公开(公告)号：US20150116134A1

公开(公告)日：2015-04-30

申请号：US14066954

申请日：2013-10-30

Applicant: Xerox Corporation

Inventor： Yao Rong Wang ,  David Cummins ,  Matthew Darst ,  Graham Pennington

IPC: G08G1/14

CPC classification number: G08G1/14 ,  G08G1/141 ,  G08G1/147

Abstract: Parking occupancy detection methods, systems and processor-readable media. A laser device unit includes a laser range finder, and a programmable pan-tilt unit is deployable on site to monitor one or more parking spaces. A laser emitting and receiving unit associated with the laser range finder determines the distance of an object by estimating a time difference between an emitted laser and a received laser. The laser range finder is controllable by the programmable pan-tilt unit and scans the parking spaces. A signal-processing unit can convert the measured distance profile to a parking occupancy data to provide continuous parking space estimation data for use in parking occupancy detection.

Abstract translation: 停车场占用检测方法，系统和处理器可读介质。 激光设备单元包括激光测距仪，并且现场可部署可编程摇摄单元以监视一个或多个停车位。 与激光测距仪相关联的激光发射和接收单元通过估计发射的激光器和接收的激光器之间的时间差来确定物体的距离。 激光测距仪可由可编程摇摄单元控制，并扫描停车位。 信号处理单元可以将所测量的距离轮廓转换为停车占用数据，以提供用于停车占用检测的连续停车位估计数据。

公开(公告)号：US20150085129A1

公开(公告)日：2015-03-26

申请号：US14037490

申请日：2013-09-26

Applicant: Xerox Corporation

Inventor： Kenneth J. Mihalyov ,  Yao Rong Wang ,  Matthew T. Darst ,  David P. Cummins ,  Johannes M. Frings ,  Vincent Ronald Chastain

IPC: H04N7/18 ,  G07B15/02 ,  G06K9/00

CPC classification number: G07B15/02 ,  G06K9/00771

Abstract: Methods, systems and processor-readable media for portable parking occupancy detection. One or more cameras can be provided on a portable mast for capturing video on parking of a street. Optional attachments to the portable mast can include stabilization base and/or a set of guy ropes for further stabilizing the mast. A power unit can be utilized for delivering power to the system. A video capturing/processing unit either captures and records the video from the camera(s) for offline processing of parking occupancy or processes the videos on-site. Optionally, a wireless communication unit for transmitting either video or processed parking occupancy data to a central location can be employed.

Abstract translation: 用于便携式停车场占用检测的方法，系统和处理器可读介质。 可以在便携式桅杆上提供一个或多个照相机，用于在街道停放时捕获视频。 便携式桅杆的可选附件可以包括稳定基座和/或一组舵绳，用于进一步稳定桅杆。 动力单元可用于向系统输送电力。 视频捕获/处理单元捕获并记录来自相机的视频，用于离线处理停车场占用或处理现场的视频。 可选地，可以采用用于将视频或处理的停车占用数据发送到中心位置的无线通信单元。

公开(公告)号：US20150009048A1

公开(公告)日：2015-01-08

申请号：US13935605

申请日：2013-07-05

Applicant: Xerox Corporation

Inventor： Yao Rong Wang ,  David Cummins ,  Mathew Darst ,  Panya Chanawangsa ,  Orhan Bulan

IPC: G08G1/14

CPC classification number: G08G1/147 ,  G06Q10/02 ,  G08G1/144

Abstract: An image assisted parking space availability searching and reservation method and system. An image capturing unit can be deployed onsite (e.g., parking lot, street side parking, etc.) to monitor parking spaces/spots. A parking space detection and reservation module can be configured in association with a mobile communications device to assist in the detection and selection of particular spaces. A destination street(s) can be located via a web browser installed associated with the mobile communications device. An IP address of the image-capturing unit monitoring the parking space can be obtained and a snapshot image/video of the street can be displayed. The captured video can be processed in real-time to report parking availability with respect to the street(s) and a parking space reserved.

Abstract translation: 图像辅助停车位可用性搜索和预订方法和系统。 可以在现场（例如，停车场，街边停车场等）部署图像捕获单元以监视停车位/点。 可以与移动通信设备相关联地配置停车位检测和预约模块，以帮助检测和选择特定空间。 目的地街道可以通过与移动通信设备相关联的网络浏览器来定位。 可以获得监视停车位的图像拍摄单元的IP地址，并且可以显示街道的快照图像/视频。 拍摄的视频可以实时处理，以报告关于街道和预留的停车位的停车可用性。

公开(公告)号：US20140368652A1

公开(公告)日：2014-12-18

申请号：US13920361

申请日：2013-06-18

Applicant: XEROX CORPORATION

Inventor： Yao Rong Wang

IPC: G06K9/00

CPC classification number: G06K9/00771

Abstract: A system and method for determining parking occupancy and maintaining a database of parking occupancy data by receiving video data for a parking area from multiple video cameras, determining parking occupancy data for the parking area using the video data for the parking area, generating textual data corresponding to the parking occupancy data for the parking area, and transmitting the textual data corresponding to the parking occupancy data for the parking area to a central server. The central server can receive textual data from multiple devices and maintain and update a database of parking occupancy data based on the textual data received.

Abstract translation: 一种用于通过从多个摄像机接收停车区域的视频数据来确定停车占有率并维护一个停车占用数据的数据库的系统和方法，使用停车区域的视频数据确定停车区域的停车占用数据，生成相应的文本数据 到停车区域的停车占用数据，并且将与停车区域的停车占用数据相对应的文本数据发送到中央服务器。 中央服务器可以从多个设备接收文本数据，并根据收到的文本数据维护和更新停车占用数据的数据库。

公开(公告)号：US20130128338A1

公开(公告)日：2013-05-23

申请号：US13718127

申请日：2012-12-18

Applicant: XEROX CORPORATION

Inventor： Pinyen Lin ,  Lalit Keshav Mestha ,  Peter M. Gulvin ,  Yao Rong Wang

IPC: G02B26/00

CPC classification number: G02B26/001 ,  G01J3/26

Abstract: A method of forming a tunable Fabry-Perot filter includes forming a first reflective layer on a surface of a substrate, forming a sacrificial layer over the first reflective layer, forming a second reflective layer over the sacrificial layer, defining vias through the sacrificial layer, forming a support body over the sacrificial layer which extends into the vias and removing the sacrificial layer to define a gap intermediate the first and second reflective layers.

Abstract translation: 形成可调谐法布里 - 珀罗滤光器的方法包括在衬底的表面上形成第一反射层，在第一反射层上形成牺牲层，在牺牲层上形成第二反射层，限定穿过牺牲层的通孔， 在所述牺牲层上形成支撑体，所述牺牲层延伸到所述通孔中并移除所述牺牲层以限定所述第一和第二反射层之间的间隙。

公开(公告)号：US09523608B2

公开(公告)日：2016-12-20

申请号：US13715446

申请日：2012-12-14

Applicant: Xerox Corporation

Inventor： Beilei Xu ,  Lalit Keshav Mestha ,  Yao Rong Wang ,  Peter Paul

IPC: G01N21/01 ,  G01J3/28 ,  G06K9/00 ,  H04N5/33 ,  G01J3/51 ,  G01J3/36 ,  G06K9/20 ,  H04N9/07

CPC classification number: G01J3/2823 ,  G01J3/36 ,  G01J3/51 ,  G01J3/513 ,  G06K9/00369 ,  G06K9/00785 ,  G06K9/2018 ,  H04N5/332 ,  H04N9/07

Abstract: What is disclosed is a system and method for processing image data acquired using a multi-band infrared camera system with a spectral mosaic filter arranged in a geometric pattern without having to perform a demosaicing that is typical with processing data from an array of sensors. In one embodiment, image data that has been captured using a camera system that has a spectral filter mosaic comprising a plurality of spectral filters arrayed on a grid. A material index is determined, using intensity values collected by sensor elements associated with a cell's respective spectral filters. All of the material indices collectively generate a material index image. Thereafter, material identification is performed on the material index image using, for example, pixel classification. Because the demosaicing step can be effectively avoided, image processing time is reduced. The teachings hereof find their uses in a wide array of applications including automated HOV/HOT violation detection.

Abstract translation: 所公开的是一种用于处理使用具有以几何图案排列的频谱马赛克滤波器的多频带红外相机系统获取的图像数据的系统和方法，而不必执行典型的来自传感器阵列的数据处理的去马赛克。 在一个实施例中，已经使用具有包括排列在网格上的多个频谱滤波器的频谱滤波器马赛克的相机系统捕获的图像数据。 使用与单元相应的光谱滤波器相关联的传感器元件收集的强度值来确定材料索引。 所有材料指标共同生成材料索引图像。 此后，使用例如像素分类对材料索引图像进行材料识别。 因为可以有效地避免去马赛克步骤，所以减少了图像处理时间。 其教导在各种应用中发现其用途，包括自动HOV / HOT违规检测。

公开(公告)号：US09514366B2

公开(公告)日：2016-12-06

申请号：US14171022

申请日：2014-02-03

Applicant: Xerox Corporation

Inventor： Stuart Alan Schweid ,  Orhan Bulan ,  Yao Rong Wang ,  Wencheng Wu ,  Robert Paul Loce

IPC: H04N7/18 ,  G06K9/00

CPC classification number: G06K9/00624 ,  G06K9/00771 ,  G06K2209/23

Abstract: This disclosure provides vehicle detection methods and systems including irrelevant search window elimination and/or window score degradation. According to one exemplary embodiment, provided is a method of detecting one or more parked vehicles in a video frame, wherein candidate search windows are limited to one or more predefined window shapes. According to another exemplary embodiment, the method includes degrading a classification score of a candidate search window based on aspect ratio, window overlap area and/or a global maximal classification.

Abstract translation: 本公开提供了车辆检测方法和系统，包括无关的搜索窗口消除和/或窗口评分降级。 根据一个示例性实施例，提供了一种检测视频帧中的一个或多个停放车辆的方法，其中候选搜索窗口被限制为一个或多个预定窗口形状。 根据另一示例性实施例，该方法包括基于宽高比，窗口重叠区域和/或全局最大分类来降级候选搜索窗口的分类分数。

公开(公告)号：US09323993B2

公开(公告)日：2016-04-26

申请号：US14018628

申请日：2013-09-05

Applicant: Xerox Corporation

Inventor： Yao Rong Wang ,  David Cummins ,  Matthew Darst ,  Michael Furst ,  Panya Chanawangsa ,  Zhigang Fan

IPC: G06K9/00

CPC classification number: G06K9/00812

Abstract: Methods, systems and processor-readable media for identifying a vehicle for street parking management. An initial identification of one or more vehicles detected parked along a street can be generated based on one or more of a group of factors. The initial identification can be communicated to a user of the vehicle by transmitting an image indicative of the vehicle parked along the street (e.g., via a mobile communications device). An operation can then be implemented for requesting a confirmation or a non-confirmation as to whether the vehicle detected and displayed on the image is associated with the user. Upon confirmation, an operation can be implemented for identifying the at least one vehicle as the initial identification. Upon non-confirmation, an operation can be implemented to query to identify the vehicle associated with the user from among a group of vehicles displayed via the image.

Abstract translation: 用于识别街道停车管理的车辆的方法，系统和处理器可读介质。 可以基于一组因素中的一个或多个来产生沿着街道停放的一个或多个车辆的初始识别。 通过发送指示沿着街道停放的车辆的图像（例如，经由移动通信设备），初始识别可以被传送给车辆的用户。 然后可以实现一个操作，用于请求确认或不确认是否在图像上检测和显示的车辆与用户相关联。 在确认后，可以实施用于识别至少一辆车辆作为初始识别的操作。 在不确认的情况下，可以实现通过图像显示的一组车辆中的查询以识别与用户相关联的车辆的操作。

公开(公告)号：US20150302611A1

公开(公告)日：2015-10-22

申请号：US14254360

申请日：2014-04-16

Applicant: Xerox Corporation

Inventor： Zhigang Fan ,  Hao Wu ,  Yao Rong Wang

IPC: G06T7/60 ,  G06T7/00 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06T7/602 ,  G06K9/00791 ,  G06K9/52 ,  G06T7/60 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/30236 ,  G06T2207/30248 ,  G06T2210/12

Abstract: A method and system for determining one or more dimension estimations for a vehicle. A sequence of image frames of a vehicle is received, and a digital representation of the vehicle is extracted from each image in the sequence of image frames. A bounding box is determined for the vehicle based upon the extracted digital representation for each digital representation of the vehicle and at least one dimension of the vehicle is estimated based upon the determined bounding box. An indication of the at least one estimated dimension is output. The indication of at least one estimated dimension is transferred as an input to a comparison technique for further processing the indication of the at least one estimated dimension. The comparison technique can include a parking determination process configured to determine a recommended spot for the vehicle based upon the indication of the at least one estimated dimension.

Abstract translation: 一种用于确定车辆的一个或多个维度估计的方法和系统。 接收车辆的一系列图像帧，并且从图像帧序列中的每个图像中提取车辆的数字表示。 基于车辆的每个数字表示的提取的数字表示，为车辆确定边界框，并且基于所确定的边界框来估计车辆的至少一个维度。 输出至少一个估计尺寸的指示。 将至少一个估计维度的指示作为输入传送到比较技术，以进一步处理至少一个估计维度的指示。 比较技术可以包括停车确定过程，其被配置为基于至少一个估计维度的指示来确定车辆的推荐点。

公开(公告)号：US20150278609A1

公开(公告)日：2015-10-01

申请号：US14226078

申请日：2014-03-26

Applicant: XEROX CORPORATION

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

IPC: G06K9/00 ,  G06K9/62 ,  G06T5/00 ,  G06T7/00 ,  G06T3/40 ,  G06K9/46 ,  G06K9/52

CPC classification number: G06K9/00785 ,  G06K9/3241 ,  G06K9/46 ,  G06K9/52 ,  G06K9/6256 ,  G06K9/6267 ,  G06K2009/4666

Abstract: A method for training a vehicle detection system used in a street occupancy estimation of stationary vehicles. The method includes defining first and second areas on an image plane of an image capture device associated with monitoring for detection of vehicles. The method includes receiving video-data from a sequence of frames captured from the image capture device. The method includes determining candidate frames that include objects relevant to a classification task in the second area. The method includes extracting the objects from the candidate frames, extracting features of each extracted object, and assigning labels to the each extracted object. The method includes training at least one classifier using the labels and extracted features. The method includes using the at least one trained classifier to classify a stationary vehicle detected in the first area.

Abstract translation: 一种在固定车辆的街道占用估计中使用的车辆检测系统的训练方法。 该方法包括在与用于检测车辆的监视相关联的图像捕获装置的图像平面上限定第一和第二区域。 该方法包括从从图像捕获设备捕获的帧序列中接收视频数据。 该方法包括确定包括与第二区域中的分类任务相关的对象的候选帧。 该方法包括从候选帧中提取对象，提取每个提取的对象的特征，以及为每个提取的对象分配标签。 该方法包括使用标签和提取的特征来训练至少一个分类器。 该方法包括使用至少一个经过训练的分类器对在第一区域中检测到的静止车辆进行分类。