利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

138 条记录 (耗时 0.021 秒)

    Method of determining parking lot occupancy from digital camera images
    1.
    发明授权
    Method of determining parking lot occupancy from digital camera images 有权
    从数码相机图像中确定停车场占用的方法

    公开(公告)号：US09129524B2

    公开(公告)日：2015-09-08

    申请号：US13433809

    申请日：2012-03-29

    申请人： Diana L. Delibaltov ,  Wencheng Wu ,  Robert P. Loce ,  Edgar Bernal

    发明人： Diana L. Delibaltov ,  Wencheng Wu ,  Robert P. Loce ,  Edgar Bernal

    IPC分类号： G06K9/00 ,  G08G1/04 ,  G08G1/065 ,  G06K9/62 ,  H04N7/18 ,  G06K9/46

    CPC分类号： G08G1/04 ,  G06K9/00785 ,  G06K9/00812 ,  G06K9/6269 ,  G06K2009/4666 ,  G08G1/065

    摘要： Described herein is a method of determining parking lot occupancy from digital images, including a set-up procedure that includes receiving a layout of a parking lot and estimating parking space volume for at least one viewing angle and the probability that an observed pixel belongs to the parking space volume. The method further includes acquiring one or more image frames of the parking lot from at least one digital camera; performing pixel classification using a vehicle detector on the acquired image frames to determine a likelihood that a pixel belongs to a vehicle; computing a probability that a parking space is occupied by a vehicle based on a spatially varying membership probability density function and a likelihood of vehicle pixels within a region of interest; and determining parking lot vacancy via a comparison of the computed probability that a parking space is occupied by a vehicle to a pre-determined threshold.

    摘要翻译： 这里描述了一种从数字图像中确定停车场占用的方法，包括建立过程，其包括接收停车场的布局并估计至少一个视角的停车空间体积，以及观察像素属于 停车位容积。 该方法还包括从至少一个数字照相机获取停车场的一个或多个图像帧; 使用车辆检测器对所获取的图像帧执行像素分类，以确定像素属于车辆的可能性; 基于空间变化的隶属概率密度函数和感兴趣区域内的车辆像素的可能性来计算车辆占据的概率; 以及通过将所述计算出的停车位被车辆占据的概率与预定阈值进行比较来确定停车场空置。

    METHOD OF DETERMINING PARKING LOT OCCUPANCY FROM DIGITAL CAMERA IMAGES
    2.
    发明申请
    METHOD OF DETERMINING PARKING LOT OCCUPANCY FROM DIGITAL CAMERA IMAGES 有权
    从数码相机图像中确定停车场的方法

    公开(公告)号：US20130258107A1

    公开(公告)日：2013-10-03

    申请号：US13433809

    申请日：2012-03-29

    申请人： Diana L. Delibaltov ,  Wencheng Wu ,  Robert P. Loce ,  Edgar Bernal

    发明人： Diana L. Delibaltov ,  Wencheng Wu ,  Robert P. Loce ,  Edgar Bernal

    IPC分类号： G08G1/14 ,  H04N7/18

    CPC分类号： G08G1/04 ,  G06K9/00785 ,  G06K9/00812 ,  G06K9/6269 ,  G06K2009/4666 ,  G08G1/065

    摘要： Described herein is a method of determining parking lot occupancy from digital images, including a set-up procedure that includes receiving a layout of a parking lot and estimating parking space volume for at least one viewing angle and the probability that an observed pixel belongs to the parking space volume. The method further includes acquiring one or more image frames of the parking lot from at least one digital camera; performing pixel classification using a vehicle detector on the acquired image frames to determine a likelihood that a pixel belongs to a vehicle; computing a probability that a parking space is occupied by a vehicle based on a spatially varying membership probability density function and a likelihood of vehicle pixels within a region of interest; and determining parking lot vacancy via a comparison of the computed probability that a parking space is occupied by a vehicle to a pre-determined threshold.

    摘要翻译： 这里描述了一种从数字图像中确定停车场占用的方法，包括建立过程，其包括接收停车场的布局并估计至少一个视角的停车空间体积，以及观察像素属于 停车位容积。 该方法还包括从至少一个数字照相机获取停车场的一个或多个图像帧; 使用车辆检测器对所获取的图像帧执行像素分类，以确定像素属于车辆的可能性; 基于空间变化的隶属概率密度函数和感兴趣区域内的车辆像素的可能性来计算车辆占据的概率; 以及通过将所述计算出的停车位被车辆占据的概率与预定阈值进行比较来确定停车场空置。

    Multiple view transportation imaging systems
    3.
    发明授权
    Multiple view transportation imaging systems 有权
    多视图运输成像系统

    公开(公告)号：US08731245B2

    公开(公告)日：2014-05-20

    申请号：US13414167

    申请日：2012-03-07

    申请人： Helen HaeKyung Shin ,  Robert P. Loce ,  Wencheng Wu ,  Thomas F. Wade ,  Peter Paul ,  Edgar Bernal

    发明人： Helen HaeKyung Shin ,  Robert P. Loce ,  Wencheng Wu ,  Thomas F. Wade ,  Peter Paul ,  Edgar Bernal

    IPC分类号： G06K9/00

    CPC分类号： G08G1/04 ,  G08G1/017

    摘要： A camera may be positioned to have a direct view of on-coming vehicle traffic from a first perspective. Additionally, a reflective surface, such as a mirror, may be positioned within the viewing area of the same camera to provide the camera with a reflected view of vehicle traffic from a second perspective. The images recorded by the camera may then be received by a computing device. The computing device may separate the images into a direct view region and a reflected view region. After separation, the regions may be analyzed independently and/or combined with other regions, and the analyzed data may be stored. The regions may be analyzed to determine various vehicle characteristics, including, but not limited to, vehicle speed, license plate identification, vehicle occupancy, vehicle count, and vehicle type.

    摘要翻译： 照相机可以从第一角度定位成直接观看即将到来的车辆交通。 此外，诸如反射镜的反射表面可以被定位在同一照相机的观看区域内，以从第二角度向相机提供车辆交通的反射视图。 然后可以由计算设备接收由相机记录的图像。 计算设备可以将图像分离成直视区域和反射视区。 分离后，可以独立地和/或与其它区域组合分析区域，并且可以存储分析的数据。 可以分析区域以确定各种车辆特性，包括但不限于车辆速度，车牌识别，车辆占用，车辆数量和车辆类型。

    VEHICLE REVERSE DETECTION METHOD AND SYSTEM VIA VIDEO ACQUISITION AND PROCESSING
    5.
    发明申请
    VEHICLE REVERSE DETECTION METHOD AND SYSTEM VIA VIDEO ACQUISITION AND PROCESSING 有权
    车辆逆向检测方法和系统通过视频采集和处理

    公开(公告)号：US20130106595A1

    公开(公告)日：2013-05-02

    申请号：US13283792

    申请日：2011-10-28

    申请人： Robert P. Loce ,  Wencheng Wu ,  Edgar A. Bernal ,  Thomas F. Wade

    发明人： Robert P. Loce ,  Wencheng Wu ,  Edgar A. Bernal ,  Thomas F. Wade

    IPC分类号： B60Q1/00

    CPC分类号： G06K9/00805 ,  G06K9/00785 ,  G06K9/00825 ,  G06K9/4661 ,  G06T7/246 ,  G06T2207/30236 ,  G08G1/056

    摘要： This disclosure provides a video camera and video processing alert system for detecting a vehicle in reverse. According to one exemplary embodiment, the system operates according to the following guidelines or steps: (1) Acquire video containing features relevant to reverse detection, (2) Identify feature(s) within the video frame that are relevant to a vehicle in reverse, (3) Examine identified features to extract the evidence of vehicle backing up for a current frame, (4) Apply temporal filtering on the frame-to-frame evidence, (5) Use filtered evidence for decision on triggering the alarm, (6) Triggering an alarm if indicated by the decision. The system can be implemented with relative low cost and complexity, due to the affordability of video cameras, and the fact that many drive-through locations have existing video capture infrastructure.

    摘要翻译： 本公开提供了一种用于相反地检测车辆的摄像机和视频处理警报系统。 根据一个示例性实施例，系统根据以下准则或步骤进行操作：（1）获取包含与反向检测相关的特征的视频，（2）相反地识别与车辆相关的视频帧内的特征， （3）检查识别的特征，提取车辆备份现有证据的证据;（4）对帧间证据应用时间过滤;（5）使用过滤证据进行触发报警，（6） 如果决定指示，触发警报。 由于摄像机的负担能力以及许多驱动器位置都有现有的视频采集基础设施，因此系统可以以相对较低的成本和复杂性实现。

    Inter-separation decorrelator
    6.
    发明授权
    Inter-separation decorrelator 有权
    分离间去相干器

    公开(公告)号：US07486416B2

    公开(公告)日：2009-02-03

    申请号：US11143818

    申请日：2005-06-02

    申请人： Edul N. Dalal ,  Wencheng Wu ,  Robert P. Loce ,  Raja Bala ,  Yeqing Zhang ,  Norman W. Zeck

    发明人： Edul N. Dalal ,  Wencheng Wu ,  Robert P. Loce ,  Raja Bala ,  Yeqing Zhang ,  Norman W. Zeck

    IPC分类号： H04N1/60 ,  H04N1/04 ,  G03F3/08 ,  G06K15/00 ,  G06K9/00

    CPC分类号： H04N1/6038 ,  H04N1/6041

    摘要： Spatially dependent colorant interaction effects are identified and isolated from other aspects of spatially dependent colorant appearance nonuniformities. A decorrelating function for compensating for the identified spatially dependent colorant interaction effects is determined. Spatially dependent single colorant compensating functions for compensating for the other aspects of the spatially dependent colorant appearance nonuniformities may also be determined. Image data is processed through the decorrelating function, thereby generating colorant values that are compensated for spatially dependent colorant interaction effects. Optionally, image data is also processed through the spatially dependent single colorant compensating functions, thereby generating colorant values that are compensated for both aspects of colorant appearance nonuniformities. The two kinds of compensating functions may be determined, calibrated and/or stored at different spatial and temporal frequencies or resolutions. One or both of the compensating functions may be employed to maintain consistency across a plurality of rendering devices (e.g., marking engines).

    摘要翻译： 从空间依赖的着色剂外观不均匀性的其他方面鉴定和分离空间依赖性着色剂相互作用效应。 确定用于补偿所识别的空间依赖着色剂相互作用效应的去相关函数。 还可以确定用于补偿空间依赖着色剂外观不均匀性的其它方面的空间依赖性单色剂补偿功能。 图像数据通过去相关功能进行处理，从而产生对空间依赖的着色剂相互作用效应进行补偿的着色剂值。 可选地，还通过空间依赖的单一着色剂补偿功能来处理图像数据，由此产生着色剂值，其对着色剂外观不均匀性的两个方面进行补偿。 可以在不同的空间和时间频率或分辨率下确定，校准和/或存储两种补偿功能。 可以采用一种或两种补偿功能来保持多个渲染设备（例如，标记引擎）之间的一致性。

    AUTOMATED METHOD AND SYSTEM FOR DETECTING THE PRESENCE OF A LIT CIGARETTE
    8.
    发明申请
    AUTOMATED METHOD AND SYSTEM FOR DETECTING THE PRESENCE OF A LIT CIGARETTE 有权
    用于检测墨西哥香烟存在的自动方法和系统

    公开(公告)号：US20120262583A1

    公开(公告)日：2012-10-18

    申请号：US13089058

    申请日：2011-04-18

    申请人： Edgar A. Bernal ,  Robert P. Loce ,  Graham Pennington ,  Wencheng Wu

    发明人： Edgar A. Bernal ,  Robert P. Loce ,  Graham Pennington ,  Wencheng Wu

    IPC分类号： H04N5/33

    CPC分类号： G08B13/196 ,  G08B17/12 ,  H04N5/33

    摘要： An automated method and system for detecting the presence of a smoking product utilizing a near infrared video-processing unit in real time. One or more near infrared (NIR) video capturing units can be configured to capture a video feed. The video feed can be processed by the video-processing unit in order to detect a smoking product (e.g., a lit cigarette) within a field of view of the video capturing unit. A near infrared video sequence can be read and analyzed for the presence of a “hot spot” of a predetermined size based on pixel color information. In some cases, the motion of the hot spot can be tracked in response to the detection of the hot spot. An alarm signal can also be triggered in some cases, if the pattern of motion is consistent with that of a cigarette being smoked.

    摘要翻译： 一种用于利用近红外视频处理单元实时检测吸烟产品的存在的自动化方法和系统。 可以配置一个或多个近红外（NIR）视频捕获单元来捕获视频馈送。 可以由视频处理单元处理视频馈送，以便在视频捕获单元的视野内检测吸烟产品（例如，点燃的香烟）。 基于像素颜色信息，可以读取和分析近红外视频序列以存在预定大小的热点。 在某些情况下，可以根据热点的检测来跟踪热点的运动。 在某些情况下，如果运动模式与吸烟香烟的运动方式一致，也可以触发报警信号。

    Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems
    9.
    发明授权
    Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems 有权
    多分辨率视频分析和关键功能，保留（实时）车辆跟踪和速度执行系统的视频减少策略

    公开(公告)号：US08953044B2

    公开(公告)日：2015-02-10

    申请号：US13253261

    申请日：2011-10-05

    申请人： Wencheng Wu ,  Edgar A. Bernal ,  Robert P. Loce ,  Martin E. Hoover

    发明人： Wencheng Wu ,  Edgar A. Bernal ,  Robert P. Loce ,  Martin E. Hoover

    IPC分类号： H04N7/18 ,  G06K9/00 ,  H04N19/33 ,  H04N19/463 ,  H04N19/59 ,  G08G1/054

    CPC分类号： G06K9/00785 ,  G06K9/00993 ,  G08G1/054 ,  H04N7/18 ,  H04N19/33 ,  H04N19/463 ,  H04N19/59

    摘要： Systems and methods are disclosed that include a video-based analysis system that detects, tracks and archives vehicles in video stream data at multiple resolutions. The system includes an image capturing device that captures video stream data having video at a first high resolution. A vehicle detection module detects at least one vehicle within the video. A vehicle analysis module is configured to analyze the video and to extract one or more key vehicle features from the video to enable identification of a vehicle of interest (VOI) according to a set of predetermined criteria. A subsampling module creates a reduced resolution video stream in a second subsampled resolution that is lower than the first high resolution while maintaining the one or more extracted key features within the reduced resolution video stream in the first high resolution, and archives the reduced resolution video stream into a video database.

    摘要翻译： 公开了包括基于视频的分析系统的系统和方法，其以多种分辨率检测，跟踪和归档视频流数据中的车辆。 该系统包括：以第一高分辨率捕获具有视频的视频流数据的图像捕获装置。 车辆检测模块检测视频内的至少一辆车辆。 车辆分析模块被配置为分析视频并从视频中提取一个或多个关键车辆特征，以使得能够根据一组预定标准识别感兴趣的车辆（VOI）。 子采样模块以低于第一高分辨率的第二子采样分辨率创建降低分辨率的视频流，同时将所提取的一个或多个提取的关键特征保持在第一高分辨率的缩小分辨率视频流内，并归档该分辨率降低的视频流 进入视频数据库。

    VIDEO-BASED VEHICLE SPEED ESTIMATION FROM MOTION VECTORS IN VIDEO STREAMS
    10.
    发明申请
    VIDEO-BASED VEHICLE SPEED ESTIMATION FROM MOTION VECTORS IN VIDEO STREAMS 有权
    视频流中运动矢量的基于视频的车速估计

    公开(公告)号：US20140063247A1

    公开(公告)日：2014-03-06

    申请号：US13600742

    申请日：2012-08-31

    申请人： Edgar A. Bernal ,  Wencheng Wu ,  Orhan Bulan ,  Robert P. Loce

    发明人： Edgar A. Bernal ,  Wencheng Wu ,  Orhan Bulan ,  Robert P. Loce

    IPC分类号： G06K9/00 ,  H04N7/18

    CPC分类号： G06K9/00785 ,  H04N7/18

    摘要： Automated low-complexity video-based vehicle speed estimation is described, that operates within the video stream to screen video sequences to identify and eliminate clear non-violators and/or identify and select potential violators within a multi-layer speed enforcement system, in which deeper layers provide enhanced accuracy on selected candidate (speeding) vehicles. Video motion vector clusters corresponding to a vehicle are identified and tracked across multiple frames of captured video. Movement of the motion vector clusters translated from pixels per second to real speed (e.g. miles per hour) to determine whether the vehicle was speeding. Estimated speed data is added to the video stream data is metadata, and video segments of candidate speeding vehicles are stored and/or transmitted for subsequent review (e.g. automated or manual).

    摘要翻译： 描述了自动低复杂度视频车辆速度估计，其在视频流内操作以屏幕视频序列以识别和消除明确的非违规者和/或识别和选择多层速度执行系统中的潜在违规者，其中 更深层次的选择候选（超速）车辆的精度提高。 对应于车辆的视频运动矢量簇在捕获的视频的多个帧上被识别和跟踪。 将运动矢量簇的运动从每秒的像素转换为实际速度（例如，每小时英里），以确定车辆是否正在超速。 估计的速度数据被添加到视频流数据是元数据，并且候选超速车辆的视频段被存储和/或发送用于随后的审查（例如自动或手动）。