. The apparatus includes: an audio object coding unit for coding audio-object signals inputted to the coding apparatus based on a spatial cue and creating rendering information for the coded audio-object signals, where the rendering information provides a coding apparatus including spatial cue information for audio-object signals; channel information of the audio-object signals; and identification information of the audio-object signals, and used in coding and decoding of the audio signals.

Abstract translation: 提供了一种用于利用各种信道对多对象音频信号进行编码和解码并提供与常规空间音频编码（SAC）比特流的向后兼容性的装置和方法。 该装置包括：音频对象编码单元，用于基于空间提示对输入到编码装置的音频对象信号进行编码，并创建用于编码的音频对象信号的再现信息，其中，所述再现信息提供包括用于 音频对象信号; 音频对象信号的信道信息; 以及音频对象信号的识别信息，并用于音频信号的编码和解码。

公开(公告)号：US20210392376A1

公开(公告)日：2021-12-16

申请号：US17446091

申请日：2021-08-26

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jeong-Il SEO ,  Wook-Joong KIM ,  Kyu-Heon KIM ,  Kyeong-Ok KANG ,  Jin-Woo HONG ,  Yung-Lyul LEE ,  Ki-Hun HAN ,  Jae-Ho HUR ,  Dong-Gyu SIM ,  Seoung-Jun OH

IPC: H04N19/61 ,  H04N19/159 ,  H04N19/176 ,  H04N19/129

Abstract: Provided is an apparatus and method for encoding/decoding a moving picture based on adaptive scanning. The moving picture apparatus and method can increase a compression rate based on adaptive scanning by performing intra prediction onto blocks of a predetermined size, and scanning coefficients acquired from Discrete Cosine Transform (DCT) of a residue signal and quantization differently according to the intra prediction mode. The moving picture encoding apparatus includes: a mode selector for selecting and outputting a prediction mode; a predictor for predicting pixel values of pixels to be encoded of an input video based on the prediction mode to thereby output a residue signal block; a transform/quantization unit for performing DCT onto the residue signal block and quantizing the transformed residue signal block; and an encoder for adaptively scanning and encoding the quantized residue signal block based on the prediction mode.

公开(公告)号：US20200154142A1

公开(公告)日：2020-05-14

申请号：US16744384

申请日：2020-01-16

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jeong-Il SEO ,  Wook-Joong Kim ,  Kyu-Heon Kim ,  Kyeong-OK Kang ,  Jin-Woo Hong ,  Yung-Lyul Lee ,  Ki-Hun Han ,  Jae-Ho Hur ,  Dong-Gyu Sim ,  Seoung-Jun Oh

IPC: H04N19/61 ,  H04N19/129 ,  H04N19/176 ,  H04N19/159

Abstract: Provided is an apparatus and method for encoding/decoding a moving picture based on adaptive scanning. The moving picture apparatus and method can increase a compression rate based on adaptive scanning by performing intra prediction onto blocks of a predetermined size, and scanning coefficients acquired from Discrete Cosine Transform (DCT) of a residue signal and quantization differently according to the intra prediction mode. The moving picture encoding apparatus includes: a mode selector for selecting and outputting a prediction mode; a predictor for predicting pixel values of pixels to be encoded of an input video based on the prediction mode to thereby output a residue signal block; a transform/quantization unit for performing DCT onto the residue signal block and quantizing the transformed residue signal block; and an encoder for adaptively scanning and encoding the quantized residue signal block based on the prediction mode.

公开(公告)号：US20190215633A1

公开(公告)日：2019-07-11

申请号：US16356410

申请日：2019-03-18

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seung-Kwon BEACK ,  Jeong-Il SEO ,  Dae-Young JANG ,  Tae-Jin LEE ,  Yong-Ju LEE ,  Jin-Woo HONG ,  Jin-Woong KIM

IPC: H04S7/00 ,  G10L19/008

CPC classification number: H04S7/30 ,  G10L19/008 ,  H04S2400/11

Abstract: The present research relates to controlling rendering of multi-object or multi-channel audio signals. The present research provides a method and apparatus for controlling rendering of multi-object or multi-channel audio signals based on spatial cues in a process of decoding the multi-object or multi-channel audio signals. To achieve the purpose, the method suggested in the research controls rendering in a spatial cue domain in the process of decoding the multi-object or multi-channel audio signals.

公开(公告)号：US20190110078A1

公开(公告)日：2019-04-11

申请号：US16216551

申请日：2018-12-11

Applicant: Electronics and Telecommunications Research Institute ,  Kwangwoon University Research Institute for Industry Cooperation ,  Industry Academy Cooperation Foundation of Sejong University

Inventor： Jeong-Il SEO ,  Wook-Joong KIM ,  Kyu-Heon KIM ,  Kyeong-Ok KANG ,  Jin-Woo HONG ,  Yung-Lyul LEE ,  Ki-Hun HAN ,  Jae-Ho HUR ,  Dong-Gyu SIM ,  Seoung-Jun OH

IPC: H04N19/61 ,  H04N19/129 ,  H04N19/159 ,  H04N19/176

CPC classification number: H04N19/61 ,  H04N19/129 ,  H04N19/159 ,  H04N19/176

Abstract: Provided is an apparatus and method for encoding/decoding a moving picture based on adaptive scanning. The moving picture apparatus and method can increase a compression rate based on adaptive scanning by performing intra prediction onto blocks of a predetermined size, and scanning coefficients acquired from Discrete Cosine Transform (DCT) of a residue signal and quantization differently according to the intra prediction mode. The moving picture encoding apparatus includes: a mode selector for selecting and outputting a prediction mode; a predictor for predicting pixel values of pixels to be encoded of an input video based on the prediction mode to thereby output a residue signal block; a transform/quantization unit for performing DCT onto the residue signal block and quantizing the transformed residue signal block; and an encoder for adaptively scanning and encoding the quantized residue signal block based on the prediction mode.

公开(公告)号：US20220398699A1

公开(公告)日：2022-12-15

申请号：US17839181

申请日：2022-06-13

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hyon-Gon CHOO ,  Jeong-Il SEO ,  Jin-Young LEE ,  Hee-Kyung LEE ,  Han-Shin LIM ,  Won-Sik CHEONG

IPC: G06T5/00

Abstract: Disclosed herein are an image processing method and apparatus for machine vision. The image processing method for machine vision includes generating an image with machine-unrecognizable distortion based on an input image, and encoding the image with machine-unrecognizable distortion.

公开(公告)号：US20210218973A1

公开(公告)日：2021-07-15

申请号：US17219985

申请日：2021-04-01

Applicant: Electronics and Telecommunications Research Institute ,  Kwangwoon University Research Institue for Industry Cooperation ,  Industy-Academia Cooperation Group of Sejong University

Inventor： Se-Yoon JEONG ,  Hae-Chul CHOI ,  Jeong-Il SEO ,  Seung-Kwon BEACK ,  In-Seon JANG ,  Jae-Gon KIM ,  Kyung-Ae MOON ,  Dae-Young JANG ,  Jin-Woo HONG ,  Jin-Woong KIM ,  Yung-Lyul LEE ,  Dong-Gyu SIM ,  Seoung-Jun OH ,  Chang-Beom AHN ,  Dae-Yeon KIM ,  Dong-Kyun KIM

IPC: H04N19/159 ,  H04N19/91 ,  H04N19/182 ,  H04N19/13 ,  H04N19/18 ,  H04N19/176 ,  H04N19/129 ,  H04N19/61 ,  H04N19/11 ,  H04N19/103 ,  H04N19/136

Abstract: The present invention discloses an encoding apparatus using a Discrete Cosine Transform (DCT) scanning, which includes a mode selection means for selecting an optimal mode for intra prediction; an intra prediction means for performing intra prediction onto video inputted based on the mode selected in the mode selection means; a DCT and quantization means for performing DCT and quantization onto residual coefficients of a block outputted from the intra prediction means; and an entropy encoding means for performing entropy encoding onto DCT coefficients acquired from the DCT and quantization by using a scanning mode decided based on pixel similarity of the residual coefficients.

公开(公告)号：US20140074487A1

公开(公告)日：2014-03-13

申请号：US14081471

申请日：2013-11-15

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jeong-Il SEO ,  Seung-Kwon BEACK ,  In-Seon JANG ,  Dae-Young JANG ,  Jin-Woo HONG ,  Jin-Woong KIM

IPC: G10L19/008

CPC classification number: G10L19/008 ,  G10L19/02 ,  G10L19/18

Abstract: Provided is a method for controlling synchronizing downmix signals and MPEG surround side information signals by controlling a delay according to the kind of downmix audio signals in an MPEG surround decoder. When multi-channel audio signals are restored using an HE-AAC decoder and a low-power MPEG surround decoder and complex QMF signals outputted from the HE-AAC decoder are used as downmix signals, a delay unit compensates for a delay caused in a real-to-complex converter. Anther delay unit delays spatial parameters to compensate for a delay caused in QMF and Nyquist banks when time-domain downmix signals are used. Also, when multi-channel audio signals are restored using an HE-AAC decoder and a high-quality MPEG surround decoder and complex QMF signals outputted from the HE-AAC decoder are used as downmix signals, a delay unit compensates for a delay caused in a real-to-complex converter.

Abstract translation: 提供了一种通过根据MPEG环绕解码器中的下混音频信号的种类来控制延迟来控制同步下混信号和MPEG环绕侧信息信号的方法。 当使用HE-AAC解码器和低功率MPEG环绕解码器来恢复多声道音频信号时，使用从HE-AAC解码器输出的复杂QMF信号作为下混合信号，延迟单元补偿实际产生的延迟 复合转换器。 花时延单元延迟空间参数以补偿在使用时域降混信号时在QMF和奈奎斯特银行中引起的延迟。 此外，当使用HE-AAC解码器和高质量MPEG环绕解码器恢复多声道音频信号并且将从HE-AAC解码器输出的复杂QMF信号用作下混合信号时，延迟单元补偿由 一个真实到复杂的转换器。