专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明授权

US5732146A Scene change detecting method for video and movie 失效
标题翻译：视频和电影的场景变化检测方法
公开(公告)号：US5732146A
公开(公告)日：1998-03-24
申请号：US424016
申请日：1995-04-18
申请人： Shin Yamada , Katsuhiro Kanamori , Toshikazu Fujioka
发明人： Shin Yamada , Katsuhiro Kanamori , Toshikazu Fujioka
IPC分类号： H04N5/262 , G06T7/20 , G11B27/28 , H04N5/76 , H04N5/91 , H04N5/93 , H04N9/74 , H04N9/79 , H04N11/04 , H04N19/105 , H04N19/136 , H04N19/137 , H04N19/14 , H04N19/172 , H04N19/186 , H04N19/196 , H04N19/20 , H04N19/44 , H04N19/46 , H04N19/50 , H04N19/51 , H04N19/543 , H04N19/587 , H04N19/70 , H04N19/85 , H04N19/87 , G06K9/00
CPC分类号： G06K9/00711 , G06T7/2053 , G11B27/28 , H04N19/142 , H04N19/179 , H04N19/87
摘要： A scene change point detecting method which detects a scene change point by successively processing time series frame images I1, I2, I3, - - - sampled in this order from a processed video. The method includes at least one of the following four scene-change-point detecting methods: a first scene-change-point detecting method for detecting a video cut; a second scene-change-point detecting method for detecting a scene change similar to dissolve by processing a feature quantity to be calculated based on an edge intensity of each frame image; a third scene-change-point detecting method for detecting a scene change similar to wipe based on an intensity-changed pixel region representing a set of pixels whose brightness changes more than a predetermined threshold between a specific frame image In and an immediately preceding frame image In-1; and a fourth scene-change-point detecting method for detecting a scene change similar to page-translate or a scene change resulting from camera movement based on an intensity-changed pixel area representing a ratio of the number of pixels involved in the intensity-changed pixel region to the total number of pixels constituting a corresponding frame image.
摘要翻译：一种场景变化点检测方法，其通过依次处理从处理过的视频中按顺序采样的时间序列帧图像I1，I2，I3， - - 来检测场景变化点。该方法包括以下四个场景切换点检测方法中的至少一个：用于检测视频剪辑的第一场景切换点检测方法; 第二场景变化点检测方法，用于通过基于每个帧图像的边缘强度处理要计算的特征量来检测类似于溶解的场景变化; 第三场景变化点检测方法，用于基于强调变化的像素区域来检测类似于擦除的场景变化，所述强度变化像素区域表示亮度在特定帧图像In和紧邻的前一帧图像之间的亮度变化超过预定阈值的像素集合 In-1; 以及第四场景变化点检测方法，用于基于强度变化的像素区域来检测类似于翻译的场景变化或由相机移动导致的场景变化，强度变化的像素区域表示强度变化的像素数量的比率像素区域相对于构成相应帧图像的总像素数。

82. 发明授权

US5712928A Picture encoding method and apparatus and picture decoding method and apparatus 失效
公开(公告)号：US5712928A
公开(公告)日：1998-01-27
申请号：US568560
申请日：1995-12-07
申请人： Jun Murayama
发明人： Jun Murayama
IPC分类号： H04N19/00 , G06T9/00 , G06T9/20 , H03M7/30 , H04N1/41 , H04N19/102 , H04N19/134 , H04N19/136 , H04N19/149 , H04N19/15 , H04N19/192 , H04N19/196 , H04N19/20 , H04N19/423 , H04N19/46 , H04N19/70 , G06K9/36
CPC分类号： G06T9/20
摘要： In a picture encoding and decoding method and apparatus, an object contour can be chain coded precisely even in the case where noise exists in the vicinity of object contour, and the object contour branched off can be coded with small quantity of codes. In the case where the branched part occurs in a feature point chain, by multiplexing branch code D1 to chain codes S23 and S22 and expressing as a tree structured feature point chain including the branch part of the object contour, an increase in number of chains can be controlled and the efficient chain coding can be conducted. Moreover, since the terminal branch chains having no branch point in the chain become the objects of thresholding, only noise elements can be effectively eliminated without cutting off the feature point chain showing the object contours.

83. 发明授权

US5701368A Apparatus for encoding an image signal having a still object 失效
标题翻译：用于编码具有静止物体的图像信号的装置
公开(公告)号：US5701368A
公开(公告)日：1997-12-23
申请号：US509260
申请日：1995-07-31
申请人： Hae-Mook Jung
发明人： Hae-Mook Jung
IPC分类号： H04N11/04 , F16H7/00 , G06T9/00 , G06T9/20 , H03M7/40 , H04N1/41 , H04N19/129 , H04N19/14 , H04N19/20 , H04N19/21 , H04N19/60 , H04N19/625 , H04N19/88 , H04N19/91 , H04N19/93 , G06K9/46 , G06K9/36
CPC分类号： G06T9/20 , F16H7/00
摘要： An apparatus for encoding a digital video signal of an image based on a still object-oriented coding technique wherein the image signal is divided into a number of blocks of an identical size and pixels lying outside of the object being masked with a zero value comprises a subblock formatter for subdividing each of the blocks into 4.sup.N subblocks; 4.sup.N encoders, each of said encoders for encoding each one of the 4.sup.N subblocks to produce a block of encoded data, respectively; 4.sup.N edge detectors, each of the edge detectors for detecting a sub-object edge in said each subblock to produce an edge detection signal and for determining a pattern of the detected edge to produce an edge pattern identification signal; an interleaving block for interleaving each of the scanned data from each of said encoder to produce a stream of scanned data; and a variable length coder for coding a stream of interleaved scanned data to produce a variable length coded signal.
摘要翻译：一种用于基于静态面向对象编码技术对图像的数字视频信号进行编码的装置，其中图像信号被划分为具有相同大小的多个块，并且位于被零掩蔽的对象之外的像素包括：子块格式化器，用于将每个块细分为4N个子块; 4N编码器，每个所述编码器分别编码4N子块中的每一个以产生编码数据块; 4N边缘检测器，每个边缘检测器用于检测所述每个子块中的子对象边缘以产生边缘检测信号，并且用于确定所检测到的边缘的图案以产生边缘图案识别信号; 交织块，用于交织来自每个所述编码器的每个扫描数据以产生扫描数据流; 以及可变长度编码器，用于对交错的扫描数据流进行编码以产生可变长度编码信号。

84. 发明授权

US5635986A Method for encoding a contour of an object in a video signal by using a contour motion estimation technique 失效
标题翻译：通过使用轮廓运动估计技术对视频信号中的对象的轮廓进行编码的方法
公开(公告)号：US5635986A
公开(公告)日：1997-06-03
申请号：US672165
申请日：1996-06-27
申请人： Jin-Hun Kim
发明人： Jin-Hun Kim
IPC分类号： H04N19/20 , G06T9/00 , G06T9/20 , H03M7/30 , H04N7/24 , H04N19/423 , H04N19/50 , H04N19/51 , H04N19/543 , H04N19/59 , H04N19/60 , H04N19/61 , H04N19/91 , H04N7/36
CPC分类号： G06T9/20 , H04N19/537 , H04N19/543 , H04N19/20
摘要： A method for encoding a contour of an object predicts a current contour by using a current and a reconstructed previous contours and generates the motion vector representing a displacement between the reconstructed previous and the predicted current contours. A matched contour between the predicted current and the current contours is subtracted from the current contour to provide a differential contour. Thereafter, vertex points is determined based on a polygonal approximation for the differential contour. A set of approximation errors calculated at a predetermined number of sample points on each line segment between two vertex points is transformed and quantized to obtain a set of quantized discrete sine transform coefficients. The quantized discrete sine transform coefficients are encoded together with the motion vector, and the vertex points are encoded based on the predicted current contour for transmission thereof. And, the coded vertex information is decoded based on the predicted current contour, and the quantized discrete sine transform coefficients are converted into the reconstructed errors to reconstruct the differential contour. The reconstructed differential contour is added to the matched contour to provide the reconstructed previous contour.
摘要翻译：用于编码对象轮廓的方法通过使用当前轮廓和重建的先前轮廓来预测当前轮廓，并且生成表示重建的先前轮廓和预测的当前轮廓之间的位移的运动矢量。从当前轮廓中减去预测电流和当前轮廓之间的匹配轮廓，以提供差分轮廓。此后，基于差分轮廓的多边形近似来确定顶点。在两个顶点之间的每个线段上的预定数量的采样点处计算的一组近似误差被变换和量化以获得一组量化的离散正弦变换系数。量化的离散正弦变换系数与运动矢量一起编码，并且基于预测的当前轮廓来对顶点进行编码以进行传输。并且，基于预测的当前轮廓对编码的顶点信息进行解码，并且将量化的离散正弦变换系数转换为重构误差以重建差分轮廓。将重建的差分轮廓添加到匹配轮廓以提供重建的先前轮廓。

85. 发明授权

US11610122B2 Generative adversarial neural network assisted reconstruction 有权
公开(公告)号：US11610122B2
公开(公告)日：2023-03-21
申请号：US17143608
申请日：2021-01-07
申请人： NVIDIA Corporation
发明人： Tero Tapani Karras , Samuli Matias Laine , David Patrick Luebke , Jaakko T. Lehtinen , Miika Samuli Aittala , Timo Oskari Aila , Ming-Yu Liu , Arun Mohanray Mallya , Ting-Chun Wang
IPC分类号： G06T9/00 , G06N3/08 , H04N19/20 , H04N7/15 , G06T7/73 , G06V40/16 , G06T5/00
摘要： A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

86. 发明申请

US20230076734A1 METHOD AND SYSTEM FOR FILMING 有权
公开(公告)号：US20230076734A1
公开(公告)日：2023-03-09
申请号：US17943359
申请日：2022-09-13
申请人： Holicom Film Limited
发明人： Stephen Ley , Ian Christopher O'Connell , Bruce Finn
IPC分类号： G03B15/06 , H04N19/112 , H04N19/132 , H04N19/137 , H04N19/186 , H04N19/17 , H04N19/20 , H04N19/587 , G03B15/02 , H04N5/222 , H04N5/272 , G02B30/56 , H04N7/15 , H04N7/14 , G03B15/07
摘要： This invention concerns a method of filming a subject to be projected as a Pepper's Ghost image. The method may comprise filming a subject under a lighting arrangement having one or more front lights for illuminating a front of a subject and one or more backlights. The lights may be controlled such that the total brightness of the one or more front lights, as measured of the subject, is less than or approximately the same as the total brightness of the one or more backlights, as measured at the subject. The subject may be located directly above one or more floor lights such the subject is illuminated from below by the one or more floor lights.

87. 发明授权

US11580395B2 Generative adversarial neural network assisted video reconstruction 有权
公开(公告)号：US11580395B2
公开(公告)日：2023-02-14
申请号：US17069449
申请日：2020-10-13
申请人： NVIDIA Corporation
发明人： Tero Tapani Karras , Samuli Matias Laine , David Patrick Luebke , Jaakko T. Lehtinen , Miika Samuli Aittala , Timo Oskari Aila , Ming-Yu Liu , Arun Mohanray Mallya , Ting-Chun Wang
IPC分类号： G06T9/00 , G06N3/08 , H04N19/20 , H04N7/15 , G06T7/73 , G06V40/16 , G06T5/00
摘要： A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

88. 发明申请

US20220377355A1 METHOD FOR IDENTIFYING STATIONARY REGIONS IN FRAMES OF A VIDEO SEQUENCE 有权
公开(公告)号：US20220377355A1
公开(公告)日：2022-11-24
申请号：US17720528
申请日：2022-04-14
申请人： Axis AB
发明人： Song YUAN
IPC分类号： H04N19/20 , H04N19/176 , H04N19/12 , H04N19/167 , G06V10/22 , G06V20/40 , H04N19/139 , H04N19/157 , H04N19/182 , H04N19/103
摘要： A method for identifying stationary regions in frames of a video sequence comprises receiving an encoded version of the video sequence, wherein the encoded version of the video sequence includes an intra-coded frame followed by a plurality of inter-coded frames; reading coding-mode information in the inter-coded frames of the encoded version of the video sequence, wherein the coding-mode information is indicative of blocks of pixels in the inter-coded frames being skip-coded; finding, using the read coding-mode information, one or more blocks of pixels that each was skip-coded in a respective plurality of consecutive frames in the encoded version of the video sequence; and designating each found block of pixels as a stationary region in the respective plurality of consecutive frames.

89. 发明授权

US11490101B2 Video signal compression processor, video signal decompression processor, video signal transmission system, method of compressing video signal, and method of decompressing video signal 有权
公开(公告)号：US11490101B2
公开(公告)日：2022-11-01
申请号：US16458943
申请日：2019-07-01
申请人： Shimadzu Corporation
发明人： Hidekazu Minami
IPC分类号： H04N19/20 , G06F3/14 , H04N19/85
摘要： It is configured to include a video signal compression unit that compresses a video signal for displaying, on an image inspection monitor, an image inspection screen including a first area for displaying a medical image and a second area for displaying information other than the medical image, and a transmitting unit that transmits, via a communication network, the video signal having been compressed, and the video signal compression unit compresses, in each frame of the video signal, the second area of the image inspection screen at a compression rate higher than a compression rate of the first area.

90. 发明申请

US20220343457A1 RANK INFORMATION IN IMMERSIVE MEDIA PROCESSING 有权
公开(公告)号：US20220343457A1
公开(公告)日：2022-10-27
申请号：US17811170
申请日：2022-07-07
申请人： ZTE Corporation
发明人： Zhao WU , Ping WU
IPC分类号： G06T3/00 , H04N19/20 , G06T9/00 , H04L65/80
摘要： Methods, apparatus, and systems for providing consistent immersive media viewing experiences to user while reducing bandwidth consumption are disclosed. In one example aspect, a method for processing multimedia content includes determining, for a conversion between a frame of panoramic media content comprising multiple segments and a bitstream representation of the frame of panoramic media content, multiple sets of rank information associated with the frame. Each set of the rank information indicates a priority level for processing a segment of the frame of panoramic media content. The method also includes performing the conversion based on the multiple sets of rank information.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式