-
公开(公告)号：US09165380B2
公开(公告)日：2015-10-20
申请号：US13834680
申请日：2013-03-15
Inventor： Eun Jin Ko , Hyun Chul Kang , Sang Wook Park , Noh-Sam Park , Mi Kyong Han , Mi Ryong Park , Jong Hyun Jang , Kwang Roh Park
IPC: G06K9/36 , G06T9/00 , H04N19/159 , H04N19/176 , H04N19/119 , H04N19/61 , H04N19/136
CPC classification number: G06T9/004 , H04N19/119 , H04N19/136 , H04N19/159 , H04N19/176 , H04N19/61
Abstract: An image encoding method using a Binary Partition Tree (BPT) includes performing the BPT on a reference frame, detecting blocks, each having a difference in a pixel value exceeding a threshold value in a current frame, based on a result of the BPT of the reference frame, and performing the BPT of the current frame on the detected blocks. In accordance with the present invention, block partition is not applied to all frames, but a partial partition method based on a difference between the pixel values of a reference frame and a current frame to be encoded is provided. Accordingly, the encoding speed within the P frame or the B frame can be improved. Furthermore, the PSNR of a corresponding frame can be maintained within a specific range of the PSNR of a reference frame, and a compression effect can be improved.
Abstract translation: 使用二进制分区树（BPT）的图像编码方法包括在参考帧上执行BPT，基于BPT的结果，检测在当前帧中具有超过阈值的像素值差异的块 参考帧，并在检测到的块上执行当前帧的BPT。 根据本发明，块分割不适用于所有帧，但是提供了基于参考帧的像素值与要编码的当前帧之间的差异的部分分割方法。 因此，可以提高P帧或B帧内的编码速度。 此外，相应帧的PSNR可以保持在参考帧的PSNR的特定范围内，并且可以提高压缩效果。
-
公开(公告)号：US11682213B2
公开(公告)日：2023-06-20
申请号：US17235537
申请日：2021-04-20
Inventor： Hyun Jin Yoon , Mi Kyong Han
IPC: G06K9/00 , G06V20/52 , G06N3/08 , G06F18/214 , G06F18/2415 , G06F18/2431 , G06V10/764 , G06V10/82 , G06V20/70
CPC classification number: G06V20/52 , G06F18/2155 , G06F18/2415 , G06F18/2431 , G06N3/08 , G06V10/764 , G06V10/82 , G06V20/70
Abstract: The present disclosure provides a method and a device for training a neural network model for use in analyzing captured images, and an intelligent image capturing apparatus employing the same. The neural network model can be trained by performing the image reconstruction and the image classification using based on image data received from a plurality of image capturing devices installed in the monitoring area, calculating at least one loss function based on data processed by the neural network model or the neural network model training device, and determining parameters minimizing the loss function. In addition, the neural network model can be updated through the re-training taking into account the newly acquired image data. Accordingly, the image analysis neural network model can operate with high precision and accuracy.
-
公开(公告)号：US10410094B2
公开(公告)日：2019-09-10
申请号：US15724118
申请日：2017-10-03
Inventor： Hyunjin Yoon , Siadari T. Suprapto , Hoon Ki Lee , Mi Kyong Han
Abstract: A method and an apparatus for authoring a machine learning-based immersive media are provided. The apparatus determines an immersive effect type of an original image of image contents to be converted into an immersive media by using an immersive effect classifier learned using an existing immersive media that the immersive effect is already added to an image, detects an immersive effect section of the original image based on the immersive effect type determination result, and generates metadata of the detected immersive effect section.
-
公开(公告)号：US11727533B2
公开(公告)日：2023-08-15
申请号：US16991689
申请日：2020-08-12
Inventor： Seok Bong Yoo , Mi Kyong Han
CPC classification number: G06T3/4076 , G06N3/04
Abstract: A method for generating a super resolution image may comprise up-scaling an input low resolution image; determining a directivity for each patch included in the up-scaled image; selecting an orientation-specified neural network or an orientation-non-specified neural network according to the directivity of the patch; applying the selected neural network to the patch; and obtaining a super resolution image by combining one or more patches output from the orientation-specified neural network and the orientation-non-specified neural network.
-
公开(公告)号：USD771735S1
公开(公告)日：2016-11-15
申请号：US29530709
申请日：2015-07-23
Designer： Yong Kwi Lee , Jong Hyun Jang , Sangwook Park , Minney Shin , Hyunjin Yoon , Mi Kyong Han
-
Patent Agency Ranking
6.发明授权公开(公告)号：US11430090B2
公开(公告)日：2022-08-30
申请号：US16987027
申请日：2020-08-06
Inventor： Seok Bong Yoo , Mi Kyong Han
Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.
-
公开(公告)号：US08891892B2
公开(公告)日：2014-11-18
申请号：US13743630
申请日：2013-01-17
Inventor： Noh-Sam Park , Sang Wook Park , Eun Jin Ko , Hyun Chul Kang , Mi Kyong Han , Jong Hyun Jang , Kwang Roh Park
CPC classification number: G06T9/004 , H04N19/124 , H04N19/154 , H04N19/176 , H04N19/61 , H04N19/85
Abstract: The present invention relates to an image encoding method using an adaptive preprocessing scheme, including loading an input image for each frame, determining an encoding type of each of the frames, determining the size of a block to be encoded in each frame according to the determined encoding type, determining blocks that can be replicated from the blocks having the determined size and performing an intra-picture replication preprocessing or inter-picture replication preprocessing procedure on the determined blocks according to the encoding types of the frames, and encoding the frames on which the preprocessing procedure has been performed.
Abstract translation: 本发明涉及一种使用自适应预处理方案的图像编码方法，包括加载每帧的输入图像，确定每个帧的编码类型，根据确定的每帧确定要编码的块的大小 编码类型，确定可以从具有确定尺寸的块中复制的块，并且根据帧的编码类型对所确定的块执行图像内复制预处理或图像间复制预处理过程，并对其进行编码 已经执行了预处理程序。
-
8.发明授权公开(公告)号：US10861221B2
公开(公告)日：2020-12-08
申请号：US16035357
申请日：2018-07-13
Inventor： Jae-Kwan Yun , Noh-Sam Park , Jong Hyun Jang , Mi Kyong Han
Abstract: Provided is a sensory effect adaptation method performed by an adaptation engine, the method including identifying first metadata associated with an object in a virtual world and used to describe the object and converting the identified first metadata into second metadata to be applied to a sensory device in a real world, wherein the second metadata is obtained by converting the first metadata based on a scene determined by a gaze of a user in the virtual world.
-
公开(公告)号：US10719741B2
公开(公告)日：2020-07-21
申请号：US15889870
申请日：2018-02-06
Inventor： Noh Sam Park , Hoon Ki Lee , Mi Kyong Han
Abstract: Disclosed is a sensory information providing apparatus. The sensory information providing apparatus may comprise a learning model database storing a plurality of learning models related to sensory effect information with respect to a plurality of videos; and a video analysis engine generating the plurality of learning models by extracting sensory effect association information by analyzing the plurality of videos and sensory effect meta information of the plurality of videos, and extracting sensory information corresponding to an input video stream by analyzing the input video stream based on the plurality of learning model.
-
公开(公告)号：US09258392B2
公开(公告)日：2016-02-09
申请号：US14086898
申请日：2013-11-21
Inventor： Mi Ryong Park , Hyun Woo Oh , Jae Kwan Yun , Mi Kyong Han , Ji Yeon Kim , Deock Gu Jee , Kwang Roh Park
CPC classification number: H04M1/0202 , G06F1/1684 , G06F1/1686 , G06F1/1694 , H04M1/72522 , H04M2250/10 , H04M2250/12 , H04M2250/52 , H04N21/4131 , H04N21/8126 , H04N21/8543
Abstract: Disclosed are a method and an apparatus for generating metadata of immersive media and disclosed also are an apparatus and a method for transmitting metadata related information. The apparatus includes: at least one of a camera module photographing or capturing the image; a gyro module sensing horizontality; a global positioning sensor (GPS) module calculating a position by receiving a satellite signal; and an audio module recording audio; and a network module receiving sensor effect information from a sensor aggregator through a wireless communication network; and an application generating metadata by performing timer-synchronization of an image photographed based on the camera module, a sensor effect collected by using the gyro module or the GPS module, or audio collected based on the audio module.
Abstract translation: 公开了用于生成沉浸式媒体的元数据的方法和装置，并且还公开了一种用于发送元数据相关信息的装置和方法。 该装置包括：照相机模块中的至少一个拍摄或拍摄图像; 感测水平度的陀螺仪模块; 全球定位传感器（GPS）模块，通过接收卫星信号来计算位置; 和音频模块录制音频; 以及网络模块，通过无线通信网络从传感器聚合器接收传感器效果信息; 以及通过执行基于相机模块拍摄的图像的定时器同步，通过使用陀螺仪模块或GPS模块收集的传感器效果或基于音频模块收集的音频来生成元数据的应用。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.012 seconds)
