公开(公告)号：US10861215B2

公开(公告)日：2020-12-08

申请号：US16181288

申请日：2018-11-05

Applicant: QUALCOMM Incorporated

Inventor： Vinay Melkote Krishnaprasad ,  Sudipto Banerjee ,  Pawan Kumar Baheti ,  Ajit Venkat Rao

IPC: G06T15/00 ,  G06T7/536 ,  G06T7/73 ,  G06K9/32 ,  G06F3/01

Abstract: A method and a system for warping a rendered frame is disclosed. On a host device of a split-rendering system, the method includes generating the rendered frame based on head tracking information of a user. The method also includes identifying a region of interest (ROI) of the rendered frame. The method also includes generating metadata for a warping operation from the ROI. The method further include transmitting the rendered frame and the metadata for a warping operation of the rendered frame. On a client device of the split-rendering system, the method includes transmitting head tracking information of a user by a client device. The method also includes receiving the rendered frame and metadata. The method further includes warping the rendered frame using the metadata and display pose information. The host device and the client device may be combined into an all-in-one head mounted display.

公开(公告)号：US10244164B1

公开(公告)日：2019-03-26

申请号：US15701062

申请日：2017-09-11

Applicant: QUALCOMM Incorporated

Inventor： Sudipto Banerjee ,  Pushkar Gorur Sheshagiri ,  Pawan Kumar Baheti ,  Ajit Deepak Gupte ,  Ajit Venkat Rao

IPC: H04N5/232 ,  G06T3/40 ,  G06T3/00 ,  G06T7/292 ,  G06T7/50

Abstract: A method performed by an electronic device is described. The method includes receiving a plurality of images from a first camera with a first field of view and a second plurality of images from a second camera with a second field of view. An overlapping region exists between the first field of view and the second field of view. The method also includes predicting a disparity of a moving object present in a first image of the first plurality of images. The moving object is not present in a corresponding second image of the second plurality of images. The method further includes determining warp vectors based on the predicted disparity. The method additionally includes combining an image from the first plurality of images with an image from the second plurality of images based on the determined warp vectors.

公开(公告)号：US20190020802A1

公开(公告)日：2019-01-17

申请号：US15649229

申请日：2017-07-13

Applicant: QUALCOMM Incorporated

Inventor： Vinay Melkote Krishnaprasad ,  Pushkar Gorur Sheshagiri ,  Pawan Kumar Baheti ,  Ajit Deepak Gupte ,  Ajit Venkat Rao

IPC: H04N5/232 ,  G06T3/40 ,  H04N5/247

CPC classification number: H04N5/2327 ,  G06T3/4038 ,  G06T5/50 ,  G06T2207/20221 ,  H04N5/247

Abstract: Techniques are described for addressing rolling shutter delay and in some cases rolling shutter delay and stabilization. Processing circuits may receive image content in overlapping portions of images, and may adjust the image content until there is overlap in the overlapping portions. Processing circuits may also receive information of deviation of the device from a common reference. Based on the overlapping image content, the deviation of the device from the common reference, and image content in non-overlapping portions, the processing circuits may determine mapping of coordinates to a rectangular mesh for generating an equirectangular image.

公开(公告)号：US09591237B2

公开(公告)日：2017-03-07

申请号：US14684227

申请日：2015-04-10

Applicant: QUALCOMM Incorporated

Inventor： Hemanth Acharya ,  Pawan Kumar Baheti

IPC: H04N5/262 ,  H04N5/232 ,  H04N5/272 ,  G06T7/20 ,  H04N5/14

CPC classification number: H04N5/2625 ,  G06T5/002 ,  G06T5/50 ,  G06T7/215 ,  G06T2207/20221 ,  H04N5/145 ,  H04N5/23229 ,  H04N5/272

Abstract: Generally described, aspects of the present disclosure relate to generation of an image representing a panned shot of an object by an image capture device. In one embodiment, a panned shot may be performed on a series of images of a scene. The series of images may include at least subject object moving within the scene. Motion data of the subject object may be captured by comparing the subject object in a second image of the series of images to the subject object in a first image of the series of images. A background image is generated by implementing a blur process using the first image and the second image based on the motion data. A final image is generated by including the image of the subject object in the background image.

Abstract translation: 一般地描述，本公开的方面涉及通过图像捕获装置生成表示对象的平移拍摄的图像。 在一个实施例中，可以对场景的一系列图像执行平移拍摄。 该系列图像可以至少包括在场景内移动的被摄物体。 可以通过将一系列图像的第二图像中的被摄体对象与该系列图像的第一图像中的被摄对象进行比较来捕获被摄体的运动数据。 通过基于运动数据实现使用第一图像和第二图像的模糊处理来生成背景图像。 通过将主体对象的图像包括在背景图像中来生成最终图像。

公开(公告)号：US09460357B2

公开(公告)日：2016-10-04

申请号：US14150682

申请日：2014-01-08

Applicant: QUALCOMM Incorporated

Inventor： Hemanth P. Acharya ,  Pawan Kumar Baheti ,  Kishor K. Barman

IPC: G06K9/00 ,  G06K9/38 ,  G06K9/18 ,  G06T7/00

CPC classification number: G06K9/18 ,  G06K9/38 ,  G06T7/10 ,  G06T2207/20021 ,  G06T2207/30244

Abstract: Embodiments disclosed facilitate robust, accurate, and reliable recovery of words and/or characters in the presence of non-uniform lighting and/or shadows. In some embodiments, a method to recover text from image may comprise: expanding a Maximally Stable Extremal Region (MSER) in an image, the neighborhood comprising a plurality of sub-blocks; thresholding a subset of the plurality of sub-blocks in the neighborhood, the subset comprising sub-blocks with text, wherein each sub-block in the subset is thresholded using a corresponding threshold associated with the sub-block; and obtaining a thresholded neighborhood.

Abstract translation: 所公开的实施例有助于在存在非均匀照明和/或阴影的情况下对字和/或字符的鲁棒，准确和可靠的恢复。 在一些实施例中，从图像中恢复文本的方法可以包括：在图像中扩展最大稳定的极大区域（MSER），所述邻域包括多个子块; 阈值化所述邻域中的所述多个子块的子集，所述子集包括具有文本的子块，其中使用与所述子块相关联的对应阈值对所述子集中的每个子块进行阈值化; 并获得阈值邻域。

公开(公告)号：US20160284099A1

公开(公告)日：2016-09-29

申请号：US15179936

申请日：2016-06-10

Applicant: QUALCOMM Incorporated

Inventor： Ashwin Swaminathan ,  Piyush Sharma ,  Bolan Jiang ,  Murali R. Chari ,  Serafin Diaz Spindola ,  Pawan Kumar Baheti ,  Vidya Narayanan

IPC: G06T7/20 ,  G06T7/00

CPC classification number: G06T7/246 ,  G06K9/00671 ,  G06T7/73 ,  G06T2207/10004

Abstract: A mobile platform efficiently processes image data, using distributed processing in which latency sensitive operations are performed on the mobile platform, while latency insensitive, but computationally intensive operations are performed on a remote server. The mobile platform acquires image data, and determines whether there is a trigger event to transmit the image data to the server. The trigger event may be a change in the image data relative to previously acquired image data, e.g., a scene change in an image. When a change is present, the image data may be transmitted to the server for processing. The server processes the image data and returns information related to the image data, such as identification of an object in an image or a reference image or model. The mobile platform may then perform reference based tracking using the identified object or reference image or model.

Abstract translation: 移动平台使用分布式处理来有效地处理图像数据，其中在移动平台上执行延迟敏感操作，而延迟不敏感，但在远程服务器上执行计算密集型操作。 移动平台获取图像数据，并确定是否存在将图像数据发送到服务器的触发事件。 触发事件可以是相对于先前获取的图像数据的图像数据的变化，例如图像中的场景变化。 当存在改变时，图像数据可以被发送到服务器进行处理。 服务器处理图像数据并返回与图像数据相关的信息，例如图像中的对象或参考图像或模型的识别。 然后，移动平台可以使用所识别的对象或参考图像或模型来执行基于参考的跟踪。

公开(公告)号：US20150242710A1

公开(公告)日：2015-08-27

申请号：US14698528

申请日：2015-04-28

Applicant: QUALCOMM Incorporated

Inventor： Pawan Kumar Baheti ,  Kishor K. Barman ,  Raj Kumar Krishna Kumar

IPC: G06K9/72

CPC classification number: G06K9/72 ,  G06K2209/01

Abstract: Systems, apparatuses, and methods to relate images of words to a list of words are provided. A trellis based word decoder analyses a set of OCR characters and probabilities using a forward pass across a forward trellis and a reverse pass across a reverse trellis. Multiple paths may result, however, the most likely path from the trellises has the highest probability with valid links. A valid link is determined from the trellis by some dictionary word traversing the link. The most likely path is compared with a list of words to find the word closest to the most.

Abstract translation: 提供了将词的图像与词列表相关联的系统，装置和方法。 基于网格的字解码器使用前向网格的正向传递和跨反向网格的反向传递来分析一组OCR字符和概率。 可能会导致多个路径，但是，来自网格的最可能的路径具有有效链接的最高概率。 通过一些通过链接的字典字词从网格确定有效的链接。 最可能的路径与单词列表进行比较，以找到最接近的单词。

公开(公告)号：US20140023271A1

公开(公告)日：2014-01-23

申请号：US13797433

申请日：2013-03-12

Applicant: QUALCOMM INCORPORATED

Inventor： Pawan Kumar Baheti ,  Kishor K. Barman ,  Raghuraman Krishnamoorthi ,  Bojan Vrcelj

IPC: G06K9/46

CPC classification number: G06K9/4661 ,  G06K9/3233 ,  G06K9/3258 ,  G06K9/4638 ,  G06K9/4642 ,  G06K2209/01

Abstract: A difference in intensities of a pair of pixels in an image is repeatedly compared to a threshold, with the pair of pixels being separated by at least one pixel (“skipped pixel”). When the threshold is found to be exceeded, a selected position of a selected pixel in the pair, and at least one additional position adjacent to the selected position are added to a set of positions. The comparing and adding are performed multiple times to generate multiple such sets, each set identifying a region in the image, e.g. an MSER. Sets of positions, identifying regions whose attributes satisfy a test, are merged to obtain a merged set. Intensities of pixels identified in the merged set are used to generate binary values for the region, followed by classification of the region as text/non-text. Regions classified as text are supplied to an optical character recognition (OCR) system.

Abstract translation: 图像中的一对像素的强度的差异与阈值重复比较，其中该对像素被至少一个像素（“跳过的像素”）分开。 当发现阈值被超过时，将一对所选择的像素的选定位置和与选定位置相邻的至少一个附加位置添加到一组位置。 执行比较和添加多次以产生多个这样的集合，每个集合标识图像中的区域，例如。 一个MSER。 集合的位置，识别属性满足测试的区域被合并以获得合并集。 在合并集中识别的像素的强度用于生成该区域的二进制值，随后将该区域分类为文本/非文本。 分类为文本的区域被提供给光学字符识别（OCR）系统。

公开(公告)号：US20130195376A1

公开(公告)日：2013-08-01

申请号：US13748562

申请日：2013-01-23

Applicant: Qualcomm Incorporated

Inventor： Pawan Kumar Baheti ,  Ankit Agarwal ,  Dhananjay Ashok Gore

IPC: G06K9/36

CPC classification number: G06K9/00456 ,  G06K9/3258 ,  G06K9/36 ,  G06K9/4647 ,  G06K2209/01 ,  G06T11/60

Abstract: An electronic device and method use a camera to capture an image of an environment outside the electronic device followed by identification of regions, based on pixel intensities in the image. At least one processor automatically computes multiple values of an indicator of skew in multiple regions in the image respectively. The multiple values are specific to the multiple regions, and thereafter used to determine whether unacceptable skew is present across the regions, e.g. globally in the image as a whole. When skew is determined to be unacceptable, user input is requested to correct the skew, e.g. by displaying on a screen, a symbol and receiving user input (e.g. by rotating an area of touch or rotating the electronic device) to align a direction of the symbol with a direction of the image, and then the process may repeat (e.g. capture image, detect skew, and if necessary request user input).

Abstract translation: 电子设备和方法使用相机来基于图像中的像素强度来捕获电子设备外的环境的图像，然后识别区域。 至少一个处理器分别自动计算图像中多个区域的偏斜指标的多个值。 多个值对于多个区域是特定的，然后用于确定跨区域是否存在不可接受的偏斜，例如， 全球在整体形象上。 当确定歪斜是不可接受的时，请求用户输入来校正歪斜，例如。 通过在屏幕上显示符号和接收用户输入（例如通过旋转触摸区域或旋转电子设备）以使符号的方向与图像的方向对齐，然后该过程可以重复（例如捕获图像 ，检测偏斜，如有必要请求用户输入）。

公开(公告)号：US20130195360A1

公开(公告)日：2013-08-01

申请号：US13791188

申请日：2013-03-08

Applicant: QUALCOMM Incorporated

Inventor： Raj Kumar Krishna Kumar ,  Pawan Kumar Baheti

IPC: G06K9/78

CPC classification number: G06K9/78 ,  G06K9/32 ,  G06K2209/01 ,  G06K2209/013

Abstract: Systems, apparatus and methods for extracting lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test are presented. The method obtains the word image and performing a plurality of tests (e.g., a first test, a second test and a third test). The first test determines whether a vertical line spanning the height of the word image exists. The second test determines whether a jump of a number of components in the lower portion of the word image exists. The third test determines sparseness in a lower portion of the word image. The plurality of tests may run sequentially and/or in parallel. Results from the plurality of tests are used to decide whether a lower modifier exists by comparing and accumulating test results from the plurality of tests.

Abstract translation: 提出了基于包括第一测试，第二测试和第三测试的多个测试之前，在执行光学字符识别（OCR）之前从单词图像中提取下修改器的系统，设备和方法。 该方法获得单词图像并执行多个测试（例如，第一测试，第二测试和第三测试）。 第一个测试确定是否存在跨越单词图像的高度的垂直线。 第二个测试确定是否存在单词图像下部的一些组件的跳转。 第三个测试确定单词图像下部的稀疏度。 多个测试可以顺序地和/或并行地运行。 多个测试的结果用于通过比较和累积来自多个测试的测试结果来决定是否存在较低的修饰符。