视频对象平面相关的专利数据

序号	专利名	申请号	申请日	公开（公告）号	公开（公告）日	发明人
1	视频中平面对象的重绘方法、电子设备和介质	CN202211178223.8	2022-09-26	CN115880167A	2023-03-31	潘志宏; 卢大明; 陈曦
提供了一种由计算机设备的至少一个处理器执行的视频重绘方法、电子设备和介质。该方法包括：接收具有一个或多个图像帧的视频序列；在所述一个或多个图像帧中检测目标对象的存在，并确定检测到的目标对象的姿态状况和风格转变；通过向针对所述一个或多个图像帧的替换对象施加相应的姿态状况和风格转变，来生成表示所述替换对象的内容；以及利用生成的内容对所述一个或多个图像帧中的所述目标对象进行重绘。
2	一种基于运动对象的视频图像平面转立体处理方法	CN201110028543.0	2011-01-26	CN102075777B	2015-02-11	罗莎莎; 刘纹高; 张登康; 邵诗强; 付东
本发明提供一种基于运动对象的视频图像平面转立体处理方法，包括以下步骤：A.获取视频中连续场景的起始帧和结束帧；B.获取该连续场景的背景模型图；C.获取背景模型图的深度图作为深度参考帧；D.从起始帧开始逐帧进行处理，将对比帧与背景模型图进行匹配对比，提取运动对象图形；E.获取运动对象图形的深度图；F.将运动对象图形的深度图与深度参考帧进行合成生成新的深度帧。上述方法使得对于视频中的连续场景进行处理时，只需要人工绘制该连续场景中的一帧深度图，就能够通过计算机或处理软件对该连续场景进行自动2D转3D处理，节省人力并提高处理效率。
3	一种基于运动对象的视频图像平面转立体处理方法	CN201110028543.0	2011-01-26	CN102075777A	2011-05-25	罗莎莎; 刘纹高; 张登康; 邵诗强; 付东
本发明提供一种基于运动对象的视频图像平面转立体处理方法，包括以下步骤：A.获取视频中连续场景的起始帧和结束帧；B.获取该连续场景的背景模型图；C.获取背景模型图的深度图作为深度参考帧；D.从起始帧开始逐帧进行处理，将对比帧与背景模型图进行匹配对比，提取运动对象图形；E.获取运动对象图形的深度图；F.将运动对象图形的深度图与深度参考帧进行合成生成新的深度帧。上述方法使得对于视频中的连续场景进行处理时，只需要人工绘制该连续场景中的一帧深度图，就能够通过计算机或处理软件对该连续场景进行自动2D转3D处理，节省人力并提高处理效率。
4	Synchronization of multiple video object planes	EP01104247.0	1997-07-03	EP1111934B1	2001-10-24	Tan, Thiow Keng; Shen, Sheng Mei; Lee, Chak Joo

5	Image content region reconfiguration data messages and methods therefor	EP06012100.1	2002-05-06	EP1701547A1	2006-09-13	Abdesselem, Ouelid; Cendon-Martin, Bruno; Garani, Pradeep
A data message including a region definition and in some embodiments a region shape attribute specifying a region shape corresponding to at least one region defined in the data message. In some embodiments, the data message includes a link type attribute, and a link origin attribute specifying a link origin. The link type attribute specifies a link shape extending from the link origin to a corresponding region. The data message enables displaying of first image information within a first region (610) and second image information within a second region (620), wherein the second region may relate to the first region with a link shape (630).
6	Method and apparatus for encoding object information of a video object plane	EP97121183.4	1997-12-02	EP0921684B1	2005-11-02	Han, Seok-Won, c/o Video Research Center

7	Method and apparatus for encoding object information of a video object plane	EP97121183.4	1997-12-02	EP0921684A1	1999-06-09	Han, Seok-Won, c/o Video Research Center
A method for encoding a video signal including a video object plane(VOP) and object information thereof, the VOP having an object therein, divides the VOP into a plurality of blocks and detecting boundary blocks and object blocks, wherein each boundary block includes therein background pixels and object pixels and each object block includes therein object pixels only, the background and the object pixels representing pixels residing outside and inside the object, respectively. Then the object information is converted into a set of object symbols and each object symbol is added to a background pixel included in a boundary block to thereby produce processing blocks, the processing blocks including the object blocks and one or more processed boundary blocks having therein the object symbols and the remaining unprocessed boundary blocks. The processing blocks are encoded to thereby generate an encoded video signal.
8	Image content region reconfiguration, data messages and methods therefor	EP02291138.2	2002-05-06	EP1361757A1	2003-11-12	Abdesselem, Ouelid; Cendon-Martin, Bruno; Garani, Pradeep
A data message including a region definition and in some embodiments a region shape attribute specifying a region shape corresponding to at least one region defined in the data message. In some embodiments, the data message includes a link type attribute, and a link origin attribute specifying a link origin. The link type attribute specifies a link shape extending from the link origin to a corresponding region. The data message enables displaying of first image information within a first region (610) and second image information within a second region (620), wherein the second region may relate to the first region with a link shape (630).
9	영상객체평면의객체정보부호화방법및장치	KR1019970071297	1997-12-20	KR1019990051878A	1999-07-05	한석원
영상 객체 평면(VOP:video object plane) 및 그 객체 정보를 포함하는 영상 신호를 부호화하는 방법에 있어서, VOP는 객체를 포함하고 있을 때, 본 발명은 VOP를 다수 개의 블럭들로 나누고, 배경 화소가 객체 외부에 위치한 화소이고 객체 화소가 객체 내부에 위치한 화소일 때, 배경 화소만을 포함하는 배경 블럭과 객체 화소만을 포함하는 객체 블럭 및 배경 화소와 객체 화소를 모두 포함하는 경계 블럭을 각각 찾아낸다. 그런 다음, 객체 정보를 객체 심볼 세트로 변환하고, 각각의 객체 심볼을 경계 블럭에 포함된 배경 화소에 더하여 처리 블럭들을 생성하며, 이때 생성되는 처리 블럭들은 객체 블럭과 객체 심볼을 포함하는 하나 이상의 처리된 경계 블럭들 및 남아있는 미처리 경계 블럭들을 포함하는 데, 이러한 처리 블럭들을 부호화하여 부호화된 영상 신호를 생성함으로써 객체 정보의 양이 많은 영상 신호의 부호화 효율을 개선할 수 있는 것이다.
10	인터레이스드 디지털 비디오를 위한 비디오 객체면의 동작 추정 및 보상	KR1019980007628	1998-03-07	KR1019980080012A	1998-11-25	로버트오.에이프리그; 쑤에민첸; 아재이루스라
동작 추정 및 보상기술은 VOP와 같은 인터레이스드 디지털 비디오에 제공된다. 현재 필드코드 매크로블록을 차별적으로 엔코딩하는데에 이용하기 위한 프레딕터 동작벡터는 주위의 블록 또는 매크로블록 동작벡터의 매디언을 이용함으로써 얻어진다. 주위의 매크로블록 자체가 인터레이스드 코드화될 경우, 매크로블록에 평균동작벡터는 반픽셀로 맵되는 소수픽셀 값과 함께 사용된다. 현재 블록이 인터레이스드 코드화되는 것이 아니라 주위의 블록이 인터레이스드 코드화될 때, 필드 동작벡터는 개별적으로 또는 평균화되어 이용된다. 인터레이스드 코드화 VOP를 위한 반복패딩기술에 있어서, VOP와 주위의 블록의 짝수 및 홀수라인은 그룹화 된다. 각 필드내에 외부픽셀은 가장 가까운 경계픽셀의 값으로 세팅함으로써 패드된다. 라인은 단일 패드된 기준 VOP 화상을 제공하도록 그 때 재정렬된다.
11	Method and apparatus for encoding object information of a video object plane	US984030	1997-12-02	US6125142A	2000-09-26	Seok-Won Han
A method for encoding a video signal including a video object plane(VOP) and object information thereof, the VOP having an object therein, divides the VOP into a plurality of blocks and detecting boundary blocks and object blocks, wherein each boundary block includes therein background pixels and object pixels and each object block includes therein object pixels only, the background and the object pixels representing pixels residing outside and inside the object, respectively. Then the object information is converted into a set of object symbols and each object symbol is added to a background pixel included in a boundary block to thereby produce processing blocks, the processing blocks including the object blocks and one or more processed boundary blocks having therein the object symbols and the remaining unprocessed boundary blocks. The processing blocks are encoded to thereby generate an encoded video signal.
12	用於交錯數位視訊之視訊物件平面之運動預估及補償	TW087103126	1998-03-04	TW373409B	1999-11-01	羅伯特O.艾依佛格; 愛潔盧沙; 程素明
一種提供有移動預估及補償技術係於諸如視訊物件平面(VOPs)的交錯數位影像例，用以不同地編碼一目前圖場編碼巨區塊的預測器移動向量係使用周圍區塊或巨區塊之移動向量的該中間值而獲得。當一周圍巨區塊的本身是交錯編碼的時候，那巨區塊的一平均的移動向量便會與映射至半圖素的少量圖素值同時使用。當該目前區塊並非是交錯編碼而是一周圍區塊的時候，該圖場移動向量便可個別地使用或平均，在一交錯編碼VOP的重複裝填技術中，VOP及周圍區塊的偶數和奇數線條會聚集。在每一欄位中，外部圖素係藉著將它們設定成最接近邊界圖素的值，或設定成定兩邊界圖素的一平均而被裝填。該等線條然後會重新排列，以提供一單獨的裝填參考VOP影像。
13	供視頻物件平面之時間及空間可定標編碼	TW087107902	1998-05-21	TW406512B	2000-09-21	陳修明; 亞傑露莎; 甘尼栩雷正; 曼黛揚娜拉辛漢
本發明提供一種包括輸入數值視頻次序中視頻物件平面(VOPS)的視頻影像之時間及空間定標。編碼效率經由適當壓縮定標欄模式視頻獲得改善，增強層中向上取樣VOP經重排而獲得與直線規範為基礎的輸入視頻次序之間較大的關係。最後餘數使用空間轉換如DCT加以編碼。增強層 VOPS的編碼使用一種由定標移動向量決定基層VOPS的移動補償設計，提供縮小的搜尋範圍，其中心由定標移動向量決定。移動補償設計適合定標框模式或欄模式視頻使用。各種不同處理機構造都會達成特別的可定標編碼結果，可定標編碼的應用包括立體視頻，圖中圖，預覽存取頻道及ATM通信。
14	Method and apparatus for generating chrominance shape information of a video object plane in a video signal	EP96306170.0	1996-08-23	EP0806871A3	2000-05-24	Kim, Jong-Il, Video Research Center
An apparatus generates chrominance shape information based on luminance shape information represented by binary values, to thereby describe an object in a video object plane effectively. The apparatus divides the luminance shape information into a multiplicity of sample blocks, a sample block including 2 x 2 pixels, and determines, for each sample block, a chrominance value based on all logic values in a sample block. The chrominance shape information is produced in a form of a matrix based on the chrominance values for all sample blocks.
15	Method and apparatus for generating chrominance shape information of a video object plane in a video signal	EP96306170.0	1996-08-23	EP0806871A2	1997-11-12	Kim, Jong-Il, Video Research Center
An apparatus generates chrominance shape information based on luminance shape information represented by binary values, to thereby describe an object in a video object plane effectively. The apparatus divides the luminance shape information into a multiplicity of sample blocks, a sample block including 2 x 2 pixels, and determines, for each sample block, a chrominance value based on all logic values in a sample block. The chrominance shape information is produced in a form of a matrix based on the chrominance values for all sample blocks.
16	Method and apparatus for generating chrominance shape information of a video object plane in a video signal	EP96306170.0	1996-08-23	EP0806871B1	2006-06-21	Kim, Jong-Il, Video Research Center

17	Temporal and spatial scaleable coding for video object planes	US869493	1997-06-05	US06057884A	2000-05-02	Xuemin Chen; Ajay Luthra; Ganesh Rajan; Mandayam Narasimhan
Temporal and spatial scaling of video images including video object planes (VOPs) in an input digital video sequence is provided. Coding efficiency is improved by adaptively compressing scaled field mode video. Upsampled VOPs in the enhancement layer are reordered to provide a greater correlation with the input video sequence based on a linear criteria. The resulting residue is coded using a spatial transformation such as the DCT. A motion compensation scheme is used for coding enhancement layer VOPs by scaling motion vectors which have already been determined for the base layer VOPs. A reduced search area whose center is defined by the scaled motion vectors is provided. The motion compensation scheme is suitable for use with scaled frame mode or field mode video. Various processor configurations achieve particular scaleable coding results. Applications of scaleable coding include stereoscopic video, picture-in-picture, preview access channels, and ATM communications.
18	用於交錯數位視訊之雙向預測視訊物件平面之預測及編碼	TW087103123	1998-03-04	TW362334B	1999-06-21
一種諸如雙向預測視訊物件平面(B-VOPs)的數位視訊影像編碼之系統，特別是，其中該B-VOP及用來編碼B-VOP的一參考影像係交錯編碼。對於與一將來圖畫之圖場預測 B-VOP巨區塊而言，直接模式預測係藉由計算四個圖場移動向量而產生，然後產生預測巨區塊。四個圖場移動向量及它們的參考圖場是從下面四項而決定(1)該目前巨區塊之編碼向量的一補償、(2)兩將來的圖場移動向量、(3)由該同時存在之將來巨區塊之兩圖場移動向量所使用的參考圖場、及(4)在圖場期間，在該等目前B-VOP圖場及該圖場之間的該暫時空間。此外，該目前MB的一編碼模式決定處理會選取一向前、向後、或平均圖場編碼模式，其係根據最小之絕對差(SAD)錯誤的總數而選取，而此絕對差錯誤是在該目前MB的頂端及底部圖場上獲得。
19	Motion estimation and compensation of video object planes for interlaced digital video	US10028007	2001-12-20	USRE38564E1	2004-08-10	Robert O. Eifrig; Xuemin Chen; Ajay Luthra
A motion estimation and compensation technique is provided for interlaced digital video such as video object planes (VOPs). Predictor motion vectors for use in differentially encoding a current field coded macroblock are obtained using the median of motion vectors of surrounding blocks or macroblocks. When a surrounding macroblock is itself interlaced coded, an average motion vector for that macroblock is used, with fractional pixel values being mapped to the half-pixel. When the current block is not interlaced coded but a surrounding block is, the field motion vectors may be used individually or averaged. In a repetitive padding technique for an interlaced coded VOP, the even and odd lines of the VOP and surrounding block are grouped. Within each field, exterior pixels are padded by setting them to the value of the nearest boundary pixel, or to an average of two boundary pixels. The lines are then reordered to provide a single padded reference VOP image.
20	Motion estimation and compensation of video object planes for interlaced digital video	US301141	1999-04-28	US6026195A	2000-02-15	Robert O. Eifrig; Xuemin Chen; Ajay Luthra
A motion estimation and compensation technique is provided for interlaced digital video such as video object planes (VOPs). Predictor motion vectors for use in differentially encoding a current field coded macroblock are obtained using the median of motion vectors of surrounding blocks or macroblocks. When a surrounding macroblock is itself interlaced coded, an average motion vector for that macroblock is used, with fractional pixel values being mapped to the half-pixel. When the current block is not interlaced coded but a surrounding block is, the field motion vectors may be used individually or averaged. In a repetitive padding technique for an interlaced coded VOP, the even and odd lines of the VOP and surrounding block are grouped. Within each field, exterior pixels are padded by setting them to the value of the nearest boundary pixel, or to an average of two boundary pixels. The lines are then reordered to provide a single padded reference VOP image.

1 2 3 4 5 6 7 8 9 10

IPRDB

热门服务

关于我们

友情链接

联系方式