公开(公告)号：US20150172623A1

公开(公告)日：2015-06-18

申请号：US14107534

申请日：2013-12-16

Applicant: Xerox Corporation

Inventor： Wencheng WU ,  Edgar A. BERNAL ,  Himanshu J. MADHU ,  Michael C. MONGEON

IPC: H04N13/00

CPC classification number: H04N13/139 ,  H04N13/111 ,  H04N13/128 ,  H04N2213/003

Abstract: What is disclosed is a system and method for enhancing a spatio-temporal resolution of a depth data stream. In one embodiment, time-sequential reflectance frames and time-sequential depth frames of a scene are received. If a temporal resolution of the reflectance frames is greater than the depth frames then a new depth frame is generated based on correlations determined between motion patterns in the sequence of reflectance frames and the sequence of depth frames. The new depth frame is inserted into the sequence of depth frames at a selected time point. If a spatial resolution of the reflectance frames is greater than the depth frames then the spatial resolution of a selected depth frame is enhanced by generating new pixel depth values which are added to the selected depth frame. The spatially enhanced depth frame is then inserted back into the sequence of depth frames.

Abstract translation: 公开的是用于增强深度数据流的时空分辨率的系统和方法。 在一个实施例中，接收场景的时序反射帧和时间顺序深度帧。 如果反射率帧的时间分辨率大于深度帧，则基于在反射帧序列中的运动模式和深度帧序列之间确定的相关性来生成新的深度帧。 在所选择的时间点将新的深度帧插入到深度帧序列中。 如果反射率帧的空间分辨率大于深度帧，则通过生成添加到所选择的深度帧的新像素深度值来增强所选深度帧的空间分辨率。 然后将空间增强的深度帧插入到深度帧序列中。

公开(公告)号：US20140368639A1

公开(公告)日：2014-12-18

申请号：US13920241

申请日：2013-06-18

Applicant: Xerox Corporation

Inventor： Wencheng WU ,  Edgar A. BERNAL ,  Lalit Keshav MESTHA ,  Paul R. AUSTIN

IPC: G01B11/02

CPC classification number: G01B11/00 ,  G01B11/2513 ,  H04M2250/52

Abstract: What is disclosed is a wireless cellular device capable of determining a volume of an object in an image captured by a camera of that apparatus. In one embodiment, the present wireless cellular device comprises an illuminator for projecting a pattern of structured light with known spatial characteristics, and a camera for capturing images of an object for which a volume is to be estimated. The camera is sensitive to a wavelength range of the projected pattern of structured light. A spatial distortion is introduced by a reflection of the projected pattern off a surface of the object. And processor executing machine readable program instructions for performing the method of: receiving an image of the object from the camera; processing the image to generate a depth map; and estimating a volume of the object from the depth map. A method for using the present wireless cellular device is also provided.

Abstract translation: 所公开的是能够确定由该设备的照相机拍摄的图像中的物体的体积的无线蜂窝设备。 在一个实施例中，本无线蜂窝设备包括用于投射具有已知空间特征的结构化光的图案的照明器，以及用于捕获要估计音量的对象的图像的照相机。 相机对结构光的投影图案的波长范围敏感。 通过将投影图案从物体的表面反射出来引入空间失真。 以及处理器执行机器可读程序指令，用于执行以下方法：从所述摄像机接收所述对象的图像; 处理图像以生成深度图; 并从深度图估计对象的体积。 还提供了一种使用本无线蜂窝设备的方法。

公开(公告)号：US20150187082A1

公开(公告)日：2015-07-02

申请号：US14141610

申请日：2013-12-27

Applicant: Xerox Corporation

Inventor： Edgar A. BERNAL ,  Wencheng WU ,  Lalit Keshav MESTHA

IPC: G06T7/00 ,  G06K9/46

CPC classification number: G06T7/0075 ,  G06K9/4604 ,  G06T7/11 ,  G06T7/521 ,  G06T7/593 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20004 ,  G06T2207/20104 ,  G06T2207/30201

Abstract: What is disclosed is a system and method for adaptively reconstructing a depth map of a scene. In one embodiment, upon receiving a mask identifying a region of interest (ROI), a processor changes either a spatial attribute of a pattern of source light projected on the scene by a light modulator which projects an undistorted pattern of light with known spatio-temporal attributes on the scene, or changes an operative resolution of a depth map reconstruction module. A sensing device detects the reflected pattern of light. A depth map of the scene is generated by the depth map reconstruction module by establishing correspondences between spatial attributes in the detected pattern and spatial attributes of the projected undistorted pattern and triangulating the correspondences to characterize differences therebetween. The depth map is such that a spatial resolution in the ROI is higher relative to a spatial resolution of locations not within the ROI.

Abstract translation: 公开的是用于自适应地重建场景的深度图的系统和方法。 在一个实施例中，在接收到识别感兴趣区域（ROI）的掩模之后，处理器通过光调制器来改变投射在场景上的源光的图案的空间属性，所述光调制器将未失真的光模式投射到已知的时空 场景上的属性，或改变深度图重建模块的可操作分辨率。 感测装置检测光的反射图案。 由深度图重建模块通过建立检测图案中的空间属性与投射的未失真模式的空间属性之间的对应关系并对其对应性进行三角测量，来形成场景的深度图。 深度图使得ROI中的空间分辨率相对于不在ROI内的位置的空间分辨率较高。

公开(公告)号：US20150051461A1

公开(公告)日：2015-02-19

申请号：US13968794

申请日：2013-08-16

Applicant: Xerox Corporation

Inventor： Edul N. DALAL ,  Wencheng WU ,  Lalit Keshav MESTHA

IPC: A61B5/024 ,  A61B5/01 ,  A61B5/1455 ,  A61B5/00

CPC classification number: A61B5/02433 ,  A61B5/0064 ,  A61B5/0077 ,  A61B5/01 ,  A61B5/02427 ,  A61B5/1176 ,  A61B5/1455 ,  A61B5/14552 ,  A61B5/441

Abstract: What is disclosed is a system and method for performing a medical diagnosis for a subject of interest using a RGB video camera and a spot radiometer in a non-contact, remote sensing environment. In one embodiment, video images are captured using a RGB video camera in real-time of a subject of interest for medical diagnostic purposes. The video images are analyzed to identify a region of exposed skin for which measurements are desired to be obtained. A relative position of a spot radiometer is then adjusted such that the spot radiometer can measure incident radiation at a desired wavelength range from the identified region of exposed skin. The measurements are then used to perform a medical diagnosis for the subject. Various embodiments are disclosed.

Abstract translation: 公开的是用于在非接触式遥感环境中使用RGB摄像机和点辐射计对感兴趣对象进行医学诊断的系统和方法。 在一个实施例中，为了医疗诊断目的，利用RGB摄像机实时拍摄感兴趣的对象的视频图像。 分析视频图像以识别期望获得测量的暴露皮肤的区域。 然后调整点辐射计的相对位置，使得点辐射计可以从所识别的暴露皮肤区域测量在期望波长范围内的入射辐射。 然后测量用于对受试者执行医学诊断。 公开了各种实施例。

公开(公告)号：US20150003738A1

公开(公告)日：2015-01-01

申请号：US14085143

申请日：2013-11-20

Applicant: Xerox Corporation

Inventor： Edgar A. BERNAL ,  Xuejin WEN ,  Wencheng WU ,  Lalit Keshav MESTHA

IPC: G06T11/00 ,  G06K9/32

CPC classification number: G06T11/003 ,  G06K9/2054 ,  G06K9/209 ,  G06K9/3233 ,  G06K9/6249 ,  H03M7/3062 ,  H04N19/60

Abstract: What is disclosed is a system and method which reconstructs an N-pixel image of a scene such that Q pixel locations associated with identified regions of interest in a scene have a higher image quality when rendered relative to other pixels in the image. Acquisition and adaptive-quality compression are performed simultaneously by semi-synchronously or asynchronously temporally modulating an ordered set of sampling functions used to spatially modulate a pattern of light. The teachings hereof improve compression efficiency of a compressed sensing framework while improving encoding efficiency with respect to traditional compressed sensing techniques.

Abstract translation: 所公开的是一种重建场景的N像素图像的系统和方法，使得当相对于图像中的其他像素渲染时，与场景中的识别的感兴趣区域相关联的Q个像素位置具有较高的图像质量。 通过半同步或异步时间调制用于空间调制光模式的有序集合采样功能同时执行采集和自适应质量压缩。 本发明的教导提高了压缩感测框架的压缩效率，同时提高了传统压缩感测技术的编码效率。

公开(公告)号：US20140355820A1

公开(公告)日：2014-12-04

申请号：US13905788

申请日：2013-05-30

Applicant: XEROX CORPORATION

Inventor： Wencheng WU ,  Edgar A. BERNAL ,  Lalit Keshav MESTHA ,  Paul R. AUSTIN

IPC: G06T7/00

CPC classification number: G06T7/004 ,  G06T7/75 ,  G06T2207/30244

Abstract: What is disclosed a system and method for estimating a position (or pose) of a camera relative to a surface upon which an object rests in an image captured by that camera such that a volume can be estimated for that object. In one embodiment, a matrix K is determined from parameters intrinsic to a camera used to capture image. An amount of a camera translation T is determined with respect to a set of real-world coordinates in (X,Y,Z). An amount of a camera rotation matrix R is determined from camera angles measured with respect to the real-world coordinates. A distance Zc of the camera at location (i,j) can then be estimated. A volume of the object in an image of that object can be estimated from the camera pose.

Abstract translation: 公开了一种用于估计相机相对于表面的位置（或姿态）的系统和方法，在该表面上物体停留在由该相机拍摄的图像中，使得可以为该对象估计音量。 在一个实施例中，矩阵K由用于捕获图像的相机固有的参数确定。 相对于（X，Y，Z）中的一组真实世界坐标来确定相机平移度T的量。 从相对于真实世界坐标测量的相机角度确定相机旋转矩阵R的量。 然后可以估计位置（i，j）处的摄像机的距离Zc。 可以从相机姿态估计该物体的图像中的物体的体积。

公开(公告)号：US20160086341A1

公开(公告)日：2016-03-24

申请号：US14958157

申请日：2015-12-03

Applicant: Xerox Corporation

Inventor： Edgar A. BERNAL ,  Wencheng WU ,  Lalit Keshav MESTHA

IPC: G06T7/00 ,  G06K9/46

CPC classification number: G06K9/4604 ,  G06T7/11 ,  G06T7/521 ,  G06T7/593 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20004 ,  G06T2207/20104 ,  G06T2207/30201

Abstract: What is disclosed is a system and method for adaptively reconstructing a depth map of a scene. In one embodiment, upon receiving a mask identifying a region of interest (ROI), a processor changes either a spatial attribute of a pattern of source light projected on the scene by a light modulator which projects an undistorted pattern of light with known spatio-temporal attributes on the scene, or changes an operative resolution of a depth map reconstruction module. A sensing device detects the reflected pattern of light. A depth map of the scene is generated by the depth map reconstruction module by establishing correspondences between spatial attributes in the detected pattern and spatial attributes of the projected undistorted pattern and triangulating the correspondences to characterize differences therebetween. The depth map is such that a spatial resolution in the ROI is higher relative to a spatial resolution of locations not within the ROI.