专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20060197761A1 Image processor and image processing method for a vehicle 有权
标题翻译：一种车辆的图像处理器和图像处理方法
公开(公告)号：US20060197761A1
公开(公告)日：2006-09-07
申请号：US11366091
申请日：2006-03-02
申请人： Masayasu Suzuki , Ken Oizumi , Takeshi Akatsuka
发明人： Masayasu Suzuki , Ken Oizumi , Takeshi Akatsuka
IPC分类号： G06T15/20
CPC分类号： H04N7/181 , G06K2009/2045 , G06T5/006
摘要： An image processor is disclosed for a vehicle having a plurality of cameras and a monitor that displays a panoramic image derived from multiple images generated by the plurality of cameras. The processor includes input buffers for storing camera image data captured through respective camera modules and output buffer for storing a panoramic image. The camera image data for generating the panoramic image are retrieved from input buffers. The camera image data are stored in an output buffer using an reconfigured address conversion table. The reconfigured address conversion table is an address conversion table which is obtained by reconfiguring an address conversion table when camera modules are assumed to be free of vehicle installation errors. The reconfiguration is performed on the basis of parameters which are used to correct vehicle installation errors of camera modules.
摘要翻译：公开了一种用于具有多个照相机的车辆的图像处理器，以及显示由多个照相机产生的多个图像导出的全景图像的监视器。处理器包括用于存储通过相应摄像机模块捕获的照相机图像数据和用于存储全景图像的输出缓冲器的输入缓冲器。从输入缓冲器检索用于产生全景图像的相机图像数据。相机图像数据使用重新配置的地址转换表存储在输出缓冲器中。重新配置的地址转换表是当相机模块被假定为没有车辆安装错误时通过重新配置地址转换表而获得的地址转换表。基于用于校正相机模块的车辆安装错误的参数来执行重新配置。

72. 发明申请

US20060152589A1 Imaging and measurement system 审中-公开
标题翻译：成像和测量系统
公开(公告)号：US20060152589A1
公开(公告)日：2006-07-13
申请号：US10528990
申请日：2003-09-25
申请人： Steven Morrison , Stuart Clarke , Laurence Linnett
发明人： Steven Morrison , Stuart Clarke , Laurence Linnett
IPC分类号： H04N5/228 , G06K9/20 , G06K9/36
CPC分类号： G06K9/209 , G06K2009/2045 , G06T5/50 , G06T7/30 , G06T7/74 , G06T7/80
摘要： Apparatus and method for presenting a highly spatially accurate visualisation of a scene from which measurements can be taken. A sensor is located in relation to a camera, and provides positional characteristics of the camera as it collects frames of video images. Using the positional characteristics the frames are corrected. The corrected frames are then synchronised to form an accurate mosaic of a scene. Example embodiments are described where the moving camera is used to survey or inspect underwater apparatus, roads, runways, railways, crime or accident scenes, archaeological digs and the inside of boilers, chimneys and pipelines.
摘要翻译：用于呈现可以进行测量的场景的高空间准确可视化的装置和方法。传感器相对于摄像机定位，并且在收集视频图像帧时提供相机的位置特性。使用位置特性校正帧。然后校正的帧被同步以形成场景的精确马赛克。描述示例性实施例，其中使用移动摄像机来检查或检查水下设备，道路，跑道，铁路，犯罪或事故场景，考古挖掘以及锅炉，烟囱和管道内部。

73. 发明申请

US20060072852A1 Deghosting mosaics using multiperspective plane sweep 审中-公开
标题翻译：使用多平面扫描的去主体马赛克
公开(公告)号：US20060072852A1
公开(公告)日：2006-04-06
申请号：US11286567
申请日：2005-11-22
申请人： Sing Bing Kang , Richard Szeliski , Mattew Uyttendaele
发明人： Sing Bing Kang , Richard Szeliski , Mattew Uyttendaele
IPC分类号： G06K9/32 , G06K9/36
CPC分类号： G06T5/20 , G06K9/32 , G06K2009/2045 , G06T3/00 , G06T5/003 , G06T7/30 , G06T7/55 , G06T15/503
摘要： A system and method for deghosting mosaics provides a novel multiperspective plane sweep approach for generating an image mosaic from a sequence of still images, video images, scanned photographic images, computer generated images, etc. This multiperspective plane sweep approach uses virtual camera positions to compute depth maps for columns of overlapping pixels in adjacent images. Object distortions and ghosting caused by image parallax when generating the image mosaics are then minimized by blending pixel colors, or grey values, for each computed depth to create a common composite area for each of the overlapping images. Further, the multiperspective plane sweep approach described herein is both computationally efficient, and applicable to both the case of limited overlap between the images used for creating the image mosaics, and to the case of extensive or increased image overlap.
摘要翻译：用于消除幻影的马赛克的系统和方法提供了一种新颖的多平面扫描方法，用于从静止图像，视频图像，扫描摄影图像，计算机生成的图像等的序列生成图像马赛克。该多平面扫描方法使用虚拟相机位置来计算相邻图像中重叠像素列的深度图。然后通过为每个计算的深度混合像素颜色或灰度值来最小化由图像视差产生的图像马赛克引起的对象失真和重影，以为每个重叠图像创建公共复合区域。此外，本文描述的多平面扫描方法在计算上是有效的，并且适用于用于创建图像马赛克的图像之间的有限重叠的情况以及广泛或增加的图像重叠的情况。

74. 发明申请

US20050220361A1 Image generation apparatus, image generation system and image synthesis method 失效
标题翻译：图像生成装置，图像生成系统和图像合成方法
公开(公告)号：US20050220361A1
公开(公告)日：2005-10-06
申请号：US11086677
申请日：2005-03-23
申请人： Masami Yamasaki
发明人： Masami Yamasaki
IPC分类号： G06T3/00 , G06K9/32 , G06K9/36 , H04N5/225 , H04N5/232 , H04N5/262 , H04N7/18
CPC分类号： G06K9/32 , G06K9/00785 , G06K2009/2045
摘要： A surveillance system includes an image deformation unit for deforming the image captured or picked up by a surveillance camera so that the appearance of a specified region within this image has the same geometric shape as that of its corresponding region on the map, and an image synthesis display unit operable to extract the specific region of the deformed image and synthesize it in the corresponding map region for on-screen visualization, obtaining the mutual relationship of a plurality of images.
摘要翻译：监视系统包括图像变形单元，用于使由监视摄像机拍摄或拾取的图像变形，使得该图像内的指定区域的外观具有与其对应区域相同的几何形状，以及图像合成显示单元，其可操作以提取变形图像的特定区域并将其合成在相应的地图区域中用于屏幕可视化，获得多个图像的相互关系。

75. 发明申请

US20050111753A1 Image mosaicing responsive to camera ego motion 审中-公开
标题翻译：图像拼接响应相机自我运动
公开(公告)号：US20050111753A1
公开(公告)日：2005-05-26
申请号：US10835596
申请日：2004-04-29
申请人： Shmuel Peleg , Alexander Rav-Acha , Yael Shor
发明人： Shmuel Peleg , Alexander Rav-Acha , Yael Shor
IPC分类号： G06T3/40 , G06K9/36 , G06K9/00
CPC分类号： G06T3/4038 , G06K9/209 , G06K9/32 , G06K2009/2045
摘要： A method of generating a mosaic from a plurality of camera images of a scene acquired by a camera moving relative to the scene, the method comprising: associating with each camera image a value of at least one variable so that the variable is a substantially a linear function of a spatial coordinate that defines the locations of the camera at which it acquires the images by requiring that a coordinate of pixels in the camera images that image a same feature in the scene is substantially a linear function of the variable; and generating the mosaic responsive to the at least one variable.
摘要翻译：一种从由相机相对于场景移动的相机移动的场景的多个相机图像生成马赛克的方法，所述方法包括：将每个相机图像与至少一个变量的值相关联，使得所述变量基本上是线性的空间坐标的功能，其通过要求在场景中对相同特征进行成像的摄像机图像中的像素的坐标基本上是该变量的线性函数来定义其获取图像的相机的位置; 以及响应所述至少一个变量产生所述马赛克。

76. 发明申请

US20050084175A1 Large-area imaging by stitching with array microscope 审中-公开
标题翻译：用阵列显微镜拼接大面积成像
公开(公告)号：US20050084175A1
公开(公告)日：2005-04-21
申请号：US10687432
申请日：2003-10-16
申请人： Artur Olszak
发明人： Artur Olszak
IPC分类号： G02B21/36 , G06K9/36 , G06T3/40
CPC分类号： G06T3/4038 , G02B21/367 , G06K9/00134 , G06K2009/2045 , H04N1/3876
摘要： An imaging apparatus consists of multiple miniaturized microscopes arranged into an array capable of simultaneously imaging a portion of an object. A step-and-repeat approach is followed to scan the object and generate multiple sets of checkerboard images. In order to improve the quality of the composite image produced by concatenation or stitching of the checkerboard images, the performance of each microscope is normalized to the same base reference for each relevant optical-system property. Correction factors are developed through calibration to equalize the spectral response measured at each detector; to similarly balance the gains and offsets of the detector/light-source combinations associated with the various objectives; to correct for geometric misalignments between microscopes; and to correct optical and chromatic aberrations in each objective.
摘要翻译：成像装置由布置成阵列的多个微型显微镜组成，能够同时成像物体的一部分。跟踪扫描对象并生成多组棋盘图像的重复步骤。为了提高棋盘图像的拼接或缝合产生的复合图像的质量，每个显微镜的性能对于每个相关的光学系统属性归一化为相同的基准参考。通过校准开发校正因子以均衡每个检测器处测得的光谱响应; 类似地平衡与各种目标相关联的检测器/光源组合的增益和偏移; 以校正显微镜之间的几何不对准; 并纠正每个目标中的光学和色差。

77. 发明授权

US06704460B1 Remote mosaic imaging system having high-resolution, wide field-of-view and low bandwidth 失效
标题翻译：遥控马赛克成像系统具有高分辨率，宽视野和低带宽
公开(公告)号：US06704460B1
公开(公告)日：2004-03-09
申请号：US09613521
申请日：2000-07-10
申请人： Michael C. Pitruzzello , Marc W. Crooks , Troy L. Hester
发明人： Michael C. Pitruzzello , Marc W. Crooks , Troy L. Hester
IPC分类号： G06K936
CPC分类号： G06K9/0063 , G06K9/32 , G06K2009/2045 , G06T3/4038 , H04N5/23203 , H04N5/3415
摘要： The Remote Mosaic Imaging System having High-Resolution, Wide Field-of-View and Low Bandwidth (“Remote Mosaic System”) uses image frame synchronization and multiplexing to reduce the bandwidth needed to transmit the plurality of images to a remote location. The Remote Mosaic System employs a plurality of remote sensors to create a plurality of images. The use of readily available and inexpensive commercial imaging sensors significantly decreases the cost of the system while greatly increasing the capabilities of the imaging system to cover virtually any target space with virtually any desired resolution.
摘要翻译：具有高分辨率，宽视场和低带宽的远程马赛克成像系统（“远程马赛克系统”）使用图像帧同步和多路复用来减少将多个图像发送到远程位置所需的带宽。远程马赛克系统采用多个远程传感器来创建多个图像。使用容易获得和便宜的商业成像传感器显着降低了系统的成本，同时大大增加了成像系统几乎覆盖任何目标空间的能力，实际上任何所需的分辨率。

78. 发明授权

US06694064B1 Digital aerial image mosaic method and apparatus 失效
标题翻译：数字航空影像拼接方法及装置
公开(公告)号：US06694064B1
公开(公告)日：2004-02-17
申请号：US09718440
申请日：2000-11-20
申请人： Cody Benkelman
发明人： Cody Benkelman
IPC分类号： G06K936
CPC分类号： G06K9/32 , G06K9/0063 , G06K2009/2045 , G06T3/4038
摘要： A computer-implemented method and system for use in alignment of multiple digital images to form a mosaic image involves selecting multiple search site points (SSPs) in an overlapping area of a pair of the digital images and searching for an interesting point (IP) near each of the SSPs. The system involves the calculation of a numeric interest measure (IM) at each of multiple IP-candidate sites near the SSPs. The IM is indicative of the presence of image features at the IP-candidate site and provides a basis for comparing the IP-candidate sites at each of the SSPs and selecting the IP-candidate site having the most significant IM. In a preferred embodiment, IP-candidate sites having an IM that does not exceed a predetermined minimum threshold are discarded. The method also involves locating a tie point (TP) on an overlapping one of the digital images correlating to the IP. The TP together with the IP comprise a tie point pair (TPP) that can be used to calculate and apply geometric transformations to align the images and thereby form a seamless mosaic. The system and method may also involve radiometric balancing of the images to reduce tonal mismatch.
摘要翻译：用于对准多个数字图像以形成马赛克图像的计算机实现的方法和系统涉及在一对数字图像的重叠区域中选择多个搜索站点点（SSP），并且搜索靠近的一个有趣点（IP）每个SSP。该系统涉及在SSP附近的多个IP候选站点的每一个处计算数字兴趣度量（IM）。 IM表示在IP候选站点处存在图像特征，并且提供了用于比较每个SSP处的IP候选站点并选择具有最重要IM的IP候选站点的基础。在优选实施例中，丢弃具有不超过预定最小阈值的IM的IP候选站点。该方法还涉及在与IP相关的数字图像的重叠的一个上定位连接点（TP）。 TP与IP一起包括一个连接点对（TPP），可以用于计算和应用几何变换以对齐图像，从而形成无缝镶嵌。该系统和方法还可以涉及图像的辐射平衡以减少色调失配。

79. 发明申请

US20030179923A1 Aligning rectilinear images in 3D through projective registration and calibration 有权
公开(公告)号：US20030179923A1
公开(公告)日：2003-09-25
申请号：US10370280
申请日：2003-02-18
发明人： Yalin Xiong , Ken Turkowski
IPC分类号： G06K009/00
CPC分类号： G06T15/506 , G06K9/32 , G06K2009/2045 , G06T3/4038 , G06T7/32 , G06T15/503
摘要： An improved apparatus and method for creating high quality virtual reality panoramas is disclosed that yields dramatic improvements during the authoring and projecting cycles, with speeds up to several orders of magnitude faster than prior systems. In a preferred embodiment, a series of rectilinear images taken from a plurality of rows are pairwise registered with one another, and locally optimized using a pairwise objective function (local error function) that minimizes certain parameters in a projective transformation, using an improved iterative procedure. The local error function values for the pairwise registrations are then saved and used to construct a quadratic surface to approximate a global optimization function (global error function). The chain rule is used to avoid the direct evaluation of the global objective function, saving computation. In one embodiment concerning the blending aspect of the present invention, an improved procedure is described that relies on Laplacian and Gaussian pyramids, using a blend mask whose boundaries are determined by the grassfire transform. An improved iterative procedure is disclosed for the blending that also determines at what level of the pyramid to perform blending, and results in low frequency image components being blended over a wider region and high frequency components being blended over a narrower region. Human interaction and input is also provided to allow manual projective registration, initial calibration and feedback in the selection of photos and convergence of the system.

80. 发明申请

US20020114536A1 Aligning rectilinear images in 3D through projective registration and calibration 有权
公开(公告)号：US20020114536A1
公开(公告)日：2002-08-22
申请号：US10077102
申请日：2002-02-14
发明人： Yalin Xiong , Ken Turkowski
IPC分类号： G06K009/36
CPC分类号： G06T15/506 , G06K9/32 , G06K2009/2045 , G06T3/4038 , G06T7/32 , G06T15/503
摘要： An improved apparatus and method for creating high quality virtual reality panoramas is disclosed that yields dramatic improvements during the authoring and projecting cycles, with speeds up to several orders of magnitude faster than prior systems. In a preferred embodiment, a series of rectilinear images taken from a plurality of rows are pairwise registered with one another, and locally optimized using a pairwise objective function (local error function) that minimizes certain parameters in a projective transformation, using an improved iterative procedure. The local error function values for the pairwise registrations are then saved and used to construct a quadratic surface to approximate a global optimization function (global error function). The chain rule is used to avoid the direct evaluation of the global objective function, saving computation. In one embodiment concerning the blending aspect of the present invention, an improved procedure is described that relies on Laplacian and Gaussian pyramids, using a blend mask whose boundaries are determined by the grassfire transform. An improved iterative procedure is disclosed for the blending that also determines at what level of the pyramid to perform blending, and results in low frequency image components being blended over a wider region and high frequency components being blended over a narrower region. Human interaction and input is also provided to allow manual projective registration, initial calibration and feedback in the selection of photos and convergence of the system.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式