Optical flow detection system
    1.
    发明授权
    Optical flow detection system 失效
    光流检测系统

    公开(公告)号:US5627905A

    公开(公告)日:1997-05-06

    申请号:US353589

    申请日:1994-12-12

    摘要: An optical flow detection system is employed in conjunction with a target cuer system, which includes a sensor carried on a platform, for the purpose of either removing undesirable sensor motion or for the purpose of removing undesirable background motion so that targets may be more easily identified. The optical flow detection system includes an optical flow estimator which receives a plurality of pixels and generates therefrom an instantaneous pixel velocity value and a predicted pixel velocity value. The instantaneous pixel velocity values and predicted pixel velocity values are then manipulated to remove undesirable features included in the image sequence generated by the sensor. Methods for operating the optical flow detection system are also provided.

    摘要翻译: 光学流量检测系统与目标指示器系统结合使用,目标指示器系统包括在平台上承载的传感器,用于消除不期望的传感器运动或为了消除不期望的背景运动,从而可以更容易地识别目标 。 光流检测系统包括光流估计器,其接收多个像素并从其产生瞬时像素速度值和预测像素速度值。 然后对瞬时像素速度值和预测像素速度值进行操作,以消除由传感器产生的图像序列中包含的不期望的特征。 还提供了用于操作光流检测系统的方法。

    Method and apparatus for determining image affine flow using artifical
neural system with simple cells and lie germs
    2.
    发明授权
    Method and apparatus for determining image affine flow using artifical neural system with simple cells and lie germs 失效
    使用具有简单细胞和细菌的人造神经系统确定图像仿射流的方法和装置

    公开(公告)号:US5535302A

    公开(公告)日:1996-07-09

    申请号:US352140

    申请日:1994-12-01

    申请人: Tien-Ren Tsao

    发明人: Tien-Ren Tsao

    摘要: A method and apparatus is provided to determine image affine flow from time-varying imagery. The novel artificial neural computational system of a cortical hypercolumn comprising a plurality of specific orientation (SO) columns and a least square error fitting circuit is based on a Lie group model of cortical visual motion processing. Time-varying imagery, comprising intensity imagery and time-derivative imagery is provided to a plurality of specific orientation (SO) columns comprising simple cells and Lie germs. The cortical representation of image time derivative and affine Lie derivatives are extracted from responses of simple cells and Lie germs, respectively. The temporal derivative and affine Lie-derivative information obtained from each specific orientation (SO) columns is applied to least square error fitting analog circuit having a three layer multiplicative neural architecture to determine image affine flow components in accordance with an error minimization gradient dynamical system technique.

    摘要翻译: 提供了一种用于确定来自时变图像的图像仿射流的方法和装置。 包含多个特定取向(SO)列和最小二乘错误拟合电路的皮质超列的新型人造神经计算系统基于皮质视觉运动处理的李群模型。 将包括强度图像和时间衍生图像的时变图像提供给包括简单单元格和谎言细菌的多个特定取向(SO)列。 图像时间导数和仿射衍射的皮层表现分别从简单细胞和谎言细菌的响应中提取出来。 从每个特定取向(SO)列获得的时间导数和仿射Lie衍生信息应用于具有三层乘法神经结构的最小二乘错误拟合模拟电路,以根据误差最小化梯度动力系统技术确定图像仿射流分量 。

    Method and device for the estimation of motion in a sequence of moving
images
    3.
    发明授权
    Method and device for the estimation of motion in a sequence of moving images 失效
    用于运动图像运动估计的方法和装置

    公开(公告)号:US5089887A

    公开(公告)日:1992-02-18

    申请号:US487956

    申请日:1990-05-14

    摘要: The process consists in estimating motion by execution of a gradient algorithm (2, 3) which brings to a minimum the mean square deviation of the local variations of the current point of the image with the point that is homologous to it in the preceding image, in initializing (7) the execution of the algorithm by the displacement values estimated in several directions within the close vicinity of the current point and by an initial vector of temporal prediction of the displacement between successive frames of the image, then in propagating each estimation in the direction of scanning of the lines of the image.

    摘要翻译: PCT No.PCT / FR89 / 00482 Sec。 371日期1990年5月14日 102(e)日期1990年5月14日PCT提交1989年9月22日PCT公布。 第WO90 / 03619号公报 日期1990年4月5日。该过程包括通过执行梯度算法(2,3)来估计运动,该梯度算法将图像当前点的局部变化的均方差与同源点 在前一图像中,通过在当前点附近的几个方向上估计的位移值和图像的连续帧之间的位移的时间预测的初始矢量来初始化(7)算法的执行 然后在扫描图像的行的方向上传播每个估计。

    Movement estimation system for video signals using a recursive gradient
method
    4.
    发明授权
    Movement estimation system for video signals using a recursive gradient method 失效
    使用递归梯度法的视频信号运动估计系统

    公开(公告)号:US4695882A

    公开(公告)日:1987-09-22

    申请号:US696371

    申请日:1985-01-30

    摘要: A movement of a small picture block in a frame of video signals is provided by recursively applying a gradient method to a picture block in a present frame and a preceding frame to provide a series of sub-movements until said sub-movement decreases less than a predetermined value, and the resultant movement is obtained by the sum of the sub-movements. The present invention provides high accuracy in estimation of movement of a block in a picture as compared with a conventional gradient method, and is attractive in hardware implementation.

    摘要翻译: 通过对当前帧和前一帧中的图像块递归地应用梯度方法来提供视频信号帧中的小图像块的运动,以提供一系列子运动,直到所述子运动减小到小于 并且通过副运动的总和来获得所得运动。 与传统的梯度方法相比,本发明提供了对图像中的块的移动的估计的高精度,并且在硬件实现方面是有吸引力的。

    Apparatus for detecting a movement of a digital television signal
    5.
    发明授权
    Apparatus for detecting a movement of a digital television signal 失效
    用于检测数字电视信号的移动的装置

    公开(公告)号:US4661846A

    公开(公告)日:1987-04-28

    申请号:US773078

    申请日:1985-09-06

    申请人: Tetsujiro Kondo

    发明人: Tetsujiro Kondo

    IPC分类号: G06T7/20 H04N5/14 H04N7/12

    CPC分类号: G06T7/2066 H04N5/145

    摘要: Upon execution of the movement detection by way of a gradient method, the leftward and rightward sampling differences .DELTA.EL and .DELTA.ER at a change extremal value point are used to detect the respective movements in the vertical and horizontal directions. The movement amounts detected are selectively fetched. Upon addition/subtraction of the frame difference, the sign of sample is held until the positive or negative sign of the sample which is obtained from the result of comparison between the sampling difference values before and after the sample is changed. The accurate movement detection is performed by controlling the addition/subtraction in response to the holding signal.

    摘要翻译: 在通过梯度方法执行移动检测时,使用变化极值点处的向左和向右采样差DELTA EL和DELTA ER来检测垂直和水平方向上的相应移动。 有选择地取出检测到的移动量。 通过加/减帧差,样本的符号被保持,直到样本的正或负符号从样本之前和之后的采样差值之间的比较结果获得。 通过响应于保持信号控制加/减来执行准确的移动检测。

    Depth map movement tracking via optical flow and velocity prediction
    7.
    发明授权
    Depth map movement tracking via optical flow and velocity prediction 有权
    通过光流和速度预测深度图移动跟踪

    公开(公告)号:US09153035B2

    公开(公告)日:2015-10-06

    申请号:US14504949

    申请日:2014-10-02

    发明人: Mark J. Finocchio

    IPC分类号: G06K9/00 G06T7/20

    摘要: Techniques for efficiently tracking points on a depth map using an optical flow are disclosed. In order to optimize the use of optical flow, isolated regions of the depth map may be tracked. The sampling regions may comprise a 3-dimensional box (width, height and depth). Each region may be “colored” as a function of depth information to generate a “zebra” pattern as a function of depth data for each sample. The disclosed techniques may provide for handling optical flow tracking when occlusion occurs by utilizing a weighting process for application of optical flow vs. velocity prediction to stabilize tracking.

    摘要翻译: 公开了使用光流在深度图上有效跟踪点的技术。 为了优化光流的使用,可以跟踪深度图的隔离区域。 采样区域可以包括三维箱体(宽度,高度和深度)。 作为深度信息的函数,每个区域可以“着色”,以产生作为每个样本的深度数据的函数的“斑马”图案。 所公开的技术可以提供用于通过利用用于应用光流与速度预测的加权过程来发生遮挡发生时的光流跟踪以稳定跟踪。

    DEPTH MAP MOVEMENT TRACKING VIA OPTICAL FLOW AND VELOCITY PREDICTION
    8.
    发明申请
    DEPTH MAP MOVEMENT TRACKING VIA OPTICAL FLOW AND VELOCITY PREDICTION 有权
    深度地图运动跟踪通过光流和速度预测

    公开(公告)号:US20150084967A1

    公开(公告)日:2015-03-26

    申请号:US14504949

    申请日:2014-10-02

    发明人: Mark J. Finocchio

    IPC分类号: G06T7/20

    摘要: Techniques for efficiently tracking points on a depth map using an optical flow are disclosed. In order to optimize the use of optical flow, isolated regions of the depth map may be tracked. The sampling regions may comprise a 3-dimensional box (width, height and depth). Each region may be “colored” as a function of depth information to generate a “zebra” pattern as a function of depth data for each sample. The disclosed techniques may provide for handling optical flow tracking when occlusion occurs by utilizing a weighting process for application of optical flow vs. velocity prediction to stabilize tracking.

    摘要翻译: 公开了使用光流在深度图上有效跟踪点的技术。 为了优化光流的使用,可以跟踪深度图的隔离区域。 采样区域可以包括三维箱体(宽度,高度和深度)。 作为深度信息的函数,每个区域可以“着色”,以产生作为每个样本的深度数据的函数的“斑马”图案。 所公开的技术可以提供用于通过利用用于应用光流与速度预测的加权过程来发生遮挡发生时的光流跟踪以稳定跟踪。

    DEPTH MAP MOVEMENT TRACKING VIA OPTICAL FLOW AND VELOCITY PREDICTION
    9.
    发明申请
    DEPTH MAP MOVEMENT TRACKING VIA OPTICAL FLOW AND VELOCITY PREDICTION 有权
    深度地图运动跟踪通过光流和速度预测

    公开(公告)号:US20100194741A1

    公开(公告)日:2010-08-05

    申请号:US12363036

    申请日:2009-01-30

    申请人: Mark J. Finocchio

    发明人: Mark J. Finocchio

    IPC分类号: G06T15/00 A63F9/24

    摘要: Techniques for efficiently tracking points on a depth map using an optical flow are disclosed. In order to optimize the use of optical flow, isolated regions of the depth map may be tracked. The sampling regions may comprise a 3-dimensional box (width, height and depth). Each region may be “colored” as a function of depth information to generate a “zebra” pattern as a function of depth data for each sample. The disclosed techniques may provide for handling optical flow tracking when occlusion occurs by utilizing a weighting process for application of optical flow vs. velocity prediction to stabilize tracking.

    摘要翻译: 公开了使用光流在深度图上有效跟踪点的技术。 为了优化光流的使用,可以跟踪深度图的隔离区域。 采样区域可以包括三维箱体(宽度,高度和深度)。 作为深度信息的函数,每个区域可以“着色”,以产生作为每个样本的深度数据的函数的“斑马”图案。 所公开的技术可以提供用于通过利用用于应用光流与速度预测的加权过程来发生遮挡发生时的光流跟踪以稳定跟踪。

    Device and method for detection of moving obstacles
    10.
    发明授权
    Device and method for detection of moving obstacles 失效
    用于检测移动障碍物的装置和方法

    公开(公告)号:US5777690A

    公开(公告)日:1998-07-07

    申请号:US588845

    申请日:1996-01-19

    摘要: A moving obstacle detecting device detects moving objects, may be applied in the field of autonomous vehicles, intelligent robots, video monitoring system and similar systems. The device includes an optical flow extracting unit 1 for extracting optical flows for the respective local regions in the measured images, an focus of expansion (F.O.E.) calculating unit for calculating an F.O.E. of a straight line extended by the extracted optical flows, and a moving obstacle detecting unit for analyzing a temporal change of the calculated F.O.E. to judge the presence of the moving obstacle when the temporal positional change is larger than a predetermined variation quantity.

    摘要翻译: 移动障碍物检测装置检测移动物体,可应用于自主车辆,智能机器人,视频监控系统和类似系统领域。 该装置包括用于提取测量图像中的各个局部区域的光流的光流提取单元1,用于计算F.O.E的扩展焦点(F.O.E.)计算单元。 由提取的光流延伸的直线;以及移动障碍物检测单元,用于分析计算出的F.O.E.的时间变化。 当时间位置变化大于预定变化量时,判断移动障碍物的存在。