专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20090245692A1 IMAGE REGISTRATION METHOD 审中-公开
标题翻译：图像注册方法
公开(公告)号：US20090245692A1
公开(公告)日：2009-10-01
申请号：US12293442
申请日：2007-03-23
申请人： Masatoshi Okutomi , Masao Shimizu , Soonkeun Chang
发明人： Masatoshi Okutomi , Masao Shimizu , Soonkeun Chang
IPC分类号： G06K9/32
CPC分类号： G06T7/32
摘要： The present invention provides a region-selection-based image registration method for estimating motions between an image of interest in an image sequence and a reference image in the image sequence which can be applied to the registration of the object having every geometry and by which the high-precision image registration with robustness to illumination variation and occlusion can be conducted.An image registration method for conducting a high-precision image registration between a reference image in an image sequence capturing an object and an image of interest in said image sequence, the method characterized in that a predetermined region on the reference image is set as a region of interest, when conducting the high-precision image registration, a motion parameter is estimated based on pixels of a mask image representing a region where the registration is performed precisely by a predetermined transformation within the region of interest that is set. The mask image is generated by utilizing the similarity evaluation between images.
摘要翻译：本发明提供了一种用于估计图像序列中感兴趣的图像与图像序列中的参考图像之间的运动的区域选择的图像配准方法，其可以应用于具有每个几何形状的对象的登记，可以进行对照明变化和遮挡的鲁棒性的高精度图像配准。一种用于在拍摄对象的图像序列中的参考图像与所述图像序列中的感兴趣的图像之间进行高精度图像配准的图像配准方法，其特征在于，将参考图像上的预定区域设置为区域感兴趣的是，当进行高精度图像配准时，基于所设置的感兴趣区域内的预定变换精确地表示表示注册的区域的掩模图像的像素来估计运动参数。通过利用图像之间的相似性评估来生成掩模图像。

2. 发明授权

US08089531B2 Image processor, image acquisition apparatus, storage medium of image processing program and image processing method 失效
标题翻译：图像处理器，图像采集装置，图像处理程序的存储介质和图像处理方法
公开(公告)号：US08089531B2
公开(公告)日：2012-01-03
申请号：US12323647
申请日：2008-11-26
申请人： Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
发明人： Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
IPC分类号： H04N5/262 , H04N5/228 , G06K9/40
CPC分类号： H04N5/217
摘要： An image processor includes an inter-superimposed-image deformation acquisition unit configured to acquire deformation information between superimposed images included in a multiple image in which images of a subject are superimposed, an image deformation unit configured to generate at least two deformed images by performing deformation processing with respect to the multiple image at least twice to be geometrically deformed based on the acquired deformation information between superimposed images, and a signal intensity relationship acquisition unit configured to acquire signal intensity relationship information indicative of a relationship between signal intensities of the superimposed images included in the multiple image. The image processor further includes a signal processing unit configured to perform addition processing of the at least two deformed images generated from the deformation processing by using the acquired signal intensity relationship information.
摘要翻译：图像处理器包括：叠加图像变形获取单元，被配置为获取包括在其中叠加有被摄体的图像的多个图像中的叠加图像之间的变形信息;图像变形单元，被配置为通过进行变形来生成至少两个变形图像基于所获取的叠加图像之间的变形信息，相对于所述多个图像进行至少两次要进行几何变形的处理;以及信号强度关系取得单元，被配置为获取指示叠加图像的信号强度之间的关系的信号强度关系信息在多个图像中。图像处理器还包括：信号处理单元，被配置为通过使用获取的信号强度关系信息来执行从变形处理产生的至少两个变形图像的加法处理。

3. 发明申请

US20100253796A1 Imaging Device And High-Resolution Processing Method Of Image 有权
标题翻译：成像设备和图像的高分辨率处理方法
公开(公告)号：US20100253796A1
公开(公告)日：2010-10-07
申请号：US11667766
申请日：2005-11-15
申请人： Takahiro Yano , Tomoyuki Nakamura , Masatoshi Okutomi , Masao Shimizu
发明人： Takahiro Yano , Tomoyuki Nakamura , Masatoshi Okutomi , Masao Shimizu
IPC分类号： H04N5/228 , G06K9/32
CPC分类号： H04N5/232 , H04N5/2625
摘要： The invention provides imaging device and high-resolution processing method of image which precisely generate high-resolution image by using image data with a little number of the pixels.An optical system images an optical image in an imaging unit (101), the imaged image is spatially discretized so as to sampled and converted into an image signal, thereby being recorded in a recording unit (105). Further, a timing at which the image is imaged by the imaging unit (101) is recorded in an imaging timing recording unit (107). A weight coefficient for imaged image is calculated by a weight calculating unit (104) by utilizing the timing information obtained by the imaging timing recording unit (107). A high-resolution processing unit (106) generates a high-resolution image by using the weighted information of the image generated by the weight calculating unit (104).
摘要翻译：本发明提供了通过使用具有少量像素的图像数据精确地生成高分辨率图像的图像的成像装置和高分辨率处理方法。光学系统在成像单元（101）中成像光学图像，将成像的图像在空间上离散化，以便被采样并转换为图像信号，从而被记录在记录单元（105）中。此外，由成像单元（101）将图像成像的定时记录在成像定时记录单元（107）中。通过利用由成像定时记录单元（107）获得的定时信息，通过权重计算单元（104）计算成像图像的权重系数。高分辨率处理单元（106）通过使用由权重计算单元（104）生成的图像的加权信息来生成高分辨率图像。

4. 发明申请

US20090174793A1 IMAGE PROCESSOR, IMAGE ACQUISITION APPARATUS, STORAGE MEDIUM OF IMAGE PROCESSING PROGRAM AND IMAGE PROCESSING METHOD 失效
标题翻译：图像处理器，图像采集装置，图像处理程序和图像处理方法的存储介质
公开(公告)号：US20090174793A1
公开(公告)日：2009-07-09
申请号：US12323647
申请日：2008-11-26
申请人： Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
发明人： Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
IPC分类号： H04N5/76 , G06K9/36 , G06K9/40 , H04N5/262
CPC分类号： H04N5/217
摘要： An image processor includes an inter-superimposed-image deformation acquisition unit configured to acquire deformation information between superimposed images included in a multiple image in which images of a subject are superimposed, an image deformation unit configured to generate at least two deformed images by performing deformation processing with respect to the multiple image at least twice to be geometrically deformed based on the acquired deformation information between superimposed images, and a signal intensity relationship acquisition unit configured to acquire signal intensity relationship information indicative of a relationship between signal intensities of the superimposed images included in the multiple image. The image processor further includes a signal processing unit configured to perform addition processing of the at least two deformed images generated from the deformation processing by using the acquired signal intensity relationship information.
摘要翻译：图像处理器包括：叠加图像变形获取单元，被配置为获取包括在其中叠加有被摄体的图像的多个图像中的叠加图像之间的变形信息;图像变形单元，被配置为通过进行变形来生成至少两个变形图像基于所获取的叠加图像之间的变形信息，相对于所述多个图像进行至少两次要进行几何变形的处理;以及信号强度关系取得单元，被配置为获取指示叠加图像的信号强度之间的关系的信号强度关系信息在多个图像中。图像处理器还包括：信号处理单元，被配置为通过使用获取的信号强度关系信息来执行从变形处理产生的至少两个变形图像的加法处理。

5. 发明授权

US08294778B2 Image processor, image acquisition apparatus, and storage medium of image processing program 失效
标题翻译：图像处理器，图像采集装置和图像处理程序的存储介质
公开(公告)号：US08294778B2
公开(公告)日：2012-10-23
申请号：US12323698
申请日：2008-11-26
申请人： Masatoshi Okutomi , Masao Shimizu , Takahiro Yano
发明人： Masatoshi Okutomi , Masao Shimizu , Takahiro Yano
IPC分类号： H04N5/228 , H04N5/232 , G03B13/00 , G06K9/62 , G06K9/64
CPC分类号： G02B7/365 , G06T7/37
摘要： An image processor includes a frequency transformation unit configured to perform frequency transformation processing with respect to a multiple image, and an inter-superimposed-image displacement acquisition unit that calculates a displacement amount between images forming superimposed images included in the multiple image by using a frequency-transformed image subjected to the frequency transformation processing by the frequency transformation unit.
摘要翻译：一种图像处理器包括：频率变换单元，被配置为对多个图像执行频率变换处理;以及帧间叠加图像位移获取单元，其通过使用频率来计算形成包括在所述多个图像中的叠加图像的图像之间的位移量经变频单元进行频率变换处理的变换图像。

6. 发明申请

US20100103175A1 METHOD FOR GENERATING A HIGH-RESOLUTION VIRTUAL-FOCAL-PLANE IMAGE 审中-公开
标题翻译：用于生成高分辨率虚拟平面图像的方法
公开(公告)号：US20100103175A1
公开(公告)日：2010-04-29
申请号：US12443844
申请日：2007-10-25
申请人： Masatoshi Okutomi , Kaoru Ikeda , Masao Shimizu
发明人： Masatoshi Okutomi , Kaoru Ikeda , Masao Shimizu
IPC分类号： G06T17/00
CPC分类号： G06T3/4053 , G06T2207/10012 , H04N13/243
摘要： The present invention provides a method for generating a high-resolution virtual-focal-plane image which is capable of generating a virtual-focal-plane image with an arbitrary desired resolution simply and rapidly by using multi-view images.The method of the present invention comprises a disparity estimating process step for estimating disparities by performing the stereo matching for multi-view images consisting of multiple images with different capturing positions and obtaining a disparity image; a region selecting process step for selecting an image among multi-view images as a basis image, setting all remaining images as reference images, and selecting a predetermined region on the basis image as a region of interest; a virtual-focal-plane estimating process step for estimating a plane in the disparity space for the region of interest based on the disparity image, and setting the estimated plane as a virtual-focal-plane; and an image integrating process step for obtaining image deformation parameters used for deforming each reference image to the basis image for the virtual-focal-plane, and generating the virtual-focal-plane image by deforming multi-view images with obtained image deformation parameters.
摘要翻译：本发明提供了一种用于生成能够通过使用多视点图像简单且快速地产生具有任意期望分辨率的虚拟焦平面图像的高分辨率虚拟焦平面图像的方法。本发明的方法包括视差估计处理步骤，用于通过对由具有不同拍摄位置的多个图像组成的多视点图像执行立体匹配来估计不同，并获得视差图像; 区域选择处理步骤，用于选择多视点图像中的图像作为基础图像，将所有剩余图像设置为参考图像，并且选择基础图像上的预定区域作为关注区域; 虚拟焦平面估计处理步骤，用于基于视差图像估计感兴趣区域的视差空间中的平面，并将估计平面设置为虚拟焦平面; 以及图像合成处理步骤，用于获得用于使每个参考图像变形为虚拟焦平面的基础图像的图像变形参数，以及通过使获得的图像变形参数变形多视图图像来生成虚拟焦平面图像。

7. 发明申请

US20060133641A1 Multi-parameter highly-accurate simultaneous estimation method in image sub-pixel matching and multi-parameter highly-accurate simultaneous estimation program 失效
公开(公告)号：US20060133641A1
公开(公告)日：2006-06-22
申请号：US10542329
申请日：2003-11-20
申请人： Masao Shimizu , Masatoshi Okutomi
发明人： Masao Shimizu , Masatoshi Okutomi
IPC分类号： G06K9/00
CPC分类号： G06K9/46 , G06T2200/32
摘要： In consideration of N-dimensional similarity, a multiparameter high precision concurrent estimation method and a multiparameter high precision concurrent estimation program in image subpixel matching, which can estimate a correspondence parameter between images precisely, concurrently, and stably with a small amount of computation at high speed. The method comprises the steps of: determining a sub-sampling position where the N-dimensional similarity value between images obtained at discrete positions is maximum or minimum on a line in parallel with a certain parameter axis, and determining an N-dimensional hyperplane that most approximates the determined sub-sampling position; determining N of the N-dimensional hyperplanes with respect to each parameter axis; determining an intersection point of N of the N-dimensional hyperplanes; and setting the intersection point as a sub-sampling grid estimation position for the correspondence parameter between images that gives a maximum value or a minimum value of N-dimensional similarity in the N-dimensional similarity space.

8. 发明授权

US07580065B2 Movement decision method for acquiring sub-pixel motion image appropriate for super resolution processing and imaging device using the same 失效
标题翻译：用于获取适合于超分辨率处理的子像素运动图像的运动判定方法和使用其的成像装置
公开(公告)号：US07580065B2
公开(公告)日：2009-08-25
申请号：US10572172
申请日：2005-04-12
申请人： Masao Shimizu , Masatoshi Okutomi
发明人： Masao Shimizu , Masatoshi Okutomi
IPC分类号： H04N5/262 , H04N5/225 , H04N9/04
CPC分类号： G06T3/4069
摘要： The present invention provides a movement decision method for determining direction and distance of one-dimensional movement of image capturing object or image capturing element for capturing two-dimensional sub-pixel motion image suitable for super-resolution processing, and an image capturing device using this movement decision method.while image capturing object is moved along a predetermined one-dimensional moving direction, sequential image of image capturing object is captured by fixed image capturing device, sequential image is set to two-dimensional sub-pixel motion image suitable for super-resolution processing, and one-dimensional moving direction of image capturing object in a coordinate system normalized by aspect ratio of pixel of image capturing element within image capturing device is determined to p/q of a rational number, wherein: one pixel of vertical direction of coordinate system is divided by an integer p, and one pixel of horizontal direction of coordinate system is divided by an integer q.
摘要翻译：本发明提供了一种用于确定用于捕获适合于超分辨率处理的二维子像素运动图像的图像捕获对象或图像捕获元件的一维运动的方向和距离的运动判定方法，以及使用该方法的图像捕获装置运动决策方法。当图像拍摄对象沿着预定的一维移动方向移动时，图像捕获对象的顺序图像被固定图像捕获装置捕获，顺序图像被设置为适合于超分辨率处理的二维子像素运动图像，以及将由图像拍摄装置内的图像拍摄元件的像素的高宽比归一化的坐标系中的图像拍摄对象的一维移动方向确定为有理数的p / q，其中：分割坐标系的垂直方向的一个像素乘以整数p，将坐标系的水平方向的一个像素除以整数q。

9. 发明申请

US20070296829A1 Imaging Device, Imaging System and Photography Method of Image 审中-公开
标题翻译：成像设备，成像系统和图像摄影方法
公开(公告)号：US20070296829A1
公开(公告)日：2007-12-27
申请号：US11667763
申请日：2005-11-15
申请人： Tomoyuki Nakamura , Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
发明人： Tomoyuki Nakamura , Takahiro Yano , Masatoshi Okutomi , Masao Shimizu
IPC分类号： H04N5/235
CPC分类号： H04N5/232 , H04N5/2251 , H04N5/2625
摘要： The invention provides an imaging device, an imaging system and an image photography method which can construct an image having a higher resolution than a photographed image. The imaging device is constituted by an optical imaging unit 11 (an optical imaging means for imaging an image of a subject), an imaging unit 12 (a means for converting an image imaged optically into an image signal that is discretized spatially and is sampled), an image processing unit 15 (a means for generating a high-resolution image from image signals of multiple frames), a moving velocity detecting unit 13 (a means for detecting a status change of the imaging device itself), and an imaging timing deciding unit 14 (a means for deciding a imaging timing). The imaging device is constituted such as to construct the high-resolution image from an imaging element with a little number of the pixels.
摘要翻译：本发明提供一种成像装置，成像系统和图像摄影方法，其可以构造具有比拍摄图像更高的分辨率的图像。成像装置由光学成像单元11（用于对对象的图像进行成像的光学成像装置），成像单元12（用于将光学成像的图像转换成空间离散化并被采样的图像信号的装置），图像处理单元15（用于从多帧的图像信号生成高分辨率图像的装置），移动速度检测单元13（用于检测成像装置本身的状态变化的装置）和成像定时决定单元14（用于决定成像定时的装置）。成像装置被构造成从具有少量像素的成像元件构造高分辨率图像。

10. 发明申请

US20070035621A1 Movement decision method for acquiring sub-pixel motion image appropriate for super resolution processing and imaging device using the same 失效
标题翻译：用于获取适合于超分辨率处理的子像素运动图像的运动判定方法和使用其的成像装置
公开(公告)号：US20070035621A1
公开(公告)日：2007-02-15
申请号：US10572172
申请日：2005-04-12
申请人： Masao Shimizu , Masatoshi Okutomi
发明人： Masao Shimizu , Masatoshi Okutomi
IPC分类号： H04N7/18 , H04N5/225
CPC分类号： G06T3/4069
摘要： The present invention provides a movement decision method for determining direction and distance of one-dimensional movement of image capturing object or image capturing element for capturing two-dimensional sub-pixel motion image suitable for super-resolution processing, and an image capturing device using this movement decision method. while image capturing object is moved along a predetermined one-dimensional moving direction, sequential image of image capturing object is captured by fixed image capturing device, sequential image is set to two-dimensional sub-pixel motion image suitable for super-resolution processing, and one-dimensional moving direction of image capturing object in a coordinate system normalized by aspect ratio of pixel of image capturing element within image capturing device is determined to p/q of a rational number, wherein: one pixel of vertical direction of coordinate system is divided by an integer p, and one pixel of horizontal direction of coordinate system is divided by an integer q.
摘要翻译：本发明提供了一种用于确定用于捕获适合于超分辨率处理的二维子像素运动图像的图像捕获对象或图像捕获元件的一维运动的方向和距离的运动判定方法，以及使用该方法的图像捕获装置运动决策方法。当图像拍摄对象沿着预定的一维移动方向移动时，图像捕获对象的顺序图像被固定图像捕获装置捕获，顺序图像被设置为适合于超分辨率处理的二维子像素运动图像，以及将由图像拍摄装置内的图像拍摄元件的像素的高宽比归一化的坐标系中的图像拍摄对象的一维移动方向确定为有理数的p / q，其中：分割坐标系的垂直方向的一个像素乘以整数p，将坐标系的水平方向的一个像素除以整数q。

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