公开(公告)号：WO9631047A3

公开(公告)日：1996-11-07

申请号：PCT/US9604400

申请日：1996-03-29

Applicant: UNIV CALIFORNIA ,  JAIN RAMESH ,  WAKIMOTO KOJI ,  MOEZZI SAIED ,  KATKERE ARUN

Inventor： JAIN RAMESH ,  WAKIMOTO KOJI ,  MOEZZI SAIED ,  KATKERE ARUN

IPC: G06T15/10 ,  H04N5/222 ,  H04N13/00 ,  H04N

CPC classification number: H04N13/0242 ,  G05B2219/32014 ,  G06T15/10 ,  G06T2207/10012 ,  G06T2207/10021 ,  H04N5/222 ,  H04N5/2627 ,  H04N13/0014 ,  H04N13/0029 ,  H04N13/004 ,  H04N13/0051 ,  H04N13/0055 ,  H04N13/0059 ,  H04N13/0246 ,  H04N13/0257 ,  H04N13/0278 ,  H04N13/0289 ,  H04N13/0296 ,  H04N13/0431 ,  H04N13/0434 ,  H04N13/0438 ,  H04N13/044 ,  H04N13/0459 ,  H04N19/597 ,  H04N2013/0081 ,  H04N2013/0085 ,  H04N2013/0092 ,  H04N2013/0096

Abstract: Immersive video, or television, images of a real-world scene are synthesized, including on demand and/or in real time, as are linked to any of a particular perspective on the scene, or an object or event in the scene. Synthesis is in accordance with user-specified parameters of presentation, including presentations that are any of panoramic, magnified, stereoscopic, or possessed of motional parallax. The image synthesis is based on computerized video processing-called "hypermosaicing"-of multiple video perspectives on the scene. In hypermosaicing a knowledge database contains information about the scene; for example scene geometry, shapes and behaviors of objects in the scene, and/or internal and/or external camera calibration models. Multiple video cameras each at a different spatial location produce multiple two-dimensional video images of the scene. A viewer/user specifies viewing criterion (ia) at a viewer interface. A computer, typically one or more engineering work station class computers or better, includes in software and/or hardware (i) a video data analyzer for detecting and for tracking scene objects and their locations, (ii) an environmental model builder combining multiple scene images to build a 3D dynamic model recording scene objects and their instant spatial locations, (iii) a viewer criterion interpreter, and (iv) a visualizer for generating from the 3D model in accordance with the viewing criterion one or more selectively synthesized 2D video image(s) of the scene.

公开(公告)号：WO2019084007A1

公开(公告)日：2019-05-02

申请号：PCT/US2018/057111

申请日：2018-10-23

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA ,  OH, Hyungik ,  JAIN, Ramesh ,  JALALI, Laleh

Inventor： OH, Hyungik ,  JAIN, Ramesh ,  JALALI, Laleh

IPC: G06F3/01 ,  F21V13/12 ,  A61B5/02 ,  A61B5/04 ,  A61B5/11 ,  A61B5/103

Abstract: Systems and methods for tracking activities from a plurality of multimodal inputs are described. Activity tracking can include receiving a plurality of multimodal inputs, synchronizing the plurality of multimodal inputs, generating segments from the synchronized multimodal inputs, recognizing activities associated with each generated segment by performing a bagged formal concept analysis (BFCA), and recording the recognized activities in a storage. Tracking of activities can include the detection of moments (e.g., eating moments), during which an activity tracking application can prompt a user for information (e.g., a food journal).

公开(公告)号：WO1996031047A2

公开(公告)日：1996-10-03

申请号：PCT/US1996004400

申请日：1996-03-29

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA ,  JAIN, Ramesh ,  WAKIMOTO, Koji ,  MOEZZI, Saied ,  KATKERE, Arun

Inventor： THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

IPC: H04N00/00

CPC classification number: G06T15/10 ,  G05B2219/32014 ,  G06T2207/10012 ,  G06T2207/10021 ,  H04N5/222 ,  H04N5/2627 ,  H04N13/117 ,  H04N13/139 ,  H04N13/156 ,  H04N13/167 ,  H04N13/189 ,  H04N13/194 ,  H04N13/243 ,  H04N13/246 ,  H04N13/257 ,  H04N13/279 ,  H04N13/289 ,  H04N13/296 ,  H04N13/334 ,  H04N13/337 ,  H04N13/341 ,  H04N13/344 ,  H04N13/363 ,  H04N19/597 ,  H04N2013/0081 ,  H04N2013/0085 ,  H04N2013/0092 ,  H04N2013/0096

Abstract: Immersive video, or television, images of a real-world scene are synthesized (i) on demand, (ii) in real time, (iii) as linked to any of a particular perspective on the scene, or an object or event in the scene, (iv) in accordance with user-specified parameters of presentation, including panoramic or magnified presentations, and/or (v) stereoscopically. The synthesis of virtual images is based on computerized video processing -- called "hypermosaicing" -- of multiple live video perspectives on the scene. In hypermosaicing a knowledge database contains information about the scene; for example scene geometry, shapes and behaviors of objects in the scene, and/or internal and/or external camera calibration models. Multiple video cameras each at a different spatial location produce multiple two-dimensional video images of the scene. A viewer/user specifies viewing criterion (ia) at a viewer interface. A computer, typically one or more engineering work station class computers or better, includes in software and/or hardware (i) a video data analyzer for detecting and for tracking scene objects and their locations, (ii) an environmental model builder combining multiple scene images to build a 3-D dynamic model recording scene objects and their instant spatial locations, (iii) a viewer criterion interpreter, and (iv) a visualizer for generating from the 3-D model in accordance with the viewing criterion one or more particular 2-D video image(s) of the scene. A video display receives and displays the synthesized 2-D video image(s). Nonetheless to being built and maintained by use of simplifying assumptions, the 3-D dynamic model is powerful, flexible and useful in permitting diverse scene views.

Abstract translation: 沉浸式视频或电视的现实世界场景的图像（i）按需合成（ii）实时，（iii）与场景中的任何特定视角相关联，或者与场景中的对象或事件相关联 场景，（iv）根据用户指定的演示参数，包括全景或放大的演示，和/或（v）立体地。 虚拟图像的综合是基于现场视频多种视频视频的计算机视频处理 - 称为“超马赛克”。 在超镶嵌中，知识数据库包含有关场景的信息; 例如场景中的对象的场景几何，形状和行为，和/或内部和/或外部相机校准模型。 每个在不同空间位置的多个摄像机产生场景的多个二维视频图像。 观众/用户在观众界面指定观看标准（ia）。 计算机（通常是一个或多个工程工作站类计算机或更好的）包括软件和/或硬件（i）用于检测和跟踪场景对象及其位置的视频数据分析器，（ii）组合多个场景的环境模型构建器 图像以构建记录场景对象及其即时空间位置的3-D动态模型，（iii）观看者标准解释器，以及（iv）根据观看标准从3D模型生成一个或多个特定的图像 2-D视频图像的场景。 视频显示接收并显示合成的二维视频图像。 尽管如此，通过使用简化假设来构建和维护，3-D动态模型在许可场景视图中是强大，灵活和有用的。