公开(公告)号：US09418426B1

公开(公告)日：2016-08-16

申请号：US14606469

申请日：2015-01-27

Applicant: Xerox Corporation

Inventor： Edgar A. Bernal ,  Qun Li

IPC: G06K9/00 ,  G06K9/34 ,  G06T7/00 ,  G06T7/40 ,  H04N9/04

CPC classification number: G06T7/408 ,  G06T7/254 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20032 ,  G06T2207/20081 ,  G06T2207/30232

Abstract: A camera outputs video as a sequence of video frames having pixel values in a first (e.g., relatively low dimensional) color space, where the first color space has a first number of channels. An image-processing device maps the video frames to a second (e.g., relatively higher dimensional) color representation of video frames. The mapping causes the second color representation of video frames to have a greater number of channels relative to the first number of channels. The image-processing device extracts a second color representation of a background frame of the scene. The image-processing device can then detect foreground objects in a current frame of the second color representation of video frames by comparing the current frame with the second color representation of a background frame. The image-processing device then outputs an identification of the foreground objects in the current frame of the video.

Abstract translation: 相机将视频输出为具有第一（例如相对低维）色彩空间中的像素值的视频帧序列，其中第一颜色空间具有第一数量的通道。 图像处理设备将视频帧映射到视频帧的第二（例如较高维度）的颜色表示。 映射使得视频帧的第二颜色表示相对于第一数量的信道具有更多数量的信道。 图像处理装置提取场景的背景帧的第二颜色表示。 然后，图像处理装置可以通过将当前帧与背景帧的第二颜色表示进行比较来检测视频帧的第二颜色表示的当前帧中的前景对象。 然后，图像处理装置输出视频的当前帧中的前景对象的标识。

公开(公告)号：US09390328B2

公开(公告)日：2016-07-12

申请号：US14262276

申请日：2014-04-25

Applicant: Xerox Corporation

Inventor： Matthew Adam Shreve ,  Qun Li ,  Edgar A. Bernal ,  Robert P. Loce

IPC: G06K9/00 ,  G06K9/52 ,  G06T7/00 ,  G06K9/46 ,  G06T7/20

CPC classification number: G06K9/00624 ,  G06K9/46 ,  G06K9/52 ,  G06K2009/4666 ,  G06T5/005 ,  G06T5/50 ,  G06T7/20 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30236 ,  G06T2207/30241

Abstract: This disclosure provides a static occlusion handling method and system for use with appearance-based video tracking algorithms where static occlusions are present. The method and system assumes that the objects to be tracked move in according to structured motion patterns within a scene, such as vehicles moving along a roadway. A primary concept is to replicate pixels associated with the tracked object from previous frames to current or future frames when the tracked object coincides with a static occlusion, where the predicted motion of the tracked object is a basis for replication of the pixels.

Abstract translation: 本公开提供了一种静态遮挡处理方法和系统，用于与存在静态遮挡的基于外观的视频跟踪算法。 方法和系统假设要跟踪的对象根据场景内的结构化运动模式移动，例如沿着道路行驶的车辆。 主要概念是当被跟踪的对象与静态遮挡一致时，将跟踪对象与先前帧相关联的像素复制到当前或将来的帧，其中跟踪对象的预测运动是像素复制的基础。

公开(公告)号：US09323991B2

公开(公告)日：2016-04-26

申请号：US14089887

申请日：2013-11-26

Applicant: Xerox Corporation

Inventor： Edgar A. Bernal ,  Peter Paul ,  Daniel Hann ,  Thomas F. Wade

IPC: G06K9/00 ,  G06T7/20

CPC classification number: G06K9/00771 ,  G06K9/00765 ,  G06K9/00785 ,  G06T7/215 ,  G06T7/223 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20036 ,  G06T2207/30232 ,  G06T2207/30236

Abstract: A method and system for adaptable video-based object tracking includes acquiring video data from a scene of interest and identifying an initial instance of an object of interest in the acquired video data. A representation of a target object is then established. One or more motion parameters associated with said scene of interest are used to adjust the size of a search neighborhood associated with said target object. The target object is then tracked frame-by-frame in the video data.

Abstract translation: 一种用于基于适应性的基于视频的对象跟踪的方法和系统包括从感兴趣的场景中获取视频数据并识别所获取的视频数据中的感兴趣对象的初始实例。 然后建立目标对象的表示。 与所述感兴趣场景相关联的一个或多个运动参数用于调整与所述目标对象相关联的搜索邻域的大小。 然后在视频数据中逐帧跟踪目标对象。

公开(公告)号：US09253503B2

公开(公告)日：2016-02-02

申请号：US13718030

申请日：2012-12-18

Applicant: Xerox Corporation

Inventor： Edgar A. Bernal ,  Stuart A. Schweid ,  Orhan Bulan

IPC: H04N19/513 ,  H04N19/57

CPC classification number: H04N19/521 ,  H04N19/57

Abstract: The method facilitates efficient motion estimation for video sequences captured with a stationary camera with respect to an object. For video captured with this type of camera, a main cause of changes between adjacent frames corresponds to object motion. In this setting the output from the motion compensation stage is the block matching algorithm describing the way pixel blocks move between adjacent frames. For video captured with cameras mounted on moving vehicles (e.g. school buses, public transportation vehicles and police cars), the motion of the vehicle itself is the largest source of apparent motion in the captured video. In both cases, the encoded set of motion vectors is a good descriptor of apparent motion of objects within the field of view of the camera.

Abstract translation: 该方法有助于相对于对象利用固定照相机拍摄的视频序列的有效运动估计。 对于使用这种相机拍摄的视频，相邻帧之间变化的主要原因对应于物体运动。 在该设置中，来自运动补偿级的输出是描述像素块在相邻帧之间移动的方式的块匹配算法。 对于搭载在移动车辆（例如校车，公共交通车辆和警车）上的摄像机拍摄的视频，车辆本身的运动是所捕获视频中最大的明显动作来源。 在这两种情况下，编码的运动矢量集合是在相机视场内的物体的明显运动的良好描述符。

公开(公告)号：US09253420B2

公开(公告)日：2016-02-02

申请号：US14178904

申请日：2014-02-12

Applicant: Xerox Corporation

Inventor： Peter J. Nystrom ,  Lalit K. Mestha ,  Edgar A. Bernal ,  Xuejin Wen ,  Peter Gulvin

IPC: H04N5/33 ,  G02B5/20 ,  H04N5/335

CPC classification number: H04N5/332 ,  G01J3/021 ,  G01J3/0229 ,  G01J3/0264 ,  G01J3/26 ,  G01J3/2823 ,  G01J3/2846 ,  G02B5/204 ,  H04N5/335

Abstract: A method is provided for using a single-pixel imager in order to spatially reconstruct an image of a scene. The method can comprise the following: configuring a light filtering device including an array of imaging elements to a spatially varying optical filtering process of incoming light according to a series of spatial patterns corresponding to sampling functions. The light filtering device can be a transmissive filter including a first membrane, a second membrane, and a variable gap therebetween. The method further comprises tuning a controller for manipulating a variable dimension of the gap; and, measuring, using a photodetector of the single-pixel imager, a magnitude of an intensity of the filtered light across pixel locations in the series of spatial patterns. The magnitude of the intensity can be equivalent to an integral value of the scene across the pixel locations.

Abstract translation: 提供了一种用于使用单像素成像器以便空间重建场景的图像的方法。 该方法可以包括以下：根据与采样功能相对应的一系列空间模式，将包括成像元件阵列的光滤波装置配置到入射光的空间变化的光学滤波处理。 光过滤装置可以是包括第一膜，第二膜和它们之间的可变间隙的透射过滤器。 该方法还包括调整控制器以操纵间隙的可变尺寸; 以及使用所述单像素成像器的光电检测器测量所述一系列空间图案中的像素位置之间的经过滤光的强度的大小。 强度的大小可以等于像素位置上的场景的积分值。

公开(公告)号：US20150312529A1

公开(公告)日：2015-10-29

申请号：US14261013

申请日：2014-04-24

Applicant: Xerox Corporation

Inventor： Edgar A. Bernal ,  Qun Li ,  Robert P. Loce

IPC: H04N7/18

CPC classification number: G06K9/00785 ,  G06K9/00771 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30236 ,  G06T2207/30241

Abstract: A method for automatically determining a dynamic queue configuration includes acquiring a series of frames from an image source surveying a queue area. The method includes detecting at least one subject in a frame. The method includes tracking locations of each detected subject across the series of frames. The method includes generating calibrated tracking data by mapping the tracking locations to a predefined coordinate system. The method includes localizing a queue configuration descriptor based on the tracking data.

Abstract translation: 用于自动确定动态队列配置的方法包括从测量队列区域的图像源获取一系列帧。 该方法包括检测帧中的至少一个被摄体。 该方法包括在该系列帧中跟踪每个检测到的对象的位置。 该方法包括通过将跟踪位置映射到预定义的坐标系来生成校准的跟踪数据。 该方法包括基于跟踪数据来定位队列配置描述符。

公开(公告)号：US20150310458A1

公开(公告)日：2015-10-29

申请号：US14279652

申请日：2014-05-16

Applicant: Xerox Corporation

Inventor： Edgar A. Bernal ,  Qun Li ,  Robert P. Loce

IPC: G06Q30/02 ,  G08B13/196 ,  G01S3/786

CPC classification number: G06Q30/0201 ,  G06K9/00778 ,  G06K9/00798 ,  G06Q50/12

Abstract: A system and method for detecting customer drive-off/walk-off from a customer queue. An embodiment includes acquiring images of a retail establishment, said images including at least a portion of a customer queue region, determining a queue configuration within the images, analyzing the images to detect entry of a customer into the customer queue, tracking a customer detected in the customer queue as the customer progresses within the queue, analyzing the images to detect if the customer leaves the customer queue, and generating a drive-off notification if a customer leaves the queue.

Abstract translation: 一种用于从客户队列中检测客户关机/脱离的系统和方法。 一个实施例包括获取零售店的图像，所述图像包括客户队列区域的至少一部分，确定图像内的队列配置，分析图像以检测客户进入客户队列中的进入，跟踪客户检测到的客户 客户队列随着客户队列中的进展，分析图像以检测客户是否离开客户队列，如果客户离开队列，则生成停车通知。

公开(公告)号：US20150310370A1

公开(公告)日：2015-10-29

申请号：US14260915

申请日：2014-04-24

Applicant: Xerox Corporation

Inventor： Aaron M. Burry ,  Peter Paul ,  Edgar A. Bernal ,  Orhan Bulan

IPC: G06Q10/06 ,  G06T7/00 ,  G06T7/20 ,  G06K9/00 ,  G06K9/62

CPC classification number: G06Q10/06316 ,  G06K9/00711 ,  G06K9/00785 ,  G06K9/00791 ,  G06K9/6267 ,  G06Q50/12 ,  G06T7/20

Abstract: A method for updating an event sequence includes acquiring video data of a queue area from at least one image source; searching the frames for subjects located at least near a region of interest (ROI) of defined start points in the video data; tracking a movement of each detected subject through the queue area over a subsequent series of frames; using the tracking, determining if a location of the a tracked subject reaches a predefined merge point where multiple queues in the queue area converge into a single queue lane; in response to the tracked subject reaching the predefined merge point, computing an observed sequence of where the tracked subject places among other subjects approaching an end-event point; and, updating a sequence of end-events to match the observed sequence of subjects in the single queue lane.

Abstract translation: 一种用于更新事件序列的方法包括从至少一个图像源获取队列区域的视频数据; 在所述帧中搜索位于所述视频数据中定义的起点的至少接近感兴趣区域（ROI）的对象; 在随后的一系列帧中跟踪每个检测到的对象通过队列区域的移动; 使用所述跟踪，确定被跟踪对象的位置是否到达所述队列区域中的多个队列收敛到单个队列通道中的预定义合并点; 响应于被跟踪的对象到达预定义的合并点，计算被跟踪对象在接近终点事件点的其他主体中所在的观察序列; 并且更新结束事件序列以匹配在单个队列通道中观察到的受试者序列。

公开(公告)号：US20150301590A1

公开(公告)日：2015-10-22

申请号：US14257393

申请日：2014-04-21

Applicant: Xerox Corporation

Inventor： Michael R. Furst ,  Edgar A. Bernal ,  Robert P. Loce ,  Lalit K. Mestha

IPC: G06F3/01 ,  A61B5/00 ,  G06T7/20 ,  G06F3/00 ,  G06T7/00 ,  A61B5/087 ,  A61B5/08

CPC classification number: G06F3/011 ,  A61B5/0077 ,  A61B5/08 ,  A61B5/0816 ,  A61B5/087 ,  A61B5/1135 ,  A61B5/7485 ,  A61B2560/0223 ,  A61B2576/00 ,  G06F3/005 ,  G06F3/012

Abstract: A method for computing output using a non-contact (invisible) input signal includes acquiring depth data of a scene captured by a depth-capable sensor. The method includes generating a temporal series of depth maps corresponding to the depth data. The method includes generating at least one volumetric attribute from the depth data. The method includes generating an output based on the volumetric attribute to control actions.

Abstract translation: 使用非接触（不可见）输入信号计算输出的方法包括获取由深度能力的传感器捕获的场景的深度数据。 该方法包括生成对应于深度数据的时间序列深度图。 该方法包括从深度数据生成至少一个体积属性。 该方法包括基于体积属性生成输出以控制动作。

公开(公告)号：US20150278616A1

公开(公告)日：2015-10-01

申请号：US14227035

申请日：2014-03-27

Applicant: Xerox Corporation

Inventor： Qun Li ,  Edgar A. Bernal ,  Matthew Shreve ,  Robert P. Loce

IPC: G06K9/00 ,  G06T7/00 ,  G06K9/62

CPC classification number: G06K9/00825 ,  G06K9/00744 ,  G06K9/6269 ,  G06T7/194 ,  G06T7/215 ,  G06T7/251 ,  G06T7/254 ,  G06T2207/10048 ,  G06T2207/20032 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30232 ,  G06T2207/30242

Abstract: A method for removing false foreground image content in a foreground detection process performed on a video sequence includes, for each current frame, comparing a feature value of each current pixel against a feature value of a corresponding pixel in a background model. The each current pixel is classified as belonging to one of a candidate foreground image and a background based on the comparing. A first classification image representing the candidate foreground image is generated using the current pixels classified as belonging to the candidate foreground image. The each pixel in the first classification image is classified as belonging to one of a foreground image and a false foreground image using a previously trained classifier. A modified classification image is generated for representing the foreground image using the pixels classified as belonging to the foreground image while the pixels classified as belonging to the false foreground image are removed.

Abstract translation: 在对视频序列执行的前景检测处理中去除假前景图像内容的方法包括：对于每个当前帧，将每个当前像素的特征值与背景模型中相应像素的特征值进行比较。 基于比较，将每个当前像素分类为属于候选前景图像和背景中的一个。 使用分类为属于候选前景图像的当前像素来生成表示候选前景图像的第一分类图像。 使用先前训练的分类器将第一分类图像中的每个像素分类为属于前景图像和假前景图像之一。 生成用于使用分类为属于前景图像的像素来表示前景图像的修改后的分类图像，而分类为属于假前景图像的像素被去除。