-
公开(公告)号：US09436886B2
公开(公告)日：2016-09-06
申请号：US14660141
申请日：2015-03-17
Applicant: Google Inc.
Inventor： Bo Wu , Alessandro Bissacco , Raymond W. Smith , Kong Man Cheung , Andrea Frome , Shlomo Urbach
CPC classification number: G06K9/3258 , G06K9/00 , G06K9/18 , G06K2209/01 , G06Q50/10
Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.
-
公开(公告)号：US20160188991A1
公开(公告)日：2016-06-30
申请号：US14660141
申请日：2015-03-17
Applicant: Google Inc.
Inventor： Bo Wu , Alessandro Bissacco , Raymond W. Smith , Kong Man Cheung , Andrea Frome , Shlomo Urbach
CPC classification number: G06K9/3258 , G06K9/00 , G06K9/18 , G06K2209/01 , G06Q50/10
Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.
Abstract translation: 提供了一种用于自动识别街道图像中的建筑物编号的系统和方法。 在一个方面，处理器选择可能靠近感兴趣的地址的街道级图像。 处理器识别图像中与街道号码视觉相似的那些部分，然后提取在这些部分中显示的字符的数值。 如果提取的值对应于感兴趣的地址的建筑物号码，例如基本上等于感兴趣的地址，则提取的值和图像部分被显示给人类操作者。 人类操作者通过观察图像部分来确认图像部分是否看起来是与提取的值相匹配的建筑物号码。 如果是这样，处理器存储将建筑物号码与街道图像相关联的值。
-
公开(公告)号：US09239626B1
公开(公告)日：2016-01-19
申请号：US13933905
申请日：2013-07-02
Applicant: Google Inc.
Inventor： Bo Wu , David Sparks , Michael Patrick Johnson
IPC: G06F3/01
CPC classification number: G06F3/017 , G02B27/017 , G02B2027/014 , G02B2027/0178 , G02B2027/0187 , G06F3/013 , G06F3/0304
Abstract: Examples of methods and systems for using eye gesture duration to provide calibration for eye gesture detection are described. In some examples, calibration can be executed using a head-mountable device. The head-mountable device may be configured to determine a duration range indicative of an eye gesture and receive a plurality of reference signals indicative of the eye gesture. The plurality of reference signals may comprise duration information indicative of a plurality of reference durations of the eye gesture. The head-mountable device may determine, based on the plurality of reference durations, a reference duration range associated with the eye gesture that is within the duration range, and adjust the duration range for the eye gesture based on the reference duration range.
Abstract translation: 描述了使用眼睛手势持续时间来提供眼睛手势检测的校准的方法和系统的示例。 在一些示例中，可以使用可头戴式装置来执行校准。 可头戴式装置可以被配置为确定指示眼睛手势的持续时间范围，并且接收指示眼睛手势的多个参考信号。 多个参考信号可以包括指示眼睛手势的多个参考持续时间的持续时间信息。 可头戴式装置可以基于多个参考持续时间来确定与持续时间范围内的眼睛手势相关联的参考持续时间范围，并且基于参考持续时间范围来调整眼睛手势的持续时间范围。
-
公开(公告)号：US09020265B2
公开(公告)日：2015-04-28
申请号：US14296781
申请日：2014-06-05
Applicant: Google Inc.
Inventor： Bo Wu , Alessandro Bissacco , Raymond W. Smith , Kong Man Cheung , Andrea Frome , Shlomo Urbach
CPC classification number: G06K9/3258 , G06K9/00 , G06K9/18 , G06K2209/01 , G06Q50/10
Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.
Abstract translation: 提供了一种用于自动识别街道图像中的建筑物编号的系统和方法。 在一个方面，处理器选择可能靠近感兴趣的地址的街道级图像。 处理器识别图像中与街道号码视觉相似的那些部分，然后提取在这些部分中显示的字符的数值。 如果提取的值对应于感兴趣的地址的建筑物号码，例如基本上等于感兴趣的地址，则提取的值和图像部分被显示给人类操作者。 人类操作者通过观察图像部分来确认图像部分是否看起来是与提取的值相匹配的建筑物号码。 如果是这样，处理器存储将建筑物号码与街道图像相关联的值。
-
5.发明授权Face and license plate detection in street level images with 3-D road width features estimated from laser data 有权街道级别图像的面部和车牌检测，具有从激光数据估计的3-D道路宽度特征公开(公告)号：US08971646B1
公开(公告)日：2015-03-03
申请号：US14297949
申请日：2014-06-06
Applicant: Google Inc.
Inventor： Bo Wu
CPC classification number: G06K9/00664 , G06K9/00624 , G06K9/00637 , G06K9/00785 , G06K9/3258 , G06K9/481
Abstract: A computer implemented system for identifying license plates and faces in street-level images is disclosed. The system includes an object detector configured to determine a set of candidate objects in the image, a feature vector module configured to generate a set of feature vectors using the object detector to generate a feature vector for each candidate object in the set of candidate objects, a composite feature vector module to generate a set of composite feature vectors by combining each generated feature vector with a corresponding road or street description of the object in question, and an identifier module configured to identify objects of a particular type using a classifier that takes a set of composite feature vectors as input and returns a list of candidate objects that are classified as being of the particular type as output.
Abstract translation: 公开了一种用于识别街道级图像中的车牌和面部的计算机实现的系统。 该系统包括被配置为确定图像中的候选对象集合的对象检测器，被配置为使用对象检测器生成一组特征向量以生成候选对象集合中的每个候选对象的特征向量的特征向量模块， 复合特征向量模块，用于通过将每个生成的特征向量与所讨论的对象的相应道路或街道描述相组合来生成一组复合特征向量，以及标识符模块，其被配置为使用分类器来识别特定类型的对象， 复合特征向量集合作为输入，并返回被分类为特定类型作为输出的候选对象的列表。
-
Patent Agency Ranking
公开(公告)号：US20170163866A1
公开(公告)日：2017-06-08
申请号：US13949603
申请日：2013-07-24
Applicant: Google Inc.
Inventor： Michael Patrick Johnson , Bo Wu , David Sparks , Hayes Solos Raffle
IPC: H04N5/232
CPC classification number: H04N5/23203 , G06F1/163 , G06F3/011 , G06F3/013 , H04N5/232
Abstract: The present disclosure provides a computing device including an image-capture device and a control system. The control system may be configured to receive sensor data from one or more sensors, and analyze the sensor data to detect at least one image-capture signal. The control system may also be configured to cause the image-capture device to capture an image in response to detection of the at least one image-capture signal. The control system may also be configured to enable one or more speech commands relating to the image-capture device in response to capturing the image. The control system may also be configured to receive one or more verbal inputs corresponding to the one or more enabled speech commands. The control system may also be configured to perform an image-capture function corresponding to the one or more verbal inputs.
-
公开(公告)号：US09664902B1
公开(公告)日：2017-05-30
申请号：US14173598
申请日：2014-02-05
Applicant: Google Inc.
Inventor： Hayes Solos Raffle , David Sparks , Bo Wu
CPC classification number: G09G5/006 , G02B27/0093 , G02B27/01 , G02B27/017 , G02B2027/0178 , G06F3/013 , G06F3/03547 , G06F3/044 , G09G5/12 , G09G2354/00 , G09G2370/06
Abstract: Disclosed are methods and devices for varying functionality of a wearable computing device. An example device includes a first sensor and a second sensor. An example method includes, while a device is operating in a first state, receiving an indication of a touch input at the first sensor. The second sensor is configured in an idle mode based on the device operating in the first state. The method further includes, in response to receiving the indication of the touch input, triggering the second sensor to operate in an active mode and receiving data from the second sensor. The method further includes determining, based on the data, whether the device is being worn.
-
公开(公告)号：US20160057339A1
公开(公告)日：2016-02-25
申请号：US14886690
申请日：2015-10-19
Applicant: Google Inc.
Inventor： Hayes Solos Raffle , Sergey Brin , Bo Wu , Michael Patrick Johnson , David Sparks
CPC classification number: H04N5/23219 , G02B27/01 , G02B27/017 , G02B2027/0178 , G02B2027/0187 , G06F3/012 , G06F3/017 , G06K9/00281 , G06K9/00604 , H04N5/232 , H04N5/23212 , H04N5/23293
Abstract: This disclosure relates to winking to capture image data using an image capture device that is associated with a head-mountable device (HMD). An illustrative method includes detecting a wink gesture at an HMD. The method also includes causing an image capture device to capture image data, in response to detecting the wink gesture at the HMD.
Abstract translation: 本公开涉及使用与头戴式装置（HMD）相关联的图像捕获装置捕获图像数据的闪光。 说明性方法包括在HMD处检测眨眼手势。 该方法还包括使得图像捕获装置响应于检测到HMD处的眨眼手势来捕获图像数据。
-
公开(公告)号：US09207760B1
公开(公告)日：2015-12-08
申请号：US13630563
申请日：2012-09-28
Applicant: Google Inc.
Inventor： Bo Wu , Yong Zhao , Hartmut Neven , Hayes Solos Raffle , Thad Eugene Starner
IPC: G06F15/18 , G06N5/02 , G06N3/02 , G06F3/01 , G06K9/62 , G06K9/00 , G06N99/00 , G02B27/00 , G02B27/01
CPC classification number: G06F3/013 , G02B27/0093 , G02B2027/0187 , G06K9/00281 , G06K9/00288 , G06K9/00617 , G06K9/623 , G06K9/6231 , G06K9/6257 , G06K9/626 , G06K9/6263 , G06N99/005
Abstract: This disclosure involves proximity sensing of eye gestures using a machine-learned model. An illustrative method comprises receiving training data that includes proximity-sensor data. The data is generated by at least one proximity sensor of a head-mountable device (HMD). The data is indicative of light received by the proximity sensor(s). The light is received by the proximity sensor(s) after a reflection of the light from an eye area. The reflection occurs while an eye gesture is being performed at the eye area. The light is generated by at least one light source of the HMD. The method further comprises applying a machine-learning process to the training data to generate at least one classifier for the eye gesture. The method further comprises generating an eye-gesture model that includes the at least one classifier for the eye gesture. The model is applicable to subsequent proximity-sensor data for detection of the eye gesture.
Abstract translation: 本公开涉及使用机器学习模型进行眼睛手势的接近感测。 一种说明性方法包括接收包括接近传感器数据的训练数据。 数据由头戴式装置（HMD）的至少一个接近传感器产生。 数据表示由接近传感器接收的光。 在来自眼睛区域的光的反射之后，光被接近传感器接收。 当在眼睛区域执行眼睛手势时发生反射。 光由HMD的至少一个光源产生。 该方法还包括将机器学习过程应用于训练数据以生成用于眼睛手势的至少一个分类器。 该方法还包括生成包括用于眼睛手势的至少一个分类器的眼睛手势模型。 该模型适用于随后的接近传感器数据，用于检测眼睛手势。
-
公开(公告)号：US20140286573A1
公开(公告)日：2014-09-25
申请号：US14296781
申请日：2014-06-05
Applicant: Google Inc.
Inventor： Bo Wu , Alessandro Bissacco , Raymond W. Smith , Kong Man Cheung , Andrea Frome , Shlomo Urbach
IPC: G06K9/18
CPC classification number: G06K9/3258 , G06K9/00 , G06K9/18 , G06K2209/01 , G06Q50/10
Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.
Abstract translation: 提供了一种用于自动识别街道图像中的建筑物编号的系统和方法。 在一个方面，处理器选择可能靠近感兴趣的地址的街道级图像。 处理器识别图像中与街道号码视觉相似的那些部分，然后提取在这些部分中显示的字符的数值。 如果提取的值对应于感兴趣的地址的建筑物号码，例如基本上等于感兴趣的地址，则提取的值和图像部分被显示给人类操作者。 人类操作者通过观察图像部分来确认图像部分是否看起来是与提取的值相匹配的建筑物号码。 如果是这样，处理器存储将建筑物号码与街道图像相关联的值。
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.047 seconds)
