公开(公告)号：US09390315B1

公开(公告)日：2016-07-12

申请号：US14750855

申请日：2015-06-25

Applicant: A9.com, Inc.

Inventor： Ismet Zeki Yalniz ,  Colin Jon Taylor ,  Mehmet Nejat Tek ,  Shanghsuan Tsai

IPC: G06K9/46 ,  G06K9/00 ,  G06T7/40 ,  G06T7/60 ,  G06T7/00

CPC classification number: G06K9/4652 ,  G06K9/00208 ,  G06K9/4609 ,  G06K9/4676 ,  G06K9/6202 ,  G06K9/6211 ,  G06T7/11 ,  G06T7/60 ,  G06T7/90 ,  G06T2207/10004

Abstract: Object identification through image matching can utilize ratio and other data to accurately identify objects having relatively few feature points otherwise useful for identifying objects. An initial image analysis attempts to locate a “scalar” in the image, such as may include a label, text, icon, or other identifier that can help to narrow a classification of the search, as well as to provide a frame of reference for relative measurements obtained from the image. By comparing the ratios of dimensions of the scalar with other dimensions of the object, it is possible to discriminate between objects containing that scalar in a way that is relatively robust to changes in viewpoint. A ratio signature can be generated for an object for use in matching, while in other embodiments a classification can identify priority ratios that can be used to more accurately identify objects in that classification.

Abstract translation: 通过图像匹配的对象识别可以利用比率和其他数据来准确地识别具有相对较少的特征点的对象，否则对识别对象是有用的。 初始图像分析尝试在图像中定位“标量”，例如可以包括可以帮助缩小搜索分类的标签，文本，图标或其他标识符，以及提供用于 从图像获得的相对测量值。 通过将标量的维数与对象的其他维度进行比较，可以以对视点变化相对鲁棒的方式来区分包含该标量的对象。 可以针对用于匹配的对象生成比例签名，而在其他实施例中，分类可以标识可用于更精确地识别该分类中的对象的优先级比。

公开(公告)号：US20160133299A1

公开(公告)日：2016-05-12

申请号：US14997351

申请日：2016-01-15

Applicant: A9.com, Inc.

Inventor： Ismet Zeki Yalniz ,  Adam Carlson ,  Douglas Ryan Gray ,  Colin Jon Taylor

IPC: G11B27/30 ,  G11B27/34 ,  G11B27/036

CPC classification number: G11B27/3072 ,  G11B27/031 ,  G11B27/036 ,  G11B27/10 ,  G11B27/3081 ,  G11B27/34

Abstract: Various embodiments identify differences between frame sequences of a video. For example, to determine a difference between two versions of a video, a fingerprint of each frame of the two versions is generated. From the fingerprints, a run-length encoded representation of each version is generated. The fingerprints which appear only once (i.e., unique fingerprints) in the entire video are identified from each version and compared to identify matching unique fingerprints across versions. The matching unique fingerprints are sorted and filtered to determine split points, which are used to align the two versions of the video. Accordingly, each version is segmented into smaller frame sequences using the split points. Once segmented, the individual frames of each segment are aligned across versions using a dynamic programming algorithm. After aligning the segments at a frame level, the segments are reassembled to generate a global alignment output.

Abstract translation: 各种实施例识别视频的帧序列之间的差异。 例如，为了确定视频的两个版本之间的差异，生成两个版本的每个帧的指纹。 从指纹中，生成每个版本的游程长度编码表示。 从每个版本识别整个视频中仅出现一次的指纹（即，唯一指纹），并进行比较以识别跨越版本的匹配的唯一指纹。 匹配的唯一指纹被分类和过滤以确定分割点，其用于对准视频的两个版本。 因此，使用分割点将每个版本分割成较小的帧序列。 一旦分段，每个段的各个帧在版本之间使用动态规划算法对齐。 在帧级别对齐段之后，重新组合段以产生全局对准输出。

公开(公告)号：US09280560B1

公开(公告)日：2016-03-08

申请号：US14133252

申请日：2013-12-18

Applicant: A9.com, Inc.

Inventor： Simant Dube ,  Sunil Ramesh ,  Xiaofan Lin ,  Arnab Sanat Kumar Dhua ,  Colin Jon Taylor ,  Jaishanker K. Pillai

IPC: G06K9/46 ,  G06F17/30 ,  G06K9/00 ,  G06T9/00 ,  H04N19/90

CPC classification number: G06K9/6215 ,  G06F17/30247 ,  G06K9/00523 ,  G06K9/4676 ,  G06K9/52 ,  G06K9/6206 ,  G06K9/6211 ,  G06K9/6218 ,  G06K9/6232 ,  G06K9/6256 ,  G06K9/6267 ,  G06K9/6269 ,  G06K9/6276 ,  G06K9/6277 ,  G06K9/6284 ,  G06K9/66 ,  G06K2209/19 ,  H04N19/426 ,  H04N19/90

Abstract: Various embodiments may increase scalability of image representations stored in a database for use in image matching and retrieval. For example, a system providing image matching can obtain images of a number of inventory items, extract features from each image using a feature extraction algorithm, and transform the same into their feature descriptor representations. These feature descriptor representations can be subsequently stored and used to compare against query images submitted by users. Though the size of each feature descriptor representation isn't particularly large, the total number of these descriptors requires a substantial amount of storage space. Accordingly, feature descriptor representations are compressed to minimize storage and, in one example, machine learning can be used to compensate for information lost as a result of the compression.

Abstract translation: 各种实施例可以增加存储在用于图像匹配和检索的数据库中的图像表示的可扩展性。 例如，提供图像匹配的系统可以获得多个库存物品的图像，使用特征提取算法从每个图像中提取特征，并将其转换成它们的特征描述符表示。 这些特征描述符表示可随后存储并用于与用户提交的查询图像进行比较。 虽然每个特征描述符表示的大小不是特别大，但是这些描述符的总数需要大量的存储空间。 因此，压缩特征描述符表示以最小化存储，并且在一个示例中，可以使用机器学习来补偿由于压缩而丢失的信息。

公开(公告)号：US09247129B1

公开(公告)日：2016-01-26

申请号：US14015884

申请日：2013-08-30

Applicant: A9.com, Inc.

Inventor： Douglas Ryan Gray ,  Colin Jon Taylor ,  Xiaofan Lin

IPC: H04N5/232

CPC classification number: G06T5/00 ,  G06F17/30256 ,  G06K9/00221 ,  G06T5/30 ,  G06T7/11 ,  G06T7/194 ,  G06T11/60 ,  G06T2207/10004 ,  G06T2207/20221 ,  G06T2207/30201 ,  H04N5/23222 ,  H04N5/23238 ,  H04N5/272

Abstract: Systems and approaches are provided for optimizing self-portraiture. The background of the self-portrait can be enhanced by image registration or stitching techniques of images captured using one or more conventional cameras. Multiple standard resolution images can be stitched together to generate a panoramic or a composite image of a higher resolution. Foreground elements, such as one or more representations of users, can also be enhanced in various ways. The representations of the users can be composited to exclude undesirable elements, such as image data of one of the users extending her arm to capture the self-portrait. An ideal pose of the users can automatically be selected and other image enhancements, such as histogram optimization, brightness and contrast optimization, color-cast correction, or reduction or removal of noise, can automatically be performed to minimize user effort in capturing self-portraits.

Abstract translation: 提供了系统和方法来优化自画像。 可以通过使用一个或多个传统照相机捕获的图像的图像配准或拼接技术来增强自画像的背景。 可以将多个标准分辨率图像拼接在一起以产生更高分辨率的全景或合成图像。 诸如用户的一个或多个表示的前景元素也可以以各种方式增强。 用户的表示可以被合成以排除不期望的元素，例如延伸她的手臂以捕获自画像的其中一个用户的图像数据。 可以自动选择用户的理想姿势，并且可以自动执行其他图像增强功能，如直方图优化，亮度和对比度优化，色差校正，或减少或消除噪点，以尽量减少用户拍摄自画像的工作量 。

公开(公告)号：US09240077B1

公开(公告)日：2016-01-19

申请号：US14219700

申请日：2014-03-19

Applicant: A9.com, Inc.

Inventor： Adam Wiggen Kraft ,  Colin Jon Taylor

IPC: G06T19/00

CPC classification number: H04N5/23293 ,  G06T11/00 ,  G06T19/006 ,  H04M2250/52 ,  H04N5/23229

Abstract: Visual effects for element of interest can be displayed within a live camera view in real time or substantially using a processing pipeline that does not immediately display an acquired image until it has been updated with the effects. In various embodiments, software-based approaches, such as fast convolution algorithms, and/or hardware-based approaches, such as using a graphics processing unit (GPU), can be used reduce the time between acquiring an image and displaying the image with various visual effects. These visual effects can include automatically highlighting elements, augmenting the color, style, and/or size of elements, casting a shadow on elements, erasing elements, substituting elements, or shaking and jumbling elements, among other effects.

Abstract translation: 感兴趣的元素的视觉效果可以在实时相机视图中实时显示，或者基本上使用不直接显示所获取的图像的处理流水线，直到其被更新为效果。 在各种实施例中，可以使用诸如快速卷积算法和/或基于硬件的方法（诸如使用图形处理单元（GPU））的基于软件的方法来减少获取图像和以各种方式显示图像之间的时间 视觉效果。 这些视觉效果可以包括自动突出显示元素，增加元素的颜色，样式和/或尺寸，在元素上投射阴影，擦除元素，替换元素，或抖动和混乱元素等。

公开(公告)号：US09055216B1

公开(公告)日：2015-06-09

申请号：US13681034

申请日：2012-11-19

Applicant: A9.com, Inc.

Inventor： Colin Jon Taylor

IPC: H04N5/232

CPC classification number: H04N5/23222 ,  G06T5/00 ,  H04N5/23238 ,  H04N5/23293

Abstract: Image data and position and orientation data collected by a computing device can be aggregated to create enhanced videos. One example of an enhanced video is a panoramic video generated from a single video camera having a standard field of view. Enhanced videos can also be created to have a display resolution that is greater than is capable of being recorded by at least one video camera of the computing device providing input to the computing device. Enhanced videos can also be streamed live to a viewer, and the viewer can change the perspective of the streamed video or auto-center and auto-focus on a specified location or object in the streamed video.

Abstract translation: 计算设备收集的图像数据和位置和方向数据可以进行聚合，以创建增强的视频。 增强视频的一个示例是从具有标准视场的单个摄像机生成的全景视频。 还可以创建增强的视频以使显示分辨率大于能够由计算设备的至少一个摄像机向计算设备提供输入的记录。 增强的视频也可以直播到观众，观众可以改变流媒体视频的视角或自动对焦，并自动对焦于流媒体视频中的指定位置或对象。