公开(公告)号：US09424461B1

公开(公告)日：2016-08-23

申请号：US13929672

申请日：2013-06-27

Applicant: Amazon Technologies, Inc.

Inventor： Chang Yuan ,  Geoffrey Scott Heller ,  Oleg Rybakov ,  Sharadh Ramaswamy ,  Jim Oommen Thomas

IPC: G06K9/00

CPC classification number: G06K9/00201 ,  G06K9/00208 ,  G06K9/00214

Abstract: Various embodiments utilize two-dimensional (“2D”) and three-dimensional (“3D”) object features for purposes such as object recognition and/or image matching. For example, a user can capture an image (e.g., still images or video) of an object and can receive information about items that are determined to match the object. For example, the image can be analyzed to detect visual features (e.g., corners, edges, etc.) of the object and the detected visual features can be combined to generate a combined visual feature vector which can be used for object recognition, image matching, or other such purposes. Other approaches utilize the image to generate a 3D model of the object represented in the image, which can be used to determine at least one object or types of objects that match the object represented in the image.

Abstract translation: 各种实施例利用二维（“2D”）和三维（“3D”）对象特征用于诸如对象识别和/或图像匹配的目的。 例如，用户可以捕获对象的图像（例如，静止图像或视频），并且可以接收关于被确定为匹配对象的项目的信息。 例如，可以分析图像以检测对象的视觉特征（例如，角，边等），并且可以组合检测到的视觉特征以生成可用于对象识别，图像匹配的组合视觉特征向量 ，或其他此类用途。 其他方法利用图像来生成在图像中表示的对象的3D模型，其可以用于确定与图像中表示的对象匹配的对象的至少一个对象或类型。

公开(公告)号：US11853391B1

公开(公告)日：2023-12-26

申请号：US16139607

申请日：2018-09-24

Applicant: Amazon Technologies, Inc.

Inventor： Pranav Prashant Ladkat ,  Oleg Rybakov ,  Nikko Strom ,  Sri Venkata Surya Siva Rama Krishna Garimella ,  Sree Hari Krishnan Parthasarathi

IPC: G06F18/214 ,  G06N20/00

CPC classification number: G06F18/2148 ,  G06N20/00

Abstract: Exemplary embodiments provide distributed parallel training of a machine learning model. Multiple processors may be used to train a machine learning model to reduce training time. To synchronize trained model data between the processors, data is communicated between the processors after some number of training cycles. To improve the communication efficiency, exemplary embodiments synchronize data among a set of processors after a predetermined number of training cycles, and synchronize data between one or more processors of each set of the processors after a predetermined number of training cycles. During the first synchronization among a set of processors, compressed model gradient data generated after performing the training cycles may be communicated. During the second synchronization between the set of processors, trained models or full model gradient data generated after performing the training cycles may be communicated.

公开(公告)号：US09536161B1

公开(公告)日：2017-01-03

申请号：US14307090

申请日：2014-06-17

Applicant: Amazon Technologies, Inc.

Inventor： Christopher John Lish ,  Oleg Rybakov ,  Sonjeev Jahagirdar ,  Junxiong Jia ,  Neil David Cooper ,  Avnish Sikka

IPC: G06K9/20 ,  H04N5/232 ,  G06K9/32

CPC classification number: H04N5/23245 ,  G01S3/00 ,  G06K9/00664 ,  G06K2009/3291 ,  H04N5/232 ,  H04N5/23219 ,  H04N5/247

Abstract: Various embodiments describe systems and methods for utilizing a reduced amount of processing capacity for incoming data over time, and, in response to detecting a scene-change-event, notify one or more data processors that a scene-change-event has occurred, and cause incoming data to be processed as new data. In some embodiments, an incoming frame can be compared with a reference frame to determine a difference between the reference frame and the incoming frame. The reference frame may be correlated to a latest scene-change-event. In response to a determination that the difference does not meet one or more difference criteria, a user interface or at least one processor of the computing device can be notified to reduce processing of incoming data over time. In response to a determination that the difference meets the one or more difference criteria, the user interface or the at least one processor can be notified that a scene-change-event has occurred. Incoming data to the computing device is then treated as new and processed as those under an active condition. The current incoming frame can be selected as a new reference frame for detecting next scene-change-event.

Abstract translation: 各种实施例描述了随着时间的推移对于输入数据利用减少量的处理能力的系统和方法，并且响应于检测到场景改变事件，通知一个或多个数据处理器已经发生场景变化事件，以及 将传入的数据作为新数据进行处理。 在一些实施例中，输入帧可以与参考帧进行比较，以确定参考帧和输入帧之间的差异。 参考帧可以与最新的场景变化事件相关联。 响应于差异不符合一个或多个差异标准的确定，可以通知用户界面或计算设备的至少一个处理器以减少输入数据随时间的处理。 响应于差异满足一个或多个差异标准的确定，可以向用户界面或至少一个处理器通知场景变化事件已经发生。 然后将接收到计算设备的数据视为新的，并处理为处于活动状态的数据。 可以将当前输入帧选择为用于检测下一个场景改变事件的新参考帧。

公开(公告)号：US09235757B1

公开(公告)日：2016-01-12

申请号：US14477031

申请日：2014-09-04

Applicant: Amazon Technologies, Inc.

Inventor： Yue Liu ,  Oleg Rybakov

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/32

CPC classification number: G06K9/325

Abstract: A system that identifies and recognizes text that offers reduced the computational complexity for processing complex images. Widths of scan line segments within candidate text regions are determined, with the shortest segments selected as being representative of stroke width. Statistical features of the stroke widths are used as part of the process to classify each region as containing or not containing a text character or glyph.

Abstract translation: 识别和识别文本的系统，降低了处理复杂图像的计算复杂度。 确定候选文本区域内的扫描线段的宽度，其中选择最短的段代表行程宽度。 使用笔画宽度的统计特征作为将每个区域分类为包含或不包含文本字符或字形的过程的一部分。

公开(公告)号：US09171195B1

公开(公告)日：2015-10-27

申请号：US14305492

申请日：2014-06-16

Applicant: Amazon Technologies, Inc.

Inventor： Oleg Rybakov ,  Avinash Aghoram Ravichandran ,  Matias Omar Gregorio Benitez

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/6807 ,  G06K9/00201

Abstract: An object recognition system may recognize an object in a query image by matching the image to one or more images in a database. The database may include images corresponding to multiple viewpoints of a particular device. Key points of the query image are compared to key points in the database images. Database images with many overlapping key points to the query image are selected as potential matches. The geometry of objects in the potential matches is verified to the geometry of the object in the query image to determine if the overlapping key points have a similar geographic relationship to each other across images. Objects in geometrically verified database images may be selected as potentially matching objects to the object in the query image. When a potential matching image is found, the system may confirm the match by performing matching with a second image of the object.

Abstract translation: 对象识别系统可以通过将图像与数据库中的一个或多个图像相匹配来识别查询图像中的对象。 数据库可以包括对应于特定设备的多个视点的图像。 将查询图像的要点与数据库图像中的要点进行比较。 选择具有查询图像的许多重叠关键点的数据库图像作为潜在匹配。 潜在匹配中的对象的几何结构被验证为查询图像中的对象的几何，以确定重叠的关键点是否在图像之间彼此具有相似的地理关系。 可以将几何校验的数据库图像中的对象选择为与查询图像中的对象潜在匹配的对象。 当找到潜在的匹配图像时，系统可以通过与对象的第二图像进行匹配来确认匹配。

公开(公告)号：US09160993B1

公开(公告)日：2015-10-13

申请号：US13945823

申请日：2013-07-18

Applicant: Amazon Technologies, Inc.

Inventor： Christopher John Lish ,  Geoffrey Scott Heller ,  Jim Oommen Thomas ,  Chang Yuan ,  Oleg Rybakov

IPC: G03B21/14 ,  H04N9/31 ,  H04N5/232

CPC classification number: H04N9/3185 ,  G06F3/0425 ,  G06F3/0488 ,  H04N5/23219 ,  H04N5/23229 ,  H04N5/23293 ,  H04N9/3194

Abstract: Approaches enable the projection of one or more visual elements, such as one or more dynamically changing graphical elements, that can substantially bound, or otherwise at least partially surround or identify, an object recognized by a computing device. The computing device can project the graphical elements to collectively appear as a bounding element for the recognized/actionable object or object portion. As such, the graphical elements can appear as a bounding element that adorns, decorates, highlights, and/or emphasizes, etc., the recognized/actionable object or object portion. The graphical elements to be dynamic. For example, the graphical elements can be projected to move around individually over time, while still appearing to at least partially surround the recognized/actionable object or object portion. Further, the graphical elements can be used to improve various object recognition approaches.

Abstract translation: 方法使得能够基本上绑定或以其他方式至少部分地围绕或识别由计算设备识别的对象的一个​​或多个可视元素的投影，诸如一个或多个动态变化的图形元素。 计算设备可以投影图形元素以集体显示为识别/可操作的对象或对象部分的边界元素。 因此，图形元素可以显示为对已识别/可操作的对象或对象部分进行装饰，装饰，突出显示和/或强调等的边界元素。 图形元素是动态的。 例如，图形元素可以被投影以随着时间逐渐移动，同时仍然显示为至少部分地围绕识别/可操作的对象或对象部分。 此外，图形元素可以用于改进各种对象识别方法。