公开(公告)号：US09420236B2

公开(公告)日：2016-08-16

申请号：US13809587

申请日：2011-03-09

申请人： Miyako Hotta ,  Masanori Miyoshi ,  Wataru Ito

发明人： Miyako Hotta ,  Masanori Miyoshi ,  Wataru Ito

IPC分类号： G06K9/00 ,  H04N7/18 ,  G06T7/20 ,  G08B13/196

CPC分类号： H04N7/18 ,  G06K9/00778 ,  G06T7/269 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/30232 ,  G08B13/19613 ,  H04N7/183

摘要： It is an object of the present invention to provide a monitoring system that captures and inputs video images of a crowd with a surveillance camera for detecting normal and/or various abnormal states. The monitoring system (MS) comprises: a video image input means (1) that captures and inputs the video images of the crowd; an optical-flow calculating means (2) that calculates optical flows from the video images captured at different times; a judgment-block setting means (3) that sets judgment blocks on a surveillance area of each video image, each judgment block serving as a unit to be judged about an abnormality; an optical-flow attribute counting means (4) that counts an attribute of optical flows generated in each judgment block; a normality-evaluating-index calculating means (5) that calculates, from the counted attribute of the optical flows, an evaluation value of a normality-evaluating index for evaluating a normality of the judgment block; an abnormal-state judging means (6) that judges, from the evaluation value of the normality-evaluating index, the abnormal state of the judgment block; and an output means (7) that outputs a result of the judgment made by the abnormal-state judging means onto the video image.

摘要翻译： 本发明的目的是提供一种监视系统，其利用用于检测正常和/或各种异常状态的监视摄像机捕获和输入人群的视频图像。 监视系统（MS）包括：视频图像输入装置（1），其捕获并输入人群的视频图像; 光流计算装置（2），其从在不同时间拍摄的视频图像计算光流; 一个判断块设置装置，用于在每个视频图像的监视区域上设置判断块，每个判断块用作关于异常的单元; 光流属性计数装置（4），其对在每个判断块中产生的光流的属性进行计数; 根据光流的属性计算用于评估判断块的正常性的正常评价指标的评价值的正常评价指标计算单元（5） 异常状态判断装置（6），根据正常评价指标的评价值判断判定块的异常状态; 以及输出装置（7），其将由异常状态判断装置进行的判断结果输出到视频图像上。

公开(公告)号：US20130113934A1

公开(公告)日：2013-05-09

申请号：US13809587

申请日：2011-03-09

申请人： Miyako Hotta ,  Masanori Miyoshi ,  Wataru Ito

发明人： Miyako Hotta ,  Masanori Miyoshi ,  Wataru Ito

IPC分类号： H04N7/18

CPC分类号： H04N7/18 ,  G06K9/00778 ,  G06T7/269 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/30232 ,  G08B13/19613 ,  H04N7/183

摘要： It is an object of the present invention to provide a monitoring system that captures and inputs video images of a crowd with a surveillance camera for detecting normal and/or various abnormal states. The monitoring system (MS) comprises: a video image input means (1) that captures and inputs the video images of the crowd; an optical-flow calculating means (2) that calculates optical flows from the video images captured at different times; a judgment-block setting means (3) that sets judgment blocks on a surveillance area of each video image, each judgment block serving as a unit to be judged about an abnormality; an optical-flow attribute counting means (4) that counts an attribute of optical flows generated in each judgment block; a normality-evaluating-index calculating means (5) that calculates, from the counted attribute of the optical flows, an evaluation value of a normality-evaluating index for evaluating a normality of the judgment block; an abnormal-state judging means (6) that judges, from the evaluation value of the normality-evaluating index, the abnormal state of the judgment block; and an output means (7) that outputs a result of the judgment made by the abnormal-state judging means onto the video image.

摘要翻译： 本发明的目的是提供一种监视系统，其利用用于检测正常和/或各种异常状态的监视摄像机捕获和输入人群的视频图像。 监视系统（MS）包括：视频图像输入装置（1），其捕获并输入人群的视频图像; 光流计算装置（2），其从在不同时间拍摄的视频图像计算光流; 一个判断块设置装置，用于在每个视频图像的监视区域上设置判断块，每个判断块用作关于异常的单元; 光流属性计数装置（4），其对在每个判断块中产生的光流的属性进行计数; 根据光流的属性计算用于评估判断块的正常性的正常评价指标的评价值的正常评价指标计算单元（5） 异常状态判断装置（6），根据正常评价指标的评价值判断判断块的异常状态; 以及输出装置（7），其将由异常状态判断装置进行的判断结果输出到视频图像上。

公开(公告)号：US09195435B2

公开(公告)日：2015-11-24

申请号：US14232046

申请日：2011-08-03

申请人： Shigetoshi Sakimura ,  Masanori Miyoshi

发明人： Shigetoshi Sakimura ,  Masanori Miyoshi

IPC分类号： G06F17/50 ,  G06F15/16 ,  G06F15/173 ,  G06F13/28 ,  G06F3/048 ,  G06F9/44

CPC分类号： G06F8/20 ,  G06F8/35

摘要： The present invention includes four types of component diagrams, namely, an input/output data memory management component diagram, an input data value setup component diagram, a library execution component diagram, and an output data value acquisition component diagram, with respect to image processing library functions for a programming language and to an input/output data structure for the image processing library functions. The present invention also includes upper-level component diagrams, which are prepared by connecting the four types of component diagrams as lower-level component diagrams in the order of use, writes an algorithm by combining the lower- and upper-level component diagrams, and executes the written algorithm. From the written algorithm, the present invention generates a programming language source code for calling an image processing library.

摘要翻译： 本发明包括关于图像处理的四种类型的组件图，即输入/输出数据存储器管理组件图，输入数据值设置组件图，库执行组件图和输出数据值获取组件图 用于编程语言的库函数以及图像处理库函数的输入/输出数据结构。 本发明还包括上级组件图，其通过将四种类型的组件图按照使用顺序连接成下级组件图来编写，通过组合下级和上级组件图来写入算法，以及 执行书面算法。 根据本发明的编写算法，生成用于调用图像处理库的编程语言源代码。

公开(公告)号：US08675065B2

公开(公告)日：2014-03-18

申请号：US12540549

申请日：2009-08-13

申请人： Masaya Itoh ,  Masanori Miyoshi ,  Masato Kazui ,  Hiromasa Fujii

发明人： Masaya Itoh ,  Masanori Miyoshi ,  Masato Kazui ,  Hiromasa Fujii

IPC分类号： H04N13/04 ,  G06F15/16

CPC分类号： G06K9/00771 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/20224 ,  G06T2207/30232 ,  G08B13/19671

摘要： A video monitoring system, comprises a camera, and a monitor apparatus, to which video data from the camera is transmitted, wherein the camera comprises a video obtaining unit for obtaining a signal from an image pickup device, a camera image recognizer unit for executing video processing upon an input video obtained from the video obtaining unit, an encoding unit for executing an encoding process upon basis of a result of the processing within the camera image recognizer unit, thereby producing the video data, and wherein the monitor apparatus comprises a decoding unit for decoding the video data, and an image recognizer unit for selecting a decoding means of the decoding unit, upon basis of the result of processing of the camera image recognizer unit.

摘要翻译： 一种视频监视系统，包括摄像机和监视器设备，来自摄像机的视频数据被发送到摄像机，其中摄像机包括用于从摄像设备获得信号的视频获取单元，用于执行视频的摄像机图像识别器单元 对从视频获取单元获得的输入视频进行处理;编码单元，用于根据相机图像识别器单元中的处理结果执行编码处理，从而产生视频数据，并且其中监视器装置包括解码单元 用于解码视频数据，以及图像识别单元，用于根据摄像机图像识别单元的处理结果选择解码单元的解码装置。

公开(公告)号：US06806875B2

公开(公告)日：2004-10-19

申请号：US10175805

申请日：2002-06-21

申请人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

发明人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

IPC分类号： G06T1550

CPC分类号： G06T1/60 ,  G06T11/40 ,  G06T15/50 ,  G06T15/80

摘要： In a data processor and a shading apparatus used in the data processor, the data processor selects an address based on the information of a memory or a translation look-aside buffer. Therefore, even when the same data are accessed, a different address at high speed is adopted according to the hardware, object to be processed, processing, etc. A plurality of geometric vectors are given as the parameters for the vertexes of a picture, the vectors are interpolated in the picture, and the luminance of each small area in the figure is calculated using the vectors generated by the interpolation. Therefore, a spotlight or highlight can be expressed with high accuracy and at high speed even when the amount of the hardware and the extent of the picture are small.

摘要翻译： 在数据处理器中使用的数据处理器和着色装置中，数据处理器根据存储器或翻译后备缓冲器的信息来选择一个地址。 因此，即使在访问相同的数据的情况下，也可以根据硬件，被处理对象，处理等来采用高速的不同的地址。作为图像的顶点的参数，给出多个几何矢量， 矢量被内插在图像中，并且使用通过内插生成的矢量来计算图中每个小区域的亮度。 因此，即使当硬件的数量和图像的程度小时，也可以高精度和高速度地表现聚光灯或高光。

公开(公告)号：US20110205360A1

公开(公告)日：2011-08-25

申请号：US12709362

申请日：2010-02-19

申请人： Takashi SAEKI ,  Masaya Itoh ,  Masato Kazui ,  Masanori Miyoshi ,  Hisao Oodawa ,  Kouichi Shiraishi ,  Takao Sukegawa

发明人： Takashi SAEKI ,  Masaya Itoh ,  Masato Kazui ,  Masanori Miyoshi ,  Hisao Oodawa ,  Kouichi Shiraishi ,  Takao Sukegawa

IPC分类号： H04N7/18

CPC分类号： G08B13/19604 ,  G08B13/19602 ,  G08B13/1961 ,  G08B29/046

摘要： The object of the invention is to provide a supervising system for image to detect a scheme at high accuracy. The supervising system for image is provided with a first portion for detecting change of time detecting the change of time in amount of feature of an image taken pictures by a image forming device, a second portion for detecting change of time in the illuminance detected by an illuminance sensor, and a scheme judging portion detecting a scheme against the image forming device in accordance with the change of time in amount of feature and the change of time in the illuminance as detected.

摘要翻译： 本发明的目的是提供一种用于图像的监控系统以高精度检测方案。 图像监视系统设置有用于检测由图像形成装置检测拍摄图像的特征量的时间变化的时间变化的第一部分，用于检测由图像形成装置检测到的照度中的时间变化的第二部分 照度传感器，以及方案判断部分，根据检测到的特征量和照明时间的变化，根据图像形成装置检测方案。

公开(公告)号：US06433782B1

公开(公告)日：2002-08-13

申请号：US08894786

申请日：1997-08-28

申请人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

发明人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

IPC分类号： G06T1550

CPC分类号： G06T1/60 ,  G06T11/40 ,  G06T15/50 ,  G06T15/80

摘要： In a data processor and a shading apparatus used in the data processor, the data processor selects an address based on the information of a memory or a translation look-aside buffer. Therefore, even when the same data are accessed, a different address at high speed is adopted according to the hardware, object to be processed, processing, etc. A plurality of geometric vectors are given as the parameters for the vertexes of a picture, the vectors are interpolated in the picture, and the luminance of each small area in the figure is calculated using the vectors generated by the interpolation. Therefore, a spotlight or highlight can be expressed with high accuracy and at high speed even when the amount of the hardware and the extent of the picture are small.

摘要翻译： 在数据处理器中使用的数据处理器和着色装置中，数据处理器根据存储器或翻译后备缓冲器的信息来选择一个地址。 因此，即使在访问相同的数据的情况下，也可以根据硬件，被处理对象，处理等来采用高速的不同的地址。作为图像的顶点的参数，给出多个几何矢量， 矢量被内插在图像中，并且使用通过内插生成的矢量来计算图中每个小区域的亮度。 因此，即使当硬件的数量和图像的程度小时，也可以高精度和高速度地表现聚光灯或高光。

公开(公告)号：US5966129A

公开(公告)日：1999-10-12

申请号：US731163

申请日：1996-10-10

申请人： Nobuhiko Matsukuma ,  Manabu Yanagimoto ,  Hiroaki Takatsuki ,  Narihiro Munemasa ,  Toshio Moriya ,  Nobuhiro Sekimoto ,  Tsuneya Kurihara ,  Masanori Miyoshi

发明人： Nobuhiko Matsukuma ,  Manabu Yanagimoto ,  Hiroaki Takatsuki ,  Narihiro Munemasa ,  Toshio Moriya ,  Nobuhiro Sekimoto ,  Tsuneya Kurihara ,  Masanori Miyoshi

IPC分类号： G06F3/14 ,  G06F3/048 ,  G06T19/20 ,  G09B29/00

CPC分类号： G06T13/20

摘要： An image producing/displaying apparatus capable of inputting a command for changing a state of an object regardless of a form of the object includes a virtual world expressing system for constructing a virtual world including at least one object and environment in which the object exists and producing an image for visually displaying at least part of the virtual world, an output system for visualizing the image produced by the virtual world expressing system and outputting the image, and a command input system for inputting a command to the virtual world expressing system. The command input system detects a movement state of a specific pixel pattern contained in an image formed by an imaging device and extracts feature quantity from the movement state to recognize the command so that the command is notified to the virtual world expressing system.

摘要翻译： 能够输入用于改变对象的状态的命令的图像产生/显示装置，而不管对象的形式如何，包括虚拟世界表达系统，用于构建虚拟世界，该虚拟世界包括至少一个对象和存在对象的环境，并产生 用于可视地显示虚拟世界的至少一部分的图像，用于可视化由虚拟世界表达系统产生的图像并输出图像的输出系统，以及用于向虚拟世界表达系统输入命令的命令输入系统。 命令输入系统检测包含在由成像装置形成的图像中的特定像素图案的移动状态，并且从移动状态提取特征量以识别该命令，从而将命令通知给虚拟世界表达系统。

公开(公告)号：US20110317016A1

公开(公告)日：2011-12-29

申请号：US13170303

申请日：2011-06-28

申请人： Takashi SAEKI ,  Ryo Yumiba ,  Masaya Itoh ,  Takao Sukegawa ,  Yasuhiro Suda ,  Masanori Miyoshi

发明人： Takashi SAEKI ,  Ryo Yumiba ,  Masaya Itoh ,  Takao Sukegawa ,  Yasuhiro Suda ,  Masanori Miyoshi

IPC分类号： H04N7/18

CPC分类号： G08B13/19639 ,  G05B2219/33045 ,  G08B13/19613 ,  G08B13/19634 ,  G08B13/19645 ,  G08B13/19652 ,  G08B13/1968 ,  G08B13/19682 ,  H04N5/247 ,  Y10S706/921

摘要： A device which can support a determination of a camera layout by automatically preparing the camera layout that satisfies a customer request based on the customer request including a surveillance layout. Specifically, a need table that is a data set of a plurality of arrangement candidate cameras satisfying the customer request is prepared from the customer request including the surveillance layout. An arrangement of the plurality of the arrangement candidate cameras on a map is calculated based on the need table using a clustering method and a temporary layout of cameras is prepared. Then, an arrangement layout of the cameras in the surveillance layout is determined based on the temporary layout.

摘要翻译： 一种可以通过基于包括监视布局的客户请求自动准备满足客户请求的相机布局来支持确定相机布局的装置。 具体而言，从包括监视布局的客户请求准备作为满足客户请求的多个配置候选摄像机的数据集的需求表。 基于使用聚类方法的需求表计算出地图上的多个布置候选摄像机的布置，并且准备了相机的临时布局。 然后，基于临时布局确定监视布局中的摄像机的布置布局。

公开(公告)号：US07433493B1

公开(公告)日：2008-10-07

申请号：US10362133

申请日：2000-09-06

申请人： Masanori Miyoshi ,  Yoshiaki Usami ,  Kazuya Takahashi ,  Norito Watanabe ,  Hideki Fujii

发明人： Masanori Miyoshi ,  Yoshiaki Usami ,  Kazuya Takahashi ,  Norito Watanabe ,  Hideki Fujii

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06T7/20 ,  G08B13/19608 ,  G08B13/19615 ,  G08B31/00 ,  H04N7/183 ,  H04N7/188

摘要： A technique for detecting an abnormal behavior by monitoring moving objects such as human being and a car. The place where the abnormal behavior of the moving objects occurs is deduced from the position of the moving object and the direction in which the moving object moves and presented to the car. An abnormal detector comprises means for determining the position of the moving object and the direction in which the moving object moves, means for determining the place where an abnormal incident causing an abnormal behavior of the moving object occurs on the basis of the determined position and direction, and means for displaying the place where the abnormal incident occurs. Therefore it is possible to immediately know the cause of the abnormal behavior of the moving object from the video information collected by observation monitoring moving objects such as a human being and a car.

摘要翻译： 一种用于通过监视诸如人和汽车的移动物体来检测异常行为的技术。 发生移动物体的异常行为的地方是从运动物体的位置和运动物体移动并呈现给汽车的方向推导出来的。 异常检测器包括用于确定移动物体的位置和运动物体移动方向的装置，用于根据确定的位置和方向确定引起运动物体的异常行为的异常事件发生的地方的装置 以及用于显示发生异常事件的地方的装置。 因此，可以从通过观察监视诸如人和汽车的移动物体收集的视频信息中立即知道移动物体的异常行为的原因。