公开(公告)号：US20140363045A1

公开(公告)日：2014-12-11

申请号：US13913606

申请日：2013-06-10

Applicant: XEROX CORPORATION

Inventor： Wencheng Wu ,  Edul N. Dalal ,  Orhan Bulan

IPC: G06T5/20

CPC classification number: G06T5/50 ,  G06T5/002 ,  G06T2207/10016 ,  G06T2207/20032 ,  G06T2207/20182 ,  G06T2207/20224 ,  G06T2207/30232 ,  G06T2207/30236

Abstract: Methods and systems receive a series of images and compare at least two of the images in the series of images to locate items that are in different positions to identify moving items. Such methods and systems further calculate a measure of the moving items within the series of images. Additionally, such methods and systems perform a continuously variable image correction to remove the moving items from the images to produce a series of corrected images. This “continuously variable image correction” increases the amount of image correction for a relatively higher measure of the moving items and decreases the amount of image correction for a relatively lower measure of the moving items, and does so continuously as the measure of the moving items changes within the series of images.

Abstract translation: 方法和系统接收一系列图像并且比较一系列图像中的至少两个图像以定位处于不同位置的物体以识别移动物品。 这样的方法和系统进一步计算一系列图像内的移动物品的度量。 此外，这样的方法和系统执行连续可变的图像校正以从图像中移除移动项目以产生一系列校正图像。 这种“连续可变图像校正”增加了移动项目的相对较高测量的图像校正量，并且减少了用于移动项目的相对较低测量的图像校正量，并且作为移动项目的度量 一系列图像内的变化。

公开(公告)号：US20140362230A1

公开(公告)日：2014-12-11

申请号：US13914752

申请日：2013-06-11

Applicant: Xerox Corporation

Inventor： Orhan Bulan ,  Edgar A. Bernal ,  Robert P. Loce

IPC: G06K9/00 ,  H04N5/232

CPC classification number: G06K9/00624 ,  G06K9/00785 ,  G06K9/3241 ,  G06K2209/23

Abstract: This disclosure provides methods and systems of classifying a vehicle using motion vectors associated with captured images including a vehicle. According to an exemplary method, a cluster of motion vectors representative of a vehicle within a target region is analyzed to determine geometric attributes of the cluster and/or measure a length of a detected vehicle, which provides a basis for classifying the detected vehicle.

Abstract translation: 本公开提供了使用与包括车辆的捕获图像相关联的运动矢量对车辆进行分类的方法和系统。 根据示例性方法，分析表示目标区域内的车辆的运动矢量的群集，以确定群集的几何属性和/或测量检测到的车辆的长度，这为检测到的车辆进行分类提供了依据。

公开(公告)号：US20140270381A1

公开(公告)日：2014-09-18

申请号：US13836310

申请日：2013-03-15

Applicant: XEROX CORPORATION

Inventor： Wencheng Wu ,  Orhan Bulan ,  Yao Rong Wang ,  Robert P. Loce

IPC: G08G1/14 ,  G06K9/00 ,  G06K9/62

CPC classification number: G08G1/14 ,  G06K9/00771 ,  G06K9/00785 ,  G06K9/6262 ,  G06K9/6267 ,  G08G1/04 ,  G08G1/146 ,  G08G1/147

Abstract: Disclosed are methods and systems for detecting one or more vehicles in video captured from a deployed video camera directed at a parking region. According to one exemplary embodiment, disclosed is a method of training a deployed classifier associated with the video camera, where a generic classifier is initially used to obtain high confidence training samples from the video camera, the high confidence training samples subsequently used to train the deployed classifier.

Abstract translation: 公开了用于检测从部署在停车区域的摄像机捕获的视频中的一个或多个车辆的方法和系统。 根据一个示例性实施例，公开了一种训练与摄像机相关联的已部署分类器的方法，其中最初使用通用分类器从摄像机获得高信度训练样本，随后用于训练所部署的高置信训练样本 分类器

公开(公告)号：US20140145862A1

公开(公告)日：2014-05-29

申请号：US13684817

申请日：2012-11-26

Applicant: XEROX CORPORATION

Inventor： Yao Rong Wang ,  Zhigang Fan ,  Robert P. Loce ,  Orhan Bulan ,  Norman W. Zeck ,  Graham Pennington

IPC: G08G1/14

CPC classification number: G08G1/04 ,  G08G1/065 ,  G08G1/141 ,  G08G1/142 ,  G08G1/147

Abstract: A method and structure for estimating parking occupancy within an area of interest can include the use of at least two image capture devices and a processor (e.g., a computer) which form at least part of a network. A method for estimating the parking occupancy within the area of interest can include the use of vehicle entry and exit data from the area of interest, as well as an estimated transit time for vehicles transiting through the area of interest without parking.

Abstract translation: 用于估计感兴趣区域内的停车占有率的方法和结构可以包括使用至少两个图像捕获装置和形成网络的至少一部分的处理器（例如，计算机）。 用于估计感兴趣区域内的停车占用的方法可以包括使用来自感兴趣区域的车辆入口和出口数据，以及在没有停车的情况下经过感兴趣区域的车辆的估计过境时间。