-
公开(公告)号：US20150160785A1
公开(公告)日：2015-06-11
申请号：US14103499
申请日：2013-12-11
Applicant: MICROSOFT CORPORATION
Inventor： Liang Wang , Sing Bing Kang , Jamie Daniel Joseph Shotton , Matheen Siddiqui , Vivek Pradeep , Steven Nabil Bathiche , Luis E. Cabrera-Cordon , Pablo Sala
CPC classification number: G06F3/0421 , G06F3/0412 , G06F3/0416 , G06F3/042 , G06F17/18 , G06K9/00389 , G06K9/2018 , G06K9/4628 , G06K9/6282
Abstract: Object detection techniques for use in conjunction with optical sensors is described. In one or more implementations, a plurality of inputs are received, each of the inputs being received from a respective one of a plurality of optical sensors. Each of the plurality of inputs are classified using machine learning as to whether the inputs are indicative of detection of an object by a respective said optical sensor.
Abstract translation: 描述了与光学传感器结合使用的物体检测技术。 在一个或多个实现中，接收多个输入，每个输入都是从多个光学传感器中的相应一个接收的。 使用机器学习来分类多个输入中的每一个，以确定输入是否指示通过相应的所述光学传感器检测物体。
-
公开(公告)号：US09558455B2
公开(公告)日：2017-01-31
申请号：US14329052
申请日：2014-07-11
Applicant: Microsoft Corporation
Inventor： Dan Johnson , Pablo Sala
CPC classification number: G06N99/005 , G06F3/0416 , G06F3/044 , G06F3/04883 , G06N5/027
Abstract: A method for touch classification includes obtaining frame data representative of a plurality of frames captured by a touch-sensitive device, analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event, computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames, and determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.
Abstract translation: 一种用于触摸分类的方法包括：获得表示由触摸敏感设备捕获的多个帧的帧数据，分析帧数据以在多个帧的每个帧中定义相应的斑点，该斑点表示触摸事件， 计算用于所述触摸事件的多个特征集，每个特征集指定所述多个帧的每个帧中的相应斑点的属性，以及经由机器学习分类确定所述触摸事件的类型，所述类型被配置为提供多个非双峰分类分数 基于多个帧的多个特征集合，每个非双模态分类分数表示机器学习分类中的模糊度级别。
-
公开(公告)号：US20160012348A1
公开(公告)日：2016-01-14
申请号：US14329052
申请日：2014-07-11
Applicant: Microsoft Corporation
Inventor： Dan Johnson , Pablo Sala
CPC classification number: G06N99/005 , G06F3/0416 , G06F3/044 , G06F3/04883 , G06N5/027
Abstract: A method for touch classification includes obtaining frame data representative of a plurality of frames captured by a touch-sensitive device, analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event, computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames, and determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.
Abstract translation: 一种用于触摸分类的方法包括：获得表示由触摸敏感设备捕获的多个帧的帧数据，分析帧数据以在多个帧的每个帧中定义相应的斑点，该斑点表示触摸事件， 计算用于所述触摸事件的多个特征集，每个特征集指定所述多个帧的每个帧中的相应斑点的属性，以及经由机器学习分类确定所述触摸事件的类型，所述类型被配置为提供多个非双峰分类分数 基于多个帧的多个特征集合，每个非双模态分类分数表示机器学习分类中的模糊度级别。
-
公开(公告)号：US20150205445A1
公开(公告)日：2015-07-23
申请号：US14162440
申请日：2014-01-23
Applicant: Microsoft Corporation
Inventor： Vivek Pradeep , Liang Wang , Pablo Sala , Luis Eduardo Cabrera-Cordon , Steven Nabil Bathiche
CPC classification number: G06F3/0425 , G06F3/0416 , G06F3/042 , G06K9/4642
Abstract: Global and local light detection techniques in optical sensor systems are described. In one or more implementations, a global lighting value is generated that describes a global lighting level for a plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors. An illumination map is generated that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors. Object detection is performed using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.
Abstract translation: 描述了光学传感器系统中的全局和局部光检测技术。 在一个或多个实施方案中，产生基于从多个光学传感器接收的多个输入来描述多个光学传感器的全局照明水平的全局照明值。 产生基于从多个光学传感器接收的多个输入来描述多个光学传感器中的相应光学传感器的本地照明条件的照明图。 使用使用多个光学传感器捕获的图像以及全局照明值和照明映射来执行对象检测。
-
-
-
Search Results
4
records
(took 0.013 seconds)
