公开(公告)号：US06404455B1

公开(公告)日：2002-06-11

申请号：US09078521

申请日：1998-05-14

申请人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada ,  Miyuki Endo

发明人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada ,  Miyuki Endo

IPC分类号： H04N5225

CPC分类号： G08B13/19602 ,  G08B13/19604 ,  G08B13/19608 ,  G08B13/19628 ,  G08B13/19643 ,  G08B13/19689 ,  H04N7/181

摘要： A system for processing a tracking picture of an intruding object includes a first TV camera for outputting a video signal used for detecting the intruding object, a second TV camera for outputting a video signal used for monitoring a magnified tracking picture of the intruding object, and a picture processing device for processing and operating on the video signal inputted from the first TV camera and outputting a rotation control signal and a zooming control signal. The system detects a difference between the video signal inputted from the first TV camera and a reference background video signal, and a change of a detecting state from the change of the numbers of objects detected in the continuous input video signal.

摘要翻译： 用于处理入侵物体的跟踪图像的系统包括用于输出用于检测入侵物体的视频信号的第一TV摄像机，用于输出用于监视入侵物体的放大跟踪图像的视频信号的第二TV摄像机，以及 用于处理和操作从第一TV摄像机输入的视频信号并输出​​旋转控制信号和变焦控制信号的图像处理装置。 该系统检测从第一TV摄像机输入的视频信号与参考背景视频信号之间的差异，以及从连续输入视频信号中检测到的对象数量变化的检测状态的改变。

公开(公告)号：US5671010A

公开(公告)日：1997-09-23

申请号：US442992

申请日：1995-05-17

申请人： Naoyuki Shimbo ,  Toshimichi Okada ,  Haruki Watanabe

发明人： Naoyuki Shimbo ,  Toshimichi Okada ,  Haruki Watanabe

IPC分类号： A63B71/06 ,  G04F10/00 ,  G04F13/02 ,  G07C1/22 ,  G07C1/24 ,  H04N7/18 ,  H04N9/74

CPC分类号： H04N7/188 ,  G04F13/02 ,  G07C1/24

摘要： Apparatus for judging the order of arrival of racers at a goal in a race and the time taken for the race, capable of storing, in a memory unit, video signals of a plurality of line sensor cameras disposed so as to be able to pick up images of moving objects from both directions with a judging criterion line between or from such angles that moving objects do not overlap, effecting scan conversion on the stored video signals of the plurality of line sensor cameras, reading resultant video signals, and displaying video signals thus read out respectively singly or simultaneously plurally on a single video monitor.

摘要翻译： 用于判断赛车在比赛中的目标的到达顺序的装置以及能够在存储器单元中存储多个行传感器相机的视频信号以便能够拾取的比赛所花费的时间 从两个方向移动的物体的图像与运动对象不重叠的角度之间的判断标准线，对多个线传感器相机所存储的视频信号进行扫描转换，从而读取合成的视频信号并显示视频信号 在单个视频监视器上分别单独或同时多次读出。

公开(公告)号：US07215795B2

公开(公告)日：2007-05-08

申请号：US09964336

申请日：2001-09-28

申请人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada ,  Miyuki Fujii

发明人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada ,  Miyuki Fujii

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06T7/254

摘要： An intruding object detecting method and an intruding object monitoring apparatus for detecting a target object intruding into an image pickup region while reducing the error detection of moving objects other than the target object. A difference in pixel value between an input image signal and each of different image signals in a predetermined number of frames greater than one is calculated for each pixel to thereby obtain differential images in the predetermined number of frames. The differential images in the predetermined number of frames are synthesized in predetermined proportions to thereby generate a synthesized differential image. The synthesized differential image is binarized on the basis of a predetermined threshold value to thereby generate a binarized image. A binarized object in the binarized image is detected as an object intruding into a monitoring visual field.

摘要翻译： 一种入侵物体检测方法和入侵物体监测装置，用于在减少对象物体以外的移动物体的误差检测的同时，检测入射到摄像区域中的目标物体。 针对每个像素计算输入图像信号和大于1的预定帧数的每个不同图像信号之间的像素值的差异，从而获得预定帧数的差分图像。 以预定比例合成预定帧数的差分图像，从而生成合成差分图像。 基于预定阈值对合成的差分图像进行二值化，从而生成二值化图像。 二维化图像中的二值化对象被检测为进入监视视野的对象。

公开(公告)号：US07082209B2

公开(公告)日：2006-07-25

申请号：US09933164

申请日：2001-08-21

申请人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada

发明人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada

IPC分类号： G06K9/00

CPC分类号： G06T7/254

摘要： An object detecting method, object detecting apparatus and intruding object monitoring apparatus employing the object detecting method. A predetermined monitor area having no object to be detected is imaged by an imaging device and reference background sequential images are registered in advance in a storage unit. When monitoring, the predetermined monitor area is imaged by the imaging device while at the same time sequentially outputting the images frame by frame from the imaging device, a reference background image corresponding to the image from the imaging device is selected from the reference background sequential images, subtraction processing is carried out between the image from the imaging device and a corresponding reference background image, and the object detecting processing is carried out based on the result of subtraction processing.

公开(公告)号：US6108033A

公开(公告)日：2000-08-22

申请号：US862918

申请日：1997-05-23

申请人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada

发明人： Wataru Ito ,  Hirotada Ueda ,  Toshimichi Okada

IPC分类号： G08B13/194 ,  G08B13/196 ,  H04N7/18

CPC分类号： G08B13/19602 ,  G08B13/19604 ,  G08B13/19608 ,  G08B13/19691 ,  H04N7/183

摘要： A difference between an input image including images of a background image picked up by an image pick-up unit and an object to be monitored is produced as an image of the object, the image of the object is divided into a plurality of parts and the plurality of divided image of the object are produced as a plurality of templates. Each of the plurality of templates is matched with a new input image and images of a plurality of parts in the new input image which have highest degrees of matching with the plurality of templates are used to update the plurality of templates to output a plurality of new templates. Each of the plurality of new templates is matched with a further new input image and images of a plurality of parts in the further new input image which have highest degrees of matching with the plurality of new templates are used to update the plurality of new templates to output a plurality of further new templates. In this manner, the plurality of templates are sequentially updated for the new input images to trace the object.

摘要翻译： 产生包括由摄像单元拍摄的背景图像的图像和被监视对象的输入图像之间的差异作为对象的图像，将对象的图像划分为多个部分，并且 生成多个分割图像的多个模板。 多个模板中的每一个与新的输入图像匹配，并且使用与多个模板具有最高匹配度的新输入图像中的多个部分的图像来更新多个模板以输出多个新的 模板。 多个新模板中的每一个与另一新的输入图像匹配，并且使用与多个新模板具有最高匹配程度的另一新输入图像中的多个部分的图像来将多个新模板更新为 输出多个另外的新模板。 以这种方式，对于新的输入图像依次更新多个模板以跟踪对象。