会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Picture image forming apparatus
    • 图像形成装置
    • US6005987A
    • 1999-12-21
    • US951713
    • 1997-10-16
    • Mitsuaki NakamuraYoshihiro KitamuraHiroshi Akagi
    • Mitsuaki NakamuraYoshihiro KitamuraHiroshi Akagi
    • H04N5/222G06T1/00G06T3/00G06T3/40G06T15/20H04N5/225H04N5/265H04N13/00G06K9/32
    • G06T3/4038G06T15/20H04N13/0239H04N5/23238G06T2207/10012H04N13/0051H04N13/0055H04N13/0296H04N2013/0081H04N2013/0088
    • In forming a panoramic picture image by compositing picture images dividedly imaged, the invention corrects deviations of images of an object at overlap regions caused by a difference in fields of view of imaging means or movement of an object to be imaged in which a picture image forming apparatus includes a picture image inputting device, a frame memory for storing divided picture images inputted from the picture image inputting device, a picture image position calculating unit for calculating positions of compositing the divided picture images, a picture image parallax sampling and processing unit for sampling parallax information among picture images from picture images including parallaxes in the overlap regions among contiguous divided picture images, an intermediate picture image forming and processing unit for forming a plurality of intermediate picture images from the picture images including the parallaxes and a picture image composition and processing unit for compositing a panoramic picture image from the divided picture images where the deviations of images in the overlap regions are corrected by the picture image parallax sampling and processing unit and the panoramic picture images are composited performing an interpolation by the intermediate picture images formed by the intermediate picture image forming and processing unit.
    • 在通过合成分割成像的图像图像来形成全景图像图像时,本发明校正由成像装置的视场差异或被成像对象的移动引起的重叠区域的对象的图像偏差,其中图像形成 装置包括图像输入装置,用于存储从图像输入装置输入的分割图像的帧存储器,用于计算合成分割图像图像的位置的图像位置计算单元,用于采样的图像视差采样和处理单元 来自图像的图像之间的视差信息包括连续分割图像之间的重叠区域中的视差,用于从包括视差的图像形成多个中间图像图像的中间图像图像形成和处理单元以及图像组成和处理 合成单位 通过由图像视差采样和处理单元校正重叠区域中的图像的偏差的分割图像图像和全景图像,通过由中间图像形成形成的中间图像图像合成进行内插的全景图像图像 和处理单元。
    • 2. 发明授权
    • Image synthesizing device and method
    • 图像合成装置及方法
    • US06292593B1
    • 2001-09-18
    • US09269031
    • 1999-03-18
    • Kazuyuki NakoMitsuaki NakamuraMasashi HirosawaHiroshi AkagiYoshihiro Kitamura
    • Kazuyuki NakoMitsuaki NakamuraMasashi HirosawaHiroshi AkagiYoshihiro Kitamura
    • G06K936
    • G06T5/006G06T7/30H04N1/3876
    • A one-dimensional image synthesizing unit 3 images an subject, and produces a plurality of image-to-be-combined signals expressing images-to-be-combined having overlapped regions. A central processing unit 5 first obtains matching of images of the subject for each of adjacent images-to-be-combined for all image-to-be-combined signals by center and large block matching processes, and detects the deviations of overlapped regions from the obtained matching. Next, in a small block matching process, on the basis of the deviations of the overlapped regions, a plurality of reference blocks and search regions are made to correspond to each other and are set in the respective overlapped regions, and the deviations of the images of the subject are detected in a unit of each search region in more detail than the deviations detected by the large block matching process. Finally, each of the images-to-be-combined is partially geometrically deformed so as to cancel the deviation of the image of the subject, the reference block and the search block are made coincident with each other, and all image-to-be-combined signals are combined to superimpose the respective images-to-be-combined, so that combined image signals are obtained.
    • 一维图像合成单元3对被摄体进行成像,并且生成表示具有重叠区域的待组合图像的多个图像组合信号。 中央处理单元5通过中心和大块匹配处理首先获得与待组合的所有图像信号相对应的每个相邻图像的对象的图像的匹配,并且检测重叠区域的偏差 获得匹配。 接下来,在小块匹配处理中,基于重叠区域的偏差,使多个参考块和搜索区域彼此对应并设置在各个重叠区域中,并且图像的偏差 以与大块匹配处理检测到的偏差更详细地检测每个搜索区域的单位。 最后,要组合的每个图像被部分地几何变形,以便消除被摄体的图像的偏差,使得参考块和搜索块彼此一致,并且所有图像将被 组合的信号被组合以叠加要组合的各个图像,从而获得组合的图像信号。
    • 3. 发明授权
    • Movement detecting apparatus with feature point extractor based on luminance gradient in current frame
    • 基于当前帧亮度梯度的特征点提取器的运动检测装置
    • US06650362B1
    • 2003-11-18
    • US09269033
    • 1999-03-18
    • Yasuhisa NakamuraYoshihiro KitamuraHiroshi Akagi
    • Yasuhisa NakamuraYoshihiro KitamuraHiroshi Akagi
    • H04N5228
    • G06T7/246H04N5/145
    • In connection with the detection of an amount of movement of an image such as a document image having a small gradient of brightness, it has been difficult to detect the amount by a representative point method, and a block matching method requires much time. An image (F1) at a time (T1), which has been imaged by moving an imaging section (1), is taken into a memory (2) and a feature point extracting section (3), where feature points of the image (F1) are extracted, and an image (F2) at a start time (T2) of the subsequent frame is taken in the memory (2) and the feature point extracting section (3). A correlation operating section (5) operates feature points of the image (F2) and the image (F1) in an area designated by a search area deciding section (4) to output an amount of movement.
    • 结合检测诸如具有小的亮度梯度的文档图像的图像的移动量​​,难以通过代表点法检测量,并且块匹配方法需要很多时间。 已经通过移动成像部分(1)成像的时间(T1)的图像(F1)被带入存储器(2)和特征点提取部分(3),其中图像的特征点 F1),并且在存储器(2)和特征点提取部(3)中取出后续帧的开始时刻(T2)的图像(F2)。 相关操作部分(5)在由搜索区域确定部分(4)指定的区域中操作图像(F2)和图像(F1)的特征点以输出移动量。
    • 4. 发明授权
    • Picture processing apparatus
    • 图像处理装置
    • US06215914B1
    • 2001-04-10
    • US09103877
    • 1998-06-24
    • Yasuhisa NakamuraYoshihiro KitamuraHiroshi AkagiMasashi HirosawaKazuyuki NakoMituaki Nakamura
    • Yasuhisa NakamuraYoshihiro KitamuraHiroshi AkagiMasashi HirosawaKazuyuki NakoMituaki Nakamura
    • G06K900
    • H04N1/3876
    • A picture processing apparatus which can reduce matching errors and shorten a processing time for matching. In the picture processing apparatus, a binarization circuit individually binarizes a pair of object picture signals to generate line picture signals. A feature point extract circuit extracts a plurality of feature point pixels for each reference area in the reference side line picture. A transforming circuit widens a line width of the search side line picture. A correlation computation circuit, for each reference area, finds a correlation between each pixel within a search area in the line picture whose line width has been widened and the feature point pixels. A composition processing section composites the pair of object picture signals based on the correlations. A picture processing apparatus which can adjust density and color tone of two pictures to be composited. At first, the picture processing apparatus finds overlapping areas of the two pictures to be processed and finds typical values typifying distributions of density values of pixels in the overlapping area of each picture, respectively. Next, it adjusts overall lightness of the two pictures by multiplying the density value of each pixel of one picture by a ratio of the typical value of the other picture to the typical value of one picture.
    • 一种能够减少匹配误差并缩短匹配处理时间的图像处理装置。 在图像处理装置中,二值化电路单独地二值化一对物体图像信号以生成线图像信号。 特征点提取电路提取参考侧线图像中的每个参考区域的多个特征点像素。 变换电路拓宽搜索侧线图像的线宽。 对于每个参考区域,相关计算电路找到线宽已经变宽的线条图像中的搜索区域内的每个像素与特征点像素之间的相关性。 合成处理部分基于相关性来合成该对物体图像信号。 一种图像处理装置,其可以调整要合成的两幅图像的浓度和色调。 首先,图像处理装置找到要处理的两个图像的重叠区域,并且分别找到代表每个图像的重叠区域中的像素的浓度值分布的典型值。 接下来,通过将一张图片的每个像素的浓度值乘以另一图像的典型值与一张图像的典型值的比率来调整两张照片的整体亮度。
    • 10. 发明授权
    • Still-image taking camera
    • 静态照相机
    • US5880778A
    • 1999-03-09
    • US635382
    • 1996-04-19
    • Hiroshi Akagi
    • Hiroshi Akagi
    • H04N5/232G06T3/00H04N1/04H04N1/32H04N1/387H04N1/41H04N5/907H04N5/91H04N5/225
    • H04N1/04H04N1/41H04N1/32128H04N2201/0414H04N2201/04787H04N2201/3225H04N2201/3242
    • In a still-image camera for taking a plurality of still-images of divisions of an object area and synthesizing the still images to obtain a highly fine image, an improvement is made to realize reduction in memory capacity and in processing time for image synthesizing, thus assuring real-time image processing at a reduced cost. The still-image camera includes an image input portion for picking-up a plurality of still-pictures of divisions of an object area, a divided image compressing portion for generating compressed divided-area images by compressing the divided still-images input from the image input portion, and a synthesizing information extracting portion for extracting information necessary for image synthesizing from the divided-area images input from the image input portion before compression. The still image camera further includes a compressed divided-image storage for storing therein compressed divided-area images and a compressed divided-image synthesizing portion for synthesizing compressed divided-area images stored in the compressed divided-image storage to a compressed entire-area image according to the synthesizing information extracted from the divided-area images by the synthesizing information extracting portion.
    • 在用于拍摄对象区域的划分的多个静止图像并合成静止图像以获得高精度图像的静止图像摄像机中,进一步改进了存储容量的降低和图像合成的处理时间, 从而以降低的成本确保实时图像处理。 静止图像摄像机包括:图像输入部分,用于拾取对象区域的划分的多个静态图像;分割图像压缩部分,用于通过压缩从图像输入的分割的静止图像来产生压缩的分割区域图像 输入部分和合成信息提取部分,用于从压缩前的图像输入部分输入的划分区域图像中提取图像合成所需的信息。 静止图像摄像机还包括压缩分割图像存储器,用于在其中存储压缩的分割区域图像和压缩分割图像合成部分,用于将存储在压缩分割图像存储器中的压缩分割区域图像合成到压缩全景图像 根据由合成信息提取部分从分割区域图像提取的合成信息。