中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.012 seconds)

    SYSTEM AND A METHOD FOR DEPTH-IMAGE-BASED RENDERING
    1.
    发明申请
    SYSTEM AND A METHOD FOR DEPTH-IMAGE-BASED RENDERING 有权
    系统和基于深度图像渲染的方法

    公开(公告)号：US20160379341A1

    公开(公告)日：2016-12-29

    申请号：US14753015

    申请日：2015-06-29

    Applicant: Politechnika Poznanska

    Inventor： Marek Domanski ,  Tomasz Grajek ,  Damian Karwowski ,  Krzysztof Klimaszewski ,  Olgierd Stankiewicz ,  Jakub Stankowski ,  Krzysztof Wegner

    IPC: G06T5/00 ,  G06T7/00 ,  G06T15/00

    CPC classification number: G06T5/002 ,  G06T7/593 ,  G06T15/00 ,  G06T2207/10012 ,  H04N13/111 ,  H04N2213/005

    Abstract: A method for depth-image-based rendering, the method comprising the steps of: obtaining a first reference view; obtaining a depth map for the first reference view; obtaining a second reference view; obtaining a depth map for the second reference view; the method further comprising the steps of extracting noise present in the first and the second reference views; denoising the first and the second reference views and, based on the denoised first and second reference views, rendering an output view using depth-image-based rendering; adding the extracted noise to the output view.

    Abstract translation: 一种用于基于深度图像的渲染的方法，所述方法包括以下步骤：获得第一参考视图; 获取第一参考视图的深度图; 获得第二参考视图; 获取第二参考视图的深度图; 该方法还包括以下步骤：提取存在于第一和第二参考视图中的噪声; 去噪第一和第二参考视图，并且基于去噪的第一和第二参考视图，使用基于深度图像的渲染来呈现输出视图; 将提取的噪声添加到输出视图。

    METHOD AND SYSTEM FOR ANALYZING HUMAN BEHAVIOR IN AN INTELLIGENT SURVEILLANCE SYSTEM
    3.
    发明申请
    METHOD AND SYSTEM FOR ANALYZING HUMAN BEHAVIOR IN AN INTELLIGENT SURVEILLANCE SYSTEM 审中-公开
    在智能监控系统中分析人类行为的方法和系统

    公开(公告)号：US20150213308A1

    公开(公告)日：2015-07-30

    申请号：US14215101

    申请日：2014-03-17

    Applicant: POLITECHNIKA POZNANSKA

    Inventor： Slawomir MACKOWIAK ,  Lukasz KAMINSKI ,  Krzysztof KOWALAK ,  Pawel GARDZINSKI ,  Lukasz JANUSZKIEWICZ

    IPC: G06K9/00 ,  G06T7/20

    CPC classification number: G06K9/00335 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30232 ,  G06T2207/30241 ,  G08B13/19613

    Abstract: A method for analyzing behavior in an intelligent surveillance system, the system being operable to provide a series of consecutive images of an area under surveillance for consecutive time points, the method comprising the steps of: for each image of the series, generating a set of points defining at least one moving silhouette on an image; tracing the position of points in the sets of points on consecutive images in order to generate trajectories of points; providing a database of predefined trajectories corresponding to behavior; comparing the generated trajectories of points for said moving silhouette with database records; outputting information regarding the type of predefined behavior said moving silhouette corresponds to.

    Abstract translation: 一种用于分析智能监视系统中的行为的方法，所述系统可操作以提供连续时间点的被监视区域的一系列连续图像，所述方法包括以下步骤：对于该系列的每个图像，生成一组 定义图像上至少一个移动轮廓的点; 跟踪连续图像中的点集合中的点的位置，以生成点的轨迹; 提供与行为相对应的预定轨迹的数据库; 将生成的所述运动轮廓的点的轨迹与数据库记录进行比较; 输出关于所述运动剪影对应的预定行为类型的信息。

    Fault-tolerant data processing computer system and method for implementing a distributed two-tier state machine
    4.
    发明授权
    Fault-tolerant data processing computer system and method for implementing a distributed two-tier state machine 有权

    公开(公告)号：US10135929B2

    公开(公告)日：2018-11-20

    申请号：US14995211

    申请日：2016-01-14

    Applicant: POLITECHNIKA POZNANSKA

    Inventor： Pawel Tomasz Wojciechowski ,  Tadeusz Kobus ,  Maciej Kokocinski

    IPC: G06F15/16 ,  H04L29/08 ,  G06F11/18 ,  G06F11/14 ,  G06F11/20

    Abstract: A fault-tolerant data processing computer system and method for implementing a distributed two-tier state machine aimed for distributed (replicated) data stores, in which consistency is maintained despite the failure of any number of replicas and communication paths. In the distributed two-tier state machine, one process (device) in a network of processes (devices) is chosen as the leader, and that leader is responsible for executing functions that return state machine commands, and for broadcasting the commands to the other processes. The processes execute the commands in the logical precedence order that corresponds to the order of function executions that return these commands. The system and method ensures that each of the processes issues exactly the same sequence of commands for execution, such that each command in the sequence, except the first one, has a precedent command on which the command logically depends.

    METHOD FOR PREDICTIVE CODING OF DEPTH MAPS AND A DEPTH MAP ENCODER
    5.
    发明申请
    METHOD FOR PREDICTIVE CODING OF DEPTH MAPS AND A DEPTH MAP ENCODER 有权
    深度编码和深度编码器的预测编码方法

    公开(公告)号：US20160381387A1

    公开(公告)日：2016-12-29

    申请号：US14753011

    申请日：2015-06-29

    Applicant: Politechnika Poznanska

    Inventor： Marek Domanski ,  Tomasz Grajek ,  Damian Karwowski ,  Krzysztof Klimaszewski ,  Olgierd Stankiewicz ,  Jakub Stankowski ,  Krzysztof Wegner

    IPC: H04N19/593 ,  H04N19/176 ,  H04N19/136

    CPC classification number: H04N19/593 ,  H04N19/136 ,  H04N19/176 ,  H04N19/597

    Abstract: A method for predictive encoding of a depth map, comprising the steps of: receiving a depth map; dividing the depth map to blocks; performing quad-tree decomposition of the depth map to sub-blocks; approximating each of the sub-blocks by a plane, the plane being associated with three plane points (p0, p1, p2); providing an encoded depth map in a form of a set of planes defined by parameters. The method further comprises: determining an order of coding of the sub-blocks; and while encoding consecutive sub-blocks: calculating predictors ({circumflex over (p)}0, {circumflex over (p)}1, {circumflex over (p)}2) for the plane points (p0, p1, p2) of the currently-encoded sub-block (C); calculating differences (Δp0, Δp1, Δp2) between the actual values of the plane points (p0, p1, p2) and the values of the corresponding predictors ({circumflex over (p)}0, {circumflex over (p)}1, {circumflex over (p)}2); providing the parameters of the plane for the currently-encoded sub-block (C) in form of the differences (Δp0, Δp1, Δp2).

    Abstract translation: 一种用于深度图的预测编码的方法，包括以下步骤：接收深度图; 将深度图划分为块; 将深度图的四叉树分解执行到子块; 通过平面近似每个子块，该平面与三个平面点（p0，p1，p2）相关联; 以由参数定义的一组平面的形式提供编码深度图。 该方法还包括：确定子块的编码顺序; 同时编码连续子块：对于平面点（p0，p1，p2），计算预测变量（{circumflex over（p）} 0，{circumflex over（p）} 1，{circumflex over（p）} 2） 当前编码的子块（C）; 计算平面点（p0，p1，p2）的实际值与相应预测值（{circumflex over（p）} 0，{circumflex over（p）} 1的值之间的差异（Δp0，Δp1，Δp2） （p）}（2）; 以差分（Δp0，Δp1，Δp2）的形式为当前编码的子块（C）提供平面的参数。

    Method for processing wide angle images with barrel distortion and a surveillance system
    6.
    发明授权
    Method for processing wide angle images with barrel distortion and a surveillance system 有权
    用桶形失真和监视系统处理广角图像的方法

    公开(公告)号：US09413927B2

    公开(公告)日：2016-08-09

    申请号：US13964114

    申请日：2013-08-12

    Applicant: POLITECHNIKA POZNANSKA

    Inventor： Adam Luczak ,  Slawomir Mackowiak

    IPC: H04N5/217 ,  H04N7/18 ,  G06T3/00 ,  G06T5/00

    CPC classification number: H04N5/217 ,  G06T3/0062 ,  G06T5/006 ,  G06T2207/10004 ,  G06T2207/20021 ,  G06T2207/20104 ,  G06T2207/30232 ,  H04N5/23238 ,  H04N7/18

    Abstract: A computer-implemented method for processing a distorted wide angle image with barrel distortion to obtain a plurality of reconstructed images, characterized in that it comprises the steps of: determining, on the basis of a mapping function representing the distortion of the distorted image, a reconstruction function representing the position of points (r0) of reconstructed image as a function of position of points (r1) on the distorted image, determining a plurality of viewing angles (α1, α2, α3), for each viewing angle (α1, α2, α3), generating a reconstructed image comprising points of the distorted image comprised within the particular viewing angle (α1, α2, α3) and reconstructed using the reconstruction function, such that each reconstructed image has its central point corresponding to the same point of the distorted image.

    Abstract translation: 一种用于处理具有桶形失真的失真广角图像以获得多个重建图像的计算机实现的方法，其特征在于，其包括以下步骤：基于表示失真图像的失真的映射函数，确定 表示重建图像的点（r0）的位置的重建函数，作为在失真图像上的点（r1）的位置的函数，对于每个视角（α1，α2）确定多个视角（α1，α2，α3） ，α3），生成包括在所述特定视角（α1，α2，α3）内的所述失真图像的点并使用所述重建功能重构的重构图像，使得每个重建图像的中心点对应于所述重建图像的相同点 扭曲的图像。

    SYSTEM AND A METHOD FOR TRACKING OBJECTS
    9.
    发明申请
    SYSTEM AND A METHOD FOR TRACKING OBJECTS 有权
    系统和跟踪对象的方法

    公开(公告)号：US20160275695A1

    公开(公告)日：2016-09-22

    申请号：US14664862

    申请日：2015-03-22

    Applicant: POLITECHNIKA POZNANSKA

    Inventor： Adam LUCZAK ,  Slawomir MACKOWIAK ,  Marek DOMANSKI ,  Jakub SIAST ,  Tomasz GRAJEK

    IPC: G06T7/20 ,  G06K9/46 ,  G06K9/00

    CPC classification number: G06T7/285 ,  G06K9/00771 ,  G06K9/4642 ,  G06T7/248 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20021 ,  G06T2207/20068 ,  G06T2207/20072 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30241

    Abstract: A method for video object tracking, the method comprising the steps of: receiving a sequence of stereoscopic images; receiving a depth map for each stereoscopic image of the sequence; calculating a first axis histogram for each depth map; applying a first object detection method to track objects based on the contents of the images and/or the depth maps; applying, in parallel to the first object detection method a second object detection method to track objects based on the contents of the histograms of the depth maps; and determining locations of tracked objects based on comparison of the results of the first object detection method and second object detection method.

    Abstract translation: 一种用于视频对象跟踪的方法，所述方法包括以下步骤：接收立体图像序列; 接收所述序列的每个立体图像的深度图; 计算每个深度图的第一轴直方图; 基于图像的内容和/或深度图应用第一对象检测方法来跟踪对象; 与第一对象检测方法并行地应用基于深度图的直方图的内容来跟踪对象的第二对象检测方法; 并且基于第一对象检测方法和第二对象检测方法的结果的比较来确定被跟踪对象的位置。

    System and method for object dimension estimation using 3D models
    10.
    发明授权
    System and method for object dimension estimation using 3D models 有权
    使用3D模型的对象尺寸估计的系统和方法

    公开(公告)号：US09430850B1

    公开(公告)日：2016-08-30

    申请号：US14690484

    申请日：2015-04-20

    Applicant: POLITECHNIKA POZNANSKA

    Inventor： Marek Domanski ,  Tomasz Grajek ,  Krzysztof Klimaszewski ,  Adam Luczak ,  Robert Ratajczak ,  Krzysztof Wegner

    IPC: G06K9/00 ,  G06T7/60 ,  G06T7/00 ,  G06K9/62 ,  H04N13/02

    CPC classification number: G06T7/60 ,  G06K9/62 ,  G06T7/70 ,  G06T7/75 ,  G06T2207/10012 ,  G06T2207/30232 ,  G06T2207/30236 ,  G06T2207/30244 ,  H04N13/204

    Abstract: A method for estimation of dimensions of an object present on images obtained from a set of N cameras and representing the same scene from different viewpoints, based on a 3D object model. The method comprises determining (302) a 3DMM model. It further comprises matching (303) the 3DMM model to each of N images of the set in order to determine a set of parameters hi, ρi, λi, wherein hi describes the orientation of the matched model with respect to the i-th image; ρi describes the 3D shape of the model matched to the i-th image and λi describes the appearance/texture of the model matched to the i-th image. The method comprises calculating (304) relative positions of the cameras, from which the images were collected, based on 3D transformations Hij of the matched 3DMM model from the i-th image to the matched 3DMM model from the j-th image; and calculating (305) the total matching error Ec for the model as a sum of matching errors of a model described by parameters hc, ρc, λc to individual images: E c = ∑ i = 1 N ⁢ E i The method further comprises estimating (306) the dimensions of the object based on locations of characteristic points from vector s, calculated as: s = s _ + ∑ k ⁢ p k · s ^ k wherein s is the vector of the average 3DMM model shape, ρk are elements of vector ρc, and ŝk are eigenvalue vectors of the 3DMM model.

    Abstract translation: 一种用于估计存在于从一组N个相机获得并且基于3D对象模型从不同视点表示相同场景的图像上存在的对象的尺寸的方法。 该方法包括确定（302）3DMM模型。 它进一步包括将3DMM模型与集合的N个图像中的每一个匹配（303），以便确定一组参数hi，ρi，λi，其中，描述匹配模型相对于第i个图像的取向; ρi描述与第i个图像匹配的模型的3D形状，λi描述与第i个图像匹配的模型的外观/纹理。 该方法包括基于从第i个图像到第j个图像的匹配3DMM模型的匹配3DMM模型的3D变换Hij，计算（304）从其收集图像的相机的相对位置; 并且计算（305）所述模型的总匹配误差Ec作为由参数hc，ρc，λc对各个图像描述的模型的匹配误差之和：E c =Σi = 1 N E i该方法还包括估计 （306）基于来自向量s的特征点的位置的对象的尺寸，其被计算为：s = s _ +Σk pk·s ^ k其中s是平均3DMM模型形状的向量，ρk是 向量ρc和ŝk是3DMM模型的特征值向量。

Patent Agency Ranking