公开(公告)号：US09948914B1

公开(公告)日：2018-04-17

申请号：US15143670

申请日：2016-05-02

申请人： The United States of America, as represented by the Secretary of the Air Force

发明人： Alan R Pinkus ,  David W Dommett

IPC分类号： H04N13/00 ,  H04N13/02 ,  G06T17/10 ,  G06T7/00

CPC分类号： H04N13/156 ,  G06T7/0026 ,  G06T7/0097 ,  G06T17/10 ,  G06T2207/20164 ,  H04N13/25 ,  H04N13/296 ,  H04N2013/0092

摘要： A mobile three-dimensional sensor configuration is provided with a first sensor of a second type mounted proximate to the first sensor of a first type. A second sensor of the second type is mounted proximate to a second sensor of the first type. The first and second sensors are coupled to a first platform operable to vary the azimuth and elevation of the first and second sensors of the first and second types. The first and second platforms are mounted on a translational drive configured to independently translate the first and second platforms with respect to one another. A controller is configured to receive images sensors of and further configured to create a pair fused images of the first sensors of the first and second type and the second sensors of the first and second type. The controller is still further configured to display the pair of fused images.

公开(公告)号：US08873861B2

公开(公告)日：2014-10-28

申请号：US13705399

申请日：2012-12-05

申请人： Kabushiki Kaisha Toshiba

发明人： Shigeru Motoi ,  Koji Yamamoto

IPC分类号： G06K9/46 ,  H04N21/845 ,  H04N21/8549 ,  G06K9/00 ,  G06T7/00 ,  H04N21/44 ,  G11B27/28 ,  G11B27/031 ,  H04N21/439

CPC分类号： G06T7/0097 ,  G06K9/00751 ,  G11B27/031 ,  G11B27/28 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/8456 ,  H04N21/8549

摘要： In one embodiment, a method is disclosed for performing a video processing. The method can extract one or more common video segments. The method can select a common summarization segment based on a first summarization score. The method can extract one or more individual video segments in which the number of segments included therein is not more than a third threshold value that is less than a second threshold value. The method can select an individual summarization segment based on a second summarization score. In addition, the method can integrate the common summarization segment and the individual summarization segment to create the summary video.

摘要翻译： 在一个实施例中，公开了一种用于执行视频处理的方法。 该方法可以提取一个或多个常见的视频片段。 该方法可以基于第一个总结分数来选择一个公共摘要段。 该方法可以提取其中包括在其中的段的数量不超过小于第二阈值的第三阈值的一个或多个单独视频段。 该方法可以基于第二个总结分数来选择单个汇总分段。 此外，该方法可以将公共摘要段和个人摘要段进行整合，创建摘要视频。

公开(公告)号：US6130964A

公开(公告)日：2000-10-10

申请号：US18984

申请日：1998-02-05

申请人： Ferran Marques ,  Cristina Molina

发明人： Ferran Marques ,  Cristina Molina

IPC分类号： H04N7/32 ,  G06T5/00 ,  G06T7/20 ,  H04N7/26 ,  G06K9/00

CPC分类号： G06T7/2006 ,  G06T7/0081 ,  G06T7/0097 ,  G06T2207/10016 ,  G06T2207/20016 ,  H04N19/70

摘要： This relates to a method for image segmentation and video object tracking. While conventional methods rely on the motion homogeneity of the objects to be tracked, the present method is based on a concept of partition projection in which both spatial and motion information are now exploited, and implemented by means of a modified double partition approach, including a re-segmentation of a first partition followed by a projection step of the obtained fine partition into the current frame. Objects presenting non-homogeneous motion, static objects, and parts of an object with homogeneous motion can thus be tracked.

摘要翻译： 这涉及图像分割和视频对象跟踪的方法。 虽然常规方法依赖于要跟踪的对象的运动均匀性，但是本方法基于分区投影的概念，其中现在利用空间和运动信息，并且通过修改的双分区方法来实现，包括 重新分割第一分区，随后将所获得的精细分区的投影步骤转换为当前帧。 因此可以跟踪呈现非均匀运动，静态物体和具有均匀运动的物体的部分的物体。

公开(公告)号：US09842402B1

公开(公告)日：2017-12-12

申请号：US14976460

申请日：2015-12-21

申请人： Amazon Technologies, Inc.

发明人： Rohith Mysore Vijaya Kumar ,  Abhishek Singh ,  Ambrish Tyagi

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  H04N5/232 ,  H04N5/341

CPC分类号： G06T7/0081 ,  G06T7/0097 ,  G06T7/2053 ,  G06T7/206 ,  G06T7/215 ,  G06T2207/20021 ,  G06T2207/20056 ,  G06T2207/20144 ,  G06T2207/20224 ,  G06T2207/30241 ,  H04N1/00 ,  H04N5/23206 ,  H04N5/23238 ,  H04N5/23254 ,  H04N5/3415

摘要： Various examples are directed to systems and methods for detecting regions in video frames. For example, a computing device may receive a video comprising a plurality of frames and a video frame sequence of the plurality of frames. The computing device may select a plurality of scene point location from a first frame. The computing device may determine a plurality of columns in the first frame and fit a first sinusoidal function to a distribution of average column Y-axis displacements for the plurality of columns by column position. The computing device may determine a first difference based at least in part on the first scene point Y-axis displacement and an output of the first sinusoidal function at the X-axis position of the first scene point and determine that the first difference is greater than a threshold distance.

公开(公告)号：US09367924B2

公开(公告)日：2016-06-14

申请号：US14270624

申请日：2014-05-06

申请人： Siemens Aktiengesellschaft

发明人： Artem Gritsenko ,  Neil Birkbeck ,  Jingdan Zhang ,  Shaohua Kevin Zhou

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06K9/62

CPC分类号： G06T7/0097 ,  G06K9/6259 ,  G06T7/13 ,  G06T7/149 ,  G06T7/174 ,  G06T2200/04 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20116 ,  G06T2207/30056

摘要： A method and system for fully automatic liver segmentation in a multi-channel magnetic resonance (MR) image is disclosed. An initial liver boundary in the multi-channel MR image, such as an MR Dixon scan. The segmented initial liver boundary in the multi-channel MR image is refined based on features extracted from multiple channels of the multi-channel MR image using a trained boundary detector. The features may be extracted from an opposed channel and a water channel of an MR Dixon scan.

摘要翻译： 公开了一种在多通道磁共振（MR）图像中全自动肝分割的方法和系统。 多通道MR图像中的初始肝脏边界，例如MR Dixon扫描。 使用训练有素的边界检测器，基于从多通道MR图像的多个通道提取的特征来改进多通道MR图像中的分段初始肝脏边界。 特征可以从MR Dixon扫描的相对的通道和水通道中提取。

公开(公告)号：US09007662B2

公开(公告)日：2015-04-14

申请号：US14102226

申请日：2013-12-10

申请人： Canon Kabushiki Kaisha

发明人： Mizuki Hayakawa ,  Yuya Tanaka

IPC分类号： H04N1/04 ,  G06T7/00 ,  H04N1/00 ,  H04N1/203 ,  H04N1/10

CPC分类号： G06T7/0097 ,  H04N1/00681 ,  H04N1/0071 ,  H04N1/00713 ,  H04N1/00718 ,  H04N1/00737 ,  H04N1/00753 ,  H04N1/00769 ,  H04N1/00774 ,  H04N1/1017 ,  H04N1/203 ,  H04N1/2038

摘要： An image processing apparatus operative to properly obtain an original area when one or a plurality of originals exists. The image processing apparatus decides an image data area of an original from read image data read thereby. The image processing apparatus has an extracting unit for extracting a plurality of image areas from the read image data and a discriminating unit for discriminating whether or not tilt angles of the image areas extracted by the extracting unit are equal. If one or more tile angles of the image areas are not equal as a result of the discrimination by the discriminating unit, it is determined that each of the image areas is an image data area of the original on the assumption that there are a plurality of originals.

摘要翻译： 当存在一个或多个原稿时，图像处理装置可操作以适当地获得原始区域。 图像处理装置从读​​取的读取图像数据确定原稿的图像数据区域。 图像处理装置具有从读取的图像数据中提取多个图像区域的提取单元和用于鉴别由提取单元提取的图像区域的倾斜角度是否相等的判别单元。 如果作为鉴别单元的鉴别的结果，图像区域的一个或多个瓦片角度不相等，则假定每个图像区域是原始图像的图像数据区域，假设存在多个 原件。

公开(公告)号：US20140168715A1

公开(公告)日：2014-06-19

申请号：US14102226

申请日：2013-12-10

申请人： CANON KABUSHIKI KAISHA

发明人： Mizuki Hayakawa ,  Yuya Tanaka

IPC分类号： H04N1/203 ,  G06T7/00

CPC分类号： G06T7/0097 ,  H04N1/00681 ,  H04N1/0071 ,  H04N1/00713 ,  H04N1/00718 ,  H04N1/00737 ,  H04N1/00753 ,  H04N1/00769 ,  H04N1/00774 ,  H04N1/1017 ,  H04N1/203 ,  H04N1/2038

摘要： An image processing apparatus operative to properly obtain an original area when one or a plurality of originals exists. The image processing apparatus decides an image data area of an original from read image data read thereby. The image processing apparatus has an extracting unit for extracting a plurality of image areas from the read image data and a discriminating unit for discriminating whether or not tilt angles of the image areas extracted by the extracting unit are equal. If one or more tile angles of the image areas are not equal as a result of the discrimination by the discriminating unit, it is determined that each of the image areas is an image data area of the original on the assumption that there are a plurality of originals.

摘要翻译： 当存在一个或多个原稿时，图像处理装置可操作以适当地获得原始区域。 图像处理装置从读​​取的读取图像数据确定原稿的图像数据区域。 图像处理装置具有从读取的图像数据中提取多个图像区域的提取单元和用于鉴别由提取单元提取的图像区域的倾斜角度是否相等的判别单元。 如果作为鉴别单元的鉴别的结果，图像区域的一个或多个瓦片角度不相等，则假定每个图像区域是原始图像的图像数据区域，假设存在多个 原件。

公开(公告)号：US6151424A

公开(公告)日：2000-11-21

申请号：US709918

申请日：1996-09-09

申请人： Shin-yi Hsu

发明人： Shin-yi Hsu

IPC分类号： G06K9/00 ,  G06K9/64 ,  G06T5/00 ,  G06K9/36

CPC分类号： G06T7/0083 ,  G06K9/00201 ,  G06K9/0063 ,  G06K9/3241 ,  G06K9/6206 ,  G06T7/0081 ,  G06T7/0087 ,  G06T7/0097 ,  G06T2207/10028 ,  G06T2207/10036 ,  G06T2207/20016 ,  G06T2207/20084 ,  G06T2207/30181 ,  G06T2207/30212

摘要： The present invention features the use of the fundamental concept of color perception and multi-level resolution to perform scene segmentation and object/feature extraction in the context of self-determining and self-calibration modes. The technique uses only a single image, instead of multiple images as the input to generate segmented images. Moreover, a flexible and arbitrary scheme is incorporated, rather than a fixed scheme of segmentation analysis. The process allows users to perform digital analysis using any appropriate means for object extraction after an image is segmented. First, an image is retrieved. The image is then transformed into at least two distinct bands. Each transformed image is then projected into a color domain or a multi-level resolution setting. A segmented image is then created from all of the transformed images. The segmented image is analyzed to identify objects. Object identification is achieved by matching a segmented region against an image library. A featureless library contains full shape, partial shape and real-world images in a dual library system. The depth contours and height-above-ground structural components constitute a dual library. Also provided is a mathematical model called a Parzen window-based statistical/neural network classifier, which forms an integral part of this featureless dual library object identification system. All images are considered three-dimensional. Laser radar based 3-D images represent a special case.

摘要翻译： 本发明的特征在于使用颜色感知和多级分辨率的基本概念来在自我确定和自校准模式的上下文中执行场景分割和对象/特征提取。 该技术仅使用单个图像，而不是多个图像作为输入来生成分割图像。 此外，并入了灵活和任意的方案，而不是固定的分割分析方案。 该过程允许用户在分割图像之后使用任何适当的对象提取方式执行数字分析。 首先，检索图像。 然后将图像转换成至少两个不同的带。 然后将每个变换图像投影到彩色域或多级分辨率设置中。 然后从所有变换图像创建分割图像。 分析分割的图像以识别对象。 通过将分割区域与图像库匹配来实现对象识别。 一个无特征库在双库系统中包含完整的形状，部分形状和真实世界的图像。 深度轮廓和高度地面结构构件构成双重库。 还提供了一种称为Parzen基于窗口的统计/神经网络分类器的数学模型，其形成该无特征的双库对象识别系统的组成部分。 所有图像都被认为是三维的。 基于激光雷达的3-D图像代表特殊情况。

公开(公告)号：US5850465A

公开(公告)日：1998-12-15

申请号：US751449

申请日：1991-08-28

申请人： Kazuo Shimura ,  Yuuma Adachi ,  Shoji Hara ,  Nobuyoshi Nakajima ,  Wataru Ito

发明人： Kazuo Shimura ,  Yuuma Adachi ,  Shoji Hara ,  Nobuyoshi Nakajima ,  Wataru Ito

IPC分类号： G06K9/46 ,  G06T5/00 ,  G06T7/00 ,  G06F159/00

CPC分类号： G06T7/0081 ,  G06K9/4604 ,  G06T7/0012 ,  G06T7/0097 ,  G06T2207/10116 ,  G06T2207/20068 ,  G06T2207/20084 ,  G06T2207/20224 ,  G06T2207/30061 ,  G06T2207/30096 ,  Y10S128/92

摘要： An abnormal pattern detecting apparatus comprises a device for finding prospective abnormal patterns in a radiation image of an object from an image signal representing the radiation image, and a device for finding anatomical information about the object from the image signal. From the image signal components of the image signal, which represent the image information at positions in the vicinity of each prospective abnormal pattern, a characteristic measure calculating device calculates a plurality of characteristic measures for each prospective abnormal pattern. An abnormal pattern finding device utilizes the characteristic measures and the anatomical information in order to find a true abnormal pattern from the prospective abnormal patterns.

摘要翻译： 异常模式检测装置包括从表示放射线图像的图像信号中发现物体的放射线图像中的预期异常模式的装置，以及用于从图像信号中找到关于对象的解剖信息的装置。 特征测量计算装置根据每个预期异常模式附近的位置处的图像信息的图像信号的图像信号分量来计算每个预期异常模式的多个特征量度。 异常模式发现装置利用特征性措施和解剖信息，从预期的异常模式中找到真正的异常模式。

公开(公告)号：US5809161A

公开(公告)日：1998-09-15

申请号：US35987

申请日：1993-03-22

申请人： Glen William Auty ,  Peter Ian Corke ,  Paul Alexander Dunn ,  Ian Barry MacIntyre ,  Dennis Charles Mills ,  Benjamin Francis Simons ,  Murray John Jensen ,  Rodney Lavis Knight ,  David Stuart Pierce ,  Ponnampalam Balakumar

发明人： Glen William Auty ,  Peter Ian Corke ,  Paul Alexander Dunn ,  Ian Barry MacIntyre ,  Dennis Charles Mills ,  Benjamin Francis Simons ,  Murray John Jensen ,  Rodney Lavis Knight ,  David Stuart Pierce ,  Ponnampalam Balakumar

IPC分类号： G01P3/38 ,  G06T5/00 ,  G06T7/20 ,  G08G1/017 ,  G08G1/04 ,  G08G1/054 ,  G06K9/00

CPC分类号： G01P3/38 ,  G06K9/00785 ,  G06K9/3241 ,  G06T7/0081 ,  G06T7/0097 ,  G06T7/2053 ,  G08G1/017 ,  G08G1/04 ,  G08G1/054 ,  G06K2209/15 ,  G06T2207/10016 ,  G06T2207/30261

摘要： An object monitoring system includes a camera node (2) for monitoring movement of an object (18) to determine an acquisition time when an image of the object (18) is to be acquired and acquiring the image at the predetermined time. The system includes a camera (6) which is able to monitor moving objects (18), and image processing circuitry (10), responsive to the camera (6), which is able to detect a predetermined moving object (18) from other moving and static objects. From the image acquired, information identifying the object (18) can be automatically extracted. The system is particularly suited to monitoring and discriminating large vehicles (18) from other vehicles over a multi-lane roadway, and acquiring high resolution images of the large vehicles (18) at a predetermined acquisition point (22). Image data acquired by a plurality of camera nodes (2) can be sent over a digital telecommunications network (45) to a central image processing system (42) which can extract vehicle identifying data, such as licence plate details, and obtain information on vehicle travel between nodes(2).

摘要翻译： 对象监视系统包括：摄像机节点（2），用于监视对象（18）的移动，以确定当要获取对象（18）的图像并在预定时间获取图像时的获取时间。 该系统包括能够监测移动物体（18）的相机（6）和响应于照相机（6）的图像处理电路（10），其能够从其他移动中检测预定的移动物体（18） 和静态对象。 从所获取的图像可以自动提取识别对象（18）的信息。 该系统特别适用于通过多车道道路监视和区分大车辆（18）与其他车辆，并在预定采集点（22）获取大型车辆（18）的高分辨率图像。 由多个照相机节点（2）获取的图像数据可以通过数字电信网络（45）发送到中央图像处理系统（42），中央图像处理系统（42）可以提取诸如车牌细节的车辆识别数据，并且获得车辆信息 节点间行进（2）。