公开(公告)号：US09471679B2

公开(公告)日：2016-10-18

申请号：US14194518

申请日：2014-02-28

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Pannag Raghunath Sanketi ,  Marius Renn ,  Ruei-sung Lin ,  Wei Hua

IPC: G06F17/30

CPC classification number: G06F17/30843

Abstract: The disclosed technology includes techniques for improved content coverage in automatically-generated content summaries. The technique may include clustering a set of input content, determining diffusion for each cluster, and selecting representatives of each cluster to optimize other secondary metrics. Various types of input content may be used, including groups of images, video clips, or other multimedia content. Contiguous content may be manually or programmatically divided into discrete portions before clustering, for example, a lengthy video divided into a number of short clips. In some implementations, the disclosed technique may be implemented effectively on a mobile device. In other words, the processing required may be computationally feasible for execution on a smartphone or similar device.

Abstract translation: 所公开的技术包括用于改进自动生成的内容摘要中的内容覆盖的技术。 该技术可以包括对一组输入内容进行聚类，确定每个集群的扩散，以及选择每个集群的代表以优化其他次要度量。 可以使用各种类型的输入内容，包括图像组，视频剪辑或其他多媒体内容。 连续的内容可以在聚类之前被手动地或者编程地划分成离散的部分，例如，被分成多个短片段的冗长的视频。 在一些实现中，可以在移动设备上有效地实现所公开的技术。 换句话说，所需的处理在计算上可以在智能电话或类似设备上执行。

公开(公告)号：US08913152B1

公开(公告)日：2014-12-16

申请号：US13628820

申请日：2012-09-27

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Pannag Raghunath Sanketi ,  Amarnag Subramanya

IPC: H04N5/228

CPC classification number: G06F17/3028 ,  G06F3/04842 ,  G06K9/6219 ,  G06T11/60 ,  H04N5/23216 ,  H04N5/23293

Abstract: A computer-implemented technique can receive a plurality of photos and automatically select a subset of the plurality of photos having a high degree of representativeness by jointly maximizing both photo quality and photo diversity to obtain a photo album. The technique can determine one or more clusters for the photo album using a hierarchical clustering algorithm, and store the photo album according to the one or more clusters. The technique can control the manner in which the photo album is displayed using the one or more clusters. The technique can adjust at least one of the one or more clusters and the automatic photo album generation based on user input. The user input can include at least one of adding, deleting, and moving a photo with respect to the one or more clusters. The technique can then re-cluster, automatically generate a new photo album, and/or adjust the presentation.

Abstract translation: 计算机实现的技术可以接收多张照片，并通过联合最大化照片质量和照片分集来获得相册，自动选择具有高度代表性的多张照片的子集。 该技术可以使用分层聚类算法确定相册的一个或多个聚类，并根据一个或多个聚类存储相册。 该技术可以使用一个或多个聚类来控制相册的显示方式。 该技术可以基于用户输入来调整一个或多个聚类中的至少一个和自动相册的生成。 用户输入可以包括关于一个或多个聚类的添加，删除和移动照片中的至少一个。 该技术可以重新聚集，自动生成新的相册和/或调整演示文稿。

公开(公告)号：US20180146133A1

公开(公告)日：2018-05-24

申请号：US15358770

申请日：2016-11-22

Applicant: Google Inc.

Inventor： Rodrigo Carceroni

IPC: H04N5/232 ,  G10L15/26

CPC classification number: H04N5/23222 ,  G06K9/00221 ,  G06K9/00355 ,  G06K9/00919 ,  G10L15/1822 ,  G10L15/22 ,  G10L15/265 ,  G10L2015/223 ,  H04N5/23203 ,  H04N5/23212 ,  H04N5/23219 ,  H04N5/23293 ,  H04N5/23296

Abstract: In general, techniques of this disclosure may enable a computing device to capture one or more images based on a natural language user input. The computing device, while operating in an image capture mode, receive an indication of a natural language user input associated with an image capture command. The computing device determines, based on the image capture command, a visual token to be included in one or more images to be captured by the camera. The computing device locates the visual token within an image preview output by the computing device while operating in the image capture mode. The computing device captures one or more images of the visual token.

公开(公告)号：US20170221217A1

公开(公告)日：2017-08-03

申请号：US15010239

申请日：2016-01-29

Applicant: Google Inc.

Inventor： Wei Hong ,  Marius Renn ,  Rodrigo Carceroni

IPC: G06T7/20 ,  G06T7/00

CPC classification number: G06T7/269 ,  G06T7/0044 ,  G06T7/204 ,  G06T7/206 ,  G06T7/2066 ,  G06T7/248 ,  G06T7/254 ,  G06T7/337 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20048 ,  G06T2207/30241 ,  G06T2207/30244

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for detecting motion in images. A computing system receives first and second images that were captured by a camera. The computing system generates, using the images, a mathematical transformation that indicates movement of the camera from the first image to the second image. The computing system generates, using the first image and the mathematical transformation, a modified version of the first image that presents the scene that was captured by the first image from a position of the camera when the second image was captured. The computing system determines a portion of the first image or second image at which a position of an object in the scene moved, by comparing the modified version of the first image to the second image.

公开(公告)号：US20160048161A1

公开(公告)日：2016-02-18

申请号：US14826437

申请日：2015-08-14

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Derya Ozkan ,  Suril Shah ,  Pannag Raghunath Sanketi

IPC: G06F1/16 ,  G01P13/00

CPC classification number: G06F1/163 ,  G06F1/3206 ,  G06F1/3265 ,  G06F3/014 ,  G06F3/017 ,  G06F3/0346 ,  G06F3/038 ,  G06F2200/1637 ,  Y02D10/153

Abstract: In one example, a method includes determining, by a processor (104) of a wearable computing device (102) and based on motion data generated by a motion sensor (106) of the wearable computing device, one or more strokes. In this example, the method also includes generating, by the processor and based on the motion data, a respective attribute vector for each respective stroke from the one or more strokes and classifying, by the processor and based on the respective attribute vector, each respective stroke from the one or more strokes into at least one category. In this example, the method also includes determining, by the processor and based on a gesture library and the at least one category for each stroke from the one or more strokes, a gesture. In this example, the method also includes performing, by the wearable device and based on the gesture, an action.

Abstract translation: 在一个示例中，方法包括由可佩戴计算设备（102）的处理器（104）确定基于由可穿戴计算设备的运动传感器（106）产生的运动数据，一个或多个笔划。 在该示例中，该方法还包括由处理器和基于运动数据生成来自一个或多个笔划的每个相应笔划的相应属性向量，并由处理器根据相应的属性向量分别分别对应 从一个或多个笔画到至少一个类别的笔画。 在该示例中，该方法还包括由处理器基于手势库以及来自一个或多个笔画的每个笔划的至少一个类别来确定手势。 在该示例中，该方法还包括通过可穿戴设备并基于手势来执行动作。

公开(公告)号：US09996109B2

公开(公告)日：2018-06-12

申请号：US14826437

申请日：2015-08-14

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Derya Ozkan ,  Suril Shah ,  Pannag Raghunath Sanketi

IPC: G09G5/00 ,  G06F1/16 ,  G06F1/32 ,  G06F3/01 ,  G06F3/038 ,  G06F3/0346

CPC classification number: G06F1/163 ,  G06F1/3206 ,  G06F1/3265 ,  G06F3/014 ,  G06F3/017 ,  G06F3/0346 ,  G06F3/038 ,  G06F2200/1637 ,  Y02D10/153

Abstract: In one example, a method includes determining, by a processor (104) of a wearable computing device (102) and based on motion data generated by a motion sensor (106) of the wearable computing device, one or more strokes. In this example, the method also includes generating, by the processor and based on the motion data, a respective attribute vector for each respective stroke from the one or more strokes and classifying, by the processor and based on the respective attribute vector, each respective stroke from the one or more strokes into at least one category. In this example, the method also includes determining, by the processor and based on a gesture library and the at least one category for each stroke from the one or more strokes, a gesture. In this example, the method also includes performing, by the wearable device and based on the gesture, an action.

公开(公告)号：US09967461B2

公开(公告)日：2018-05-08

申请号：US14883515

申请日：2015-10-14

Applicant: Google Inc.

Inventor： Wei Hong ,  Rodrigo Carceroni

IPC: H04N5/232 ,  G06T5/10 ,  G06T5/20

CPC classification number: H04N5/23248 ,  G06T3/0093 ,  G06T5/003 ,  G06T5/10 ,  G06T5/20 ,  G06T7/246 ,  G06T2207/10016 ,  H04N5/23229 ,  H04N5/23296

Abstract: In general, the subject matter can be embodied in methods, systems, and program products for identifying, by a computing system and using first and second frames of a video, a transformation that indicates movement of a camera with respect to the frames. The computing system generates a modified transformation so that the transformation is less representative of recent movement. The computing system uses the transformation and the modified transformation to generate a second transformation. The computing system identifies an anticipated distortion that would be present in a stabilized version of the second frame. The computing system determines an amount by which to reduce a stabilizing effect. The computing system applies the second transformation to the second frame to stabilize the second frame, where the stabilizing effect has been reduced based on the determined amount by which to reduce the stabilizing effect.

公开(公告)号：US09626384B2

公开(公告)日：2017-04-18

申请号：US14547078

申请日：2014-11-18

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Pannag Raghunath Sanketi ,  Amarnag Subramanya

IPC: G06F17/30 ,  G06F3/0484 ,  H04N5/232 ,  G06T11/60 ,  G06K9/62

CPC classification number: G06F17/3028 ,  G06F3/04842 ,  G06K9/6219 ,  G06T11/60 ,  H04N5/23216 ,  H04N5/23293

Abstract: A computer-implemented technique can receive a plurality of photos and automatically select a subset of the plurality of photos having a high degree of representativeness by jointly maximizing both photo quality and photo diversity to obtain a photo album. The technique can determine one or more clusters for the photo album using a hierarchical clustering algorithm, and store the photo album according to the one or more clusters. The technique can control the manner in which the photo album is displayed using the one or more clusters. The technique can adjust at least one of the one or more clusters and the automatic photo album generation based on user input. The user input can include at least one of adding, deleting, and moving a photo with respect to the one or more clusters. The technique can then re-cluster, automatically generate a new photo album, and/or adjust the presentation.

公开(公告)号：US09137488B2

公开(公告)日：2015-09-15

申请号：US13661924

申请日：2012-10-26

Applicant: Google Inc.

Inventor： Michael Dodd ,  Rodrigo Carceroni

IPC: H04N7/14 ,  H04N7/15 ,  H04N9/67 ,  G06T3/40 ,  H04N21/258 ,  H04N21/2662 ,  H04N21/414 ,  H04N21/4788 ,  H04L29/06

CPC classification number: H04N7/15 ,  G06T3/4092 ,  H04L65/403 ,  H04L65/605 ,  H04N9/67 ,  H04N21/25825 ,  H04N21/2662 ,  H04N21/41407 ,  H04N21/4788

Abstract: Implementations relate to a system for video encoding and conversion including an image resolution conversion component operable to convert a resolution of a source image frame from a first resolution to a second resolution to produce a first intermediate image frame at the second resolution; an image conversion component operable to receive the first intermediate image frame and convert an image size of the first intermediate image frame to another image frame size to produce a first viewable image frame; an image viewer component operable to display the first viewable image on a first display; a color space conversion component comprising a luminance conversion component and a chrominance operable to receive the first viewable image frame and convent a first luminance value and a first chrominance value of the first viewable image frame to a second intermediate image frame having a second luminance value and a second chrominance value.

Abstract translation: 实现涉及用于视频编码和转换的系统，包括可操作以将源图像帧的分辨率从第一分辨率转换为第二分辨率以产生第二分辨率的第一中间图像帧的图像分辨率转换组件; 图像转换部件，用于接收所述第一中间图像帧，并将所述第一中间图像帧的图像尺寸转换为另一图像帧尺寸，以产生第一可视图像帧; 图像查看器组件，可操作以在第一显示器上显示第一可视图像; 颜色空间转换组件，包括亮度转换分量和色度，可操作以接收第一可视图像帧并将第一可视图像帧的第一亮度值和第一色度值修改为具有第二亮度值的第二中间图像帧，以及 第二个色度值。

公开(公告)号：US20150120733A1

公开(公告)日：2015-04-30

申请号：US14194518

申请日：2014-02-28

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Pannag Raghunath Sanketi ,  Marius Renn ,  Ruei-sung Lin ,  Wei Hua

IPC: G06F17/30

CPC classification number: G06F17/30843

Abstract: The disclosed technology includes techniques for improved content coverage in automatically-generated content summaries. The technique may include clustering a set of input content, determining diffusion for each cluster, and selecting representatives of each cluster to optimize other secondary metrics. Various types of input content may be used, including groups of images, video clips, or other multimedia content. Contiguous content may be manually or programmatically divided into discrete portions before clustering, for example, a lengthy video divided into a number of short clips. In some implementations, the disclosed technique may be implemented effectively on a mobile device. In other words, the processing required may be computationally feasible for execution on a smartphone or similar device.

Abstract translation: 所公开的技术包括用于改进自动生成的内容摘要中的内容覆盖的技术。 该技术可以包括对一组输入内容进行聚类，确定每个集群的扩散，以及选择每个集群的代表以优化其他次要度量。 可以使用各种类型的输入内容，包括图像组，视频剪辑或其他多媒体内容。 连续的内容可以在聚类之前被手动地或者编程地划分成离散的部分，例如，被分成多个短片段的冗长的视频。 在一些实现中，可以在移动设备上有效地实现所公开的技术。 换句话说，所需的处理在计算上可以在智能电话或类似设备上执行。