专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明申请

US20100182463A1 PROCESSING OF SENSOR VALUES IN IMAGING SYSTEMS 有权
标题翻译：成像系统传感器值的处理
公开(公告)号：US20100182463A1
公开(公告)日：2010-07-22
申请号：US12710681
申请日：2010-02-23
申请人： Szepo Robert Hung , Hsiang-Tsun Li
发明人： Szepo Robert Hung , Hsiang-Tsun Li
IPC分类号： H04N9/64
CPC分类号： H04N5/367 , H04N9/045
摘要： A digital image system identifies defective pixels of a digital image sensor based on sensor values of pixels positioned in at least two dimensions on the digital image sensor. The exemplary imaging system includes a buffer for receiving sensor values that are each associated with a pixel in the digital image sensor and electronics for comparing the sensor value associated with a test pixel to the sensor values of pixels positioned in at least two dimensions on the digital image sensor. The electronics determines whether the test pixel is a defective pixel based on the comparison.
摘要翻译：数字图像系统基于位于数字图像传感器上的至少二维的像素的传感器值来识别数字图像传感器的缺陷像素。示例性成像系统包括用于接收每个与数字图像传感器中的像素相关联的传感器值的缓冲器和用于将与测试像素相关联的传感器值与位于数字图像上至少二维的像素的传感器值进行比较的电子装置图像传感器。电子设备基于比较来确定测试像素是否是缺陷像素。

32. 发明申请

US20100157079A1 SYSTEM AND METHOD TO SELECTIVELY COMBINE IMAGES 审中-公开
标题翻译：选择合并图像的系统和方法
公开(公告)号：US20100157079A1
公开(公告)日：2010-06-24
申请号：US12340522
申请日：2008-12-19
申请人： Kalin M. Atanassov , Hsiang-Tsun Li , Hau Hwang
发明人： Kalin M. Atanassov , Hsiang-Tsun Li , Hau Hwang
IPC分类号： H04N5/228 , G06K9/32 , H04M1/00
CPC分类号： G06T5/50 , G06T3/0068 , G06T2207/10144 , G06T2207/10148 , G06T2207/10152 , G06T2207/20016 , H04N5/23232 , H04N5/23254 , H04N5/23267
摘要： Systems and methods to selectively combine images are disclosed. In a particular embodiment, an apparatus includes a registration circuit configured to generate a set of motion vector data based on first image data corresponding to a first image and second image data corresponding to a second image. The apparatus includes a combination circuit to selectively combine the first image data and adjusted second image data that corresponds to the second image data adjusted according to the motion vector data. The apparatus further includes a control circuit to control the combination circuit to generate third image data.
摘要翻译：公开了选择性地组合图像的系统和方法。在特定实施例中，一种装置包括：配准电路，配置为基于与第一图像对应的第一图像数据和对应于第二图像的第二图像数据生成一组运动矢量数据。该装置包括组合电路，用于选择性地组合第一图像数据和对应于根据运动矢量数据调整的第二图像数据的经调整的第二图像数据。该装置还包括控制电路以控制组合电路以产生第三图像数据。

33. 发明申请

US20090123082A1 BLOCK-BASED IMAGE STABILIZATION 有权
标题翻译：基于块的图像稳定
公开(公告)号：US20090123082A1
公开(公告)日：2009-05-14
申请号：US11938711
申请日：2007-11-12
申请人： Kalin Atanssov , Chinchuan Andrew Chiu , Hau Hwang , Hsiang-Tsun Li
发明人： Kalin Atanssov , Chinchuan Andrew Chiu , Hau Hwang , Hsiang-Tsun Li
IPC分类号： G06K9/36
CPC分类号： G06T5/002 , G06T5/50 , G06T7/223 , G06T2207/20021 , H04N5/23267
摘要： This disclosure describes image stabilization techniques for devices with image capture capabilities. An image capture device may capture two or more images and combine the image using the techniques described in this disclosure. In particular, the image capture device may compute motion vectors for a plurality of blocks of pixels of one of the images. In cases, the image capture device may also interpolate or extrapolate motion vectors for individual pixels or sub-blocks of pixels using the block motion vectors. The image capture device may then average the first and second images by averaging each of the pixels of the first image with pixels of the second image that correspond to a location indicated by the plurality of motion vectors. The techniques may be particularly effective in reducing blur in image information resulting from certain movements during image capture or use of certain image capture technologies.
摘要翻译：本公开描述了具有图像捕获能力的装置的图像稳定技术。图像捕获设备可以捕获两个或更多图像并且使用本公开中描述的技术组合图像。特别地，图像捕获设备可以计算多个图像中的一个像素块的运动矢量。在这种情况下，图像捕获装置还可以使用块运动矢量来内插或外推各个像素或像素子块的运动矢量。然后，图像捕获设备可以通过对与第一图像的每个像素对应于由多个运动矢量指示的位置对应的第二图像的像素对第一和第二图像进行平均。这些技术可以特别有效地减少在图像捕捉或使用某些图像捕捉技术期间由某些移动导致的图像信息模糊。

34. 发明授权

US09195898B2 Systems and methods for image recognition using mobile devices 有权
标题翻译：使用移动设备进行图像识别的系统和方法
公开(公告)号：US09195898B2
公开(公告)日：2015-11-24
申请号：US12537520
申请日：2009-08-07
申请人： Joseph Jyh-Huei Huang , Chang Yong , Hsiang-Tsun Li , Devender Akira Yamakawa , Jose Ricardo Dos Santos
发明人： Joseph Jyh-Huei Huang , Chang Yong , Hsiang-Tsun Li , Devender Akira Yamakawa , Jose Ricardo Dos Santos
IPC分类号： G06K9/00 , G06K9/20 , G06F17/30
CPC分类号： G06K9/20 , G06F17/30247 , G06K9/00671 , G06K9/6262
摘要： Implementations relate to systems and methods for real-time image recognition and mobile visual searching. A mobile device, such as a cellular phone, acquires an image and pre-processes the acquired image to generate a visual search query based on objects detected in the acquired image. The visual search query includes the acquired image or a query image extracted therefrom and metadata associated with the detected objects. The mobile device wirelessly communicates the visual search query to a remote server, and in response to the visual search query, the remote server recognizes an object in the query image based on the associated metadata. The remote server then generates information content based on the recognized object and communicates the information content to the mobile device to be presented via the mobile device.
摘要翻译：实现涉及用于实时图像识别和移动视觉搜索的系统和方法。诸如蜂窝电话的移动设备获取图像并对获取的图像进行预处理，以基于获取的图像中检测到的对象生成视觉搜索查询。视觉搜索查询包括获取的图像或从其提取的查询图像和与检测到的对象相关联的元数据。移动设备将视觉搜索查询无线地传送到远程服务器，并且响应于可视搜索查询，远程服务器基于相关联的元数据来识别查询图像中的对象。然后，远程服务器基于识别的对象生成信息内容，并将该信息内容传送到要通过移动设备呈现的移动设备。

35. 发明授权

US08384801B2 Scene-dependent auto exposure control 有权
标题翻译：场景相关的自动曝光控制
公开(公告)号：US08384801B2
公开(公告)日：2013-02-26
申请号：US11831612
申请日：2007-07-31
申请人： Szepo Robert Hung , Hsiang-Tsun Li , Jingqiang Li
发明人： Szepo Robert Hung , Hsiang-Tsun Li , Jingqiang Li
IPC分类号： H04N5/235
CPC分类号： G03B7/093 , H04N5/2351 , H04N5/2353 , H04N5/243 , H04N2007/145
摘要： A device has a processing unit to implement a set of operations to use both luma and chroma information from a scene of an image to dynamically adjust exposure time and sensor gain. The processing unit collects bright near grey pixels and high chroma pixels in the scene. Based on the collected pixels, brightness of the near grey pixels is increased to a predetermined level without saturation. At the same time, the high chroma pixels are kept away from saturation.
摘要翻译：一种设备具有处理单元，用于实现一组操作，以使用来自图像场景的亮度和色度信息来动态地调整曝光时间和传感器增益。处理单元收集场景中明亮的近灰色像素和高色度像素。基于所收集的像素，近灰色像素的亮度增加到预定的水平而不饱和。同时，高色度像素远离饱和度。

36. 发明授权

US08023758B2 Surface mesh matching for lens roll-off correction 有权
标题翻译：表面网格匹配用于镜头滚降校正
公开(公告)号：US08023758B2
公开(公告)日：2011-09-20
申请号：US11835220
申请日：2007-08-07
申请人： Szepo Robert Hung , Jingqiang Li , Hsiang-Tsun Li , Xin Zhong
发明人： Szepo Robert Hung , Jingqiang Li , Hsiang-Tsun Li , Xin Zhong
IPC分类号： G06K9/40
CPC分类号： G06T5/006 , G06T3/4007
摘要： A two-dimensional (2D) mesh is applied over a distortion surface to approximate a lens roll-off distortion pattern. The process to apply the 2D mesh distributes a plurality of grid points among the distortion pattern and sub-samples the distortion pattern to derive corrected digital gains at each grid location. Non-grid pixels underlying grid blocks having a grid point at each corner are adjusted based on the approximation of the lens roll-off for the grid points of the grid block. In one example, bilinear interpolation is used. The techniques universally correct lens roll-off distortion irregardless of the distortion pattern shape or type. The technique may also correct for green channel imbalance.
摘要翻译：将二维（2D）网格施加在失真表面上以近似透镜滚降失真图案。应用2D网格的过程在失真模式中分配多个网格点，并对失真模式进行子采样，以在每个网格位置导出校正的数字增益。基于网格块的网格点的镜头滚降的近似来调整在每个角上具有网格点的网格块下方的非网格像素。在一个示例中，使用双线性插值。这些技术无损于失真图案的形状或类型，普遍地校正镜头滚降。该技术也可能纠正绿色通道不平衡。

37. 发明申请

US20100271498A1 SYSTEM AND METHOD TO SELECTIVELY COMBINE VIDEO FRAME IMAGE DATA 有权
标题翻译：选择合并视频帧图像数据的系统和方法
公开(公告)号：US20100271498A1
公开(公告)日：2010-10-28
申请号：US12428354
申请日：2009-04-22
申请人： Hau Hwang , Hsiang-Tsun Li , Kalin M. Atanassov
发明人： Hau Hwang , Hsiang-Tsun Li , Kalin M. Atanassov
IPC分类号： H04N5/228
CPC分类号： H04N5/23248 , G06T5/50 , G06T7/32 , G06T2207/10016 , G06T2207/20016 , G06T2207/20021 , H04N5/23232 , H04N5/235 , H04N5/2355
摘要： Systems and methods to selectively combine video frame image data are disclosed. First image data corresponding to a first video frame and second image data corresponding to a second video frame are received from an image sensor. The second image data is adjusted by at least partially compensating for offsets between portions of the first image data with respect to corresponding portions of the second image data to produce adjusted second image data. Combined image data corresponding to a combined video frame is generated by performing a hierarchical combining operation on the first image data and the adjusted second image data.
摘要翻译：公开了选择性地组合视频帧图像数据的系统和方法。从图像传感器接收对应于第一视频帧的第一图像数据和对应于第二视频帧的第二图像数据。通过至少部分地补偿第一图像数据的部分之间相对于第二图像数据的相应部分的偏移来调整第二图像数据，以产生经调整的第二图像数据。通过对第一图像数据和经调整的第二图像数据执行分层组合操作来生成与组合视频帧相对应的组合图像数据。

38. 发明申请

US20100066871A1 BAD PIXEL CLUSTER DETECTION 失效
标题翻译： BAD像素集群检测
公开(公告)号：US20100066871A1
公开(公告)日：2010-03-18
申请号：US12233413
申请日：2008-09-18
申请人： Kalin Atanassov , Hsiang-Tsun Li , Hau Hwang , Babak Forutanpour
发明人： Kalin Atanassov , Hsiang-Tsun Li , Hau Hwang , Babak Forutanpour
IPC分类号： H04N9/64
CPC分类号： H04N5/3675
摘要： Systems and methods of bad pixel cluster detection are disclosed. In a particular embodiment, a method includes determining a correlation value corresponding to a correlation coefficient between image data and at least one bad pixel cluster pattern, and detecting a bad pixel cluster corresponding to the at least one bad pixel cluster pattern based on the correlation value exceeding a threshold.
摘要翻译：公开了不良像素簇检测的系统和方法。在特定实施例中，一种方法包括：确定与图像数据和至少一个不良像素簇图案之间的相关系数对应的相关值，以及基于相关值检测与至少一个不良像素簇图案对应的不良像素簇超过阈值。

39. 发明申请

US20090202176A1 SHARED BLOCK COMPARISON ARCHITECHTURE FOR IMAGE REGISTRATION AND VIDEO CODING 有权
标题翻译：用于图像注册和视频编码的共享块比较架构
公开(公告)号：US20090202176A1
公开(公告)日：2009-08-13
申请号：US12030820
申请日：2008-02-13
申请人： Hau Hwang , Hsiang-Tsun Li , Kalin Atanassov
发明人： Hau Hwang , Hsiang-Tsun Li , Kalin Atanassov
IPC分类号： G06K9/32
CPC分类号： H04N5/23248 , G06T7/30 , G06T2207/10016 , G06T2207/20021 , H04N5/23277 , H04N5/2355 , H04N5/2357 , H04N19/43 , H04N19/51 , H04N19/537 , H04N19/85
摘要： This disclosure describes an efficient architecture for an imaging device that supports image registration for still images and video coding of a video sequence. For image registration, the described architecture uses block-based comparisons of image blocks of a captured image relative to blocks of another reference image to support image registration on a block-by-block basis. For video coding, the described architecture uses block-based comparisons, e.g., to support for motion estimation and motion compensation. According to this disclosure, a common block comparison engine is used on a shared basis for both block-based image registration and block-based video coding. In this way, a hardware unit designed for block-based comparisons may be implemented so as to work in both the image registration process for still images and the video coding process for coding a video sequence.
摘要翻译：本公开描述了一种用于成像设备的有效架构，其支持用于静止图像的图像注册和视频序列的视频编码。对于图像注册，所描述的架构使用与相对于另一参考图像的块相关的捕获图像的图像块的基于块的比较，以在逐块的基础上支持图像注册。对于视频编码，所描述的架构使用基于块的比较，例如支持运动估计和运动补偿。根据本公开，公共块比较引擎在基于块的图像配准和基于块的视频编码的共享的基础上被使用。以这种方式，可以实现设计用于基于块的比较的硬件单元，以便在静止图像的图像注册处理和用于编码视频序列的视频编码处理两者中工作。

40. 发明申请

US20080150945A1 COMPLEXITY-ADAPTIVE 2D-TO-3D VIDEO SEQUENCE CONVERSION 失效
标题翻译：复杂自适应2D到3D视频序列转换
公开(公告)号：US20080150945A1
公开(公告)日：2008-06-26
申请号：US11615393
申请日：2006-12-22
申请人： Haohong Wang , Hsiang-Tsun Li , Sharath Manjunath
发明人： Haohong Wang , Hsiang-Tsun Li , Sharath Manjunath
IPC分类号： G06T15/10
CPC分类号： G06T7/50 , G06K9/20 , G06K2209/40 , G06T2207/10012 , H04N13/261 , H04N13/275
摘要： Techniques for complexity-adaptive and automatic two-dimensional (2D) to three-dimensional (3D) image and video conversion which classifies a frame of a 2D input into one of a flat image class and a non-flat image class are described. The flat image class frame is directly converted into 3D stereo for display. The frame that is classified as a non-flat image class is further processed automatically and adaptively, based on complexity, to create a depth map estimate. Thereafter, the non-flat image class frame is converted into a 3D stereo image using the depth map estimate or an adjusted depth map. The adjusted depth map is processed based on the complexity.
摘要翻译：描述了将2D输入的帧分成平面图像类和非平坦图像类之一的复杂度自适应和自动二维（2D）到三维（3D）图像和视频转换的技术。平面图像类框架直接转换成3D立体声显示。基于复杂度，被分类为非平面图像类的帧被自动地和自适应地进一步处理，以创建深度图估计。此后，使用深度图估计或调整深度图将非平面图像类帧转换成3D立体图像。调整后的深度图基于复杂度进行处理。

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