公开(公告)号：US5701398A

公开(公告)日：1997-12-23

申请号：US684683

申请日：1996-07-19

申请人： Michael T. Glier ,  John Cole ,  Mark Laird

发明人： Michael T. Glier ,  John Cole ,  Mark Laird

IPC分类号： G06N3/04 ,  G06N3/063 ,  G06F15/18

CPC分类号： G06K9/6273 ,  G06K9/6274 ,  G06N3/0454 ,  G06N3/063

摘要： A neural network including a plurality of sub-nets stored in a memory array and a method of operation. Each of the sub-nets includes a corresponding plurality of weights and is individually operable to classify an input vector. A computation unit, including a distance calculation unit and a math unit, is responsive to an input vector comprising input training features for determining a distance between the weights of each sub-net to each of the input features of the input vector and for determining whether the distance is within a particular region of influence. Also described is a parallel process for training the sub-nets.

摘要翻译： 包括存储在存储器阵列中的多个子网的神经网络和操作方法。 每个子网包括相应的多个权重，并且可单独地操作以对输入向量进行分类。 包括距离计算单元和数学单元的计算单元响应于包括输入训练特征的输入向量，用于确定每个子网的权重与输入向量的每个输入特征之间的距离，并且用于确定是否 距离在特定的影响范围内。 还描述了用于训练子网的并行过程。

公开(公告)号：US06281808B1

公开(公告)日：2001-08-28

申请号：US09444942

申请日：1999-11-22

申请人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel ,  Douglas L. Reilly

发明人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel ,  Douglas L. Reilly

IPC分类号： G08G101

CPC分类号： G08G1/054 ,  G07B15/06 ,  G08G1/0175 ,  G08G1/07 ,  G08G1/08 ,  G08G1/164 ,  Y10S707/99932 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A collision avoidance system and method for a traffic intersection having a traffic light, which selectively extends the duration of a red light cycle to prevent traffic from entering the intersection during a red light violation. Output from one or more violation prediction image capturing devices is used to provide images showing one or more vehicles approaching the intersection. A violation prediction unit, which is also coupled to a signal reflecting a current light phase of the first traffic signal, receives and processes vehicle location information derived from the images to generate violation predictions for the vehicles approaching the intersection. The violation prediction indicates a likelihood that an associated vehicle will violate an upcoming red light phase of the traffic signal. In response to the violation prediction, a violation predicted signal is provided to a traffic signal controlling traffic intersecting with the predicted violator. That traffic signal then preempts a transition to a green light phase, thus extending a current red traffic light phase and thereby preventing traffic from entering the intersection during the predicted red light violation.

摘要翻译： 一种具有交通灯的交通路口的防撞系统和方法，其选择性地延长红灯循环的持续时间，以防止红灯违规期间交通进入交叉路口。 使用来自一个或多个违规预测图像捕获装置的输出来提供示出接近交叉路口的一个或多个车辆的图像。 还耦合到反映第一交通信号灯的当前光相位的信号的违规预测单元接收并处理从图像导出的车辆位置信息，以生成接近交叉口的车辆的违规预测。 违规预测表明相关联的车辆将违反交通信号灯的即将到来的红灯阶段的可能性。 响应于违规预测，将违规预测信号提供给控制与预测违规者相交的交通信号的交通信号。 该交通信号然后抢占向绿灯阶段的过渡，从而延长当前的红色交通灯阶段，从而防止在预测的红光违规期间交通进入交叉路口。

公开(公告)号：US06573929B1

公开(公告)日：2003-06-03

申请号：US09444084

申请日：1999-11-22

申请人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel

发明人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel

IPC分类号： H04N718

CPC分类号： G08G1/054 ,  G07B15/06 ,  G08G1/0175 ,  G08G1/07 ,  G08G1/08 ,  G08G1/164 ,  Y10S707/99932 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A traffic light violation prediction and recording system, including at least one violation prediction video camera and a violation prediction unit. The violation prediction unit generates violation probability scores for vehicles approaching a traffic intersection based on attributes of those vehicles, such as position, current speed and acceleration. The violation probability scores are passed to a violation recording unit, which allocates violation recording resources, such as a violation video camera, to capture activities of one or more vehicles associated with relatively high violation probabilities. The violation recording unit determines a violation recording resource allocation schedule. If sufficient resources cannot be allocated to record all possible violations within a given time period, the violation recording unit may ignore a potential violation having a relatively low priority. In one embodiment, the violation recording resources include a number of video cameras, as well as one or more violation recorders capable of producing digital data files for storing video recordings of the violation as it occurred.

摘要翻译： 一种交通灯违规预测和记录系统，包括至少一个违规预测摄像机和违规预测单元。 违规预测单元根据这些车辆的属性，如位置，当前速度和加速度，对接近交通路口的车辆产生违规概率分数。 违规概率分数被传递到违规记录单元，其违例记录资源（例如违规摄像机）分配用于捕获与较高违规概率相关联的一个或多个车辆的活动。 违规记录单元确定违规记录资源分配调度。 如果不能分配足够的资源来记录给定时间段内的所有可能的违规，则违规记录单元可以忽略具有较低优先级的潜在违规。 在一个实施例中，违规记录资源包括多个摄像机，以及能够产生数字数据文件的一个或多个违规记录器，用于存储违规发生时的视频记录。

公开(公告)号：US06760061B1

公开(公告)日：2004-07-06

申请号：US09059151

申请日：1998-04-13

申请人： Michael T. Glier ,  Douglas L. Reilly ,  Michael T. Tinnemeier ,  Steven I. Small ,  Steven S. Hsieh ,  Randall T. Sybel ,  Mark D. Laird

发明人： Michael T. Glier ,  Douglas L. Reilly ,  Michael T. Tinnemeier ,  Steven I. Small ,  Steven S. Hsieh ,  Randall T. Sybel ,  Mark D. Laird

IPC分类号： H04N718

CPC分类号： G08G1/164 ,  G08G1/04 ,  G08G1/08 ,  G08G1/087 ,  H04N7/183

摘要： A traffic sensor system for detecting and tracking vehicles is describede. A video camera is employed to obtain a video image of a section of a roadway. Motion is detected through changes in luminance and edges in frames of the video image. Predetermined sets of pixels (“tiles”) in the frames are designated to be in either an “active” state or an “inactive” state. A tile becomes active when the luminance or edge values of the pixels of the tile differ from the respective luminance or edge values of a corresponding tile in a reference frame in accordance with predetermined criteria. The tile becomes inactive when the luminance or edge values of the pixels of the tile do not differ from the corresponding reference frame tile in accordance with the is predetermined criteria. Shape and motion of groups of active tiles (“quanta”) are analyzed with software and a neural network to detect and track vehicles.

摘要翻译： 描述用于检测和跟踪车辆的交通传感器系统。 采用摄像机来获取道路的一部分的视频图像。 通过视频图像的帧中的亮度和边缘的变化来检测运动。 帧中的预定像素组（“瓦片”）被指定为处于“活动”状态或“非活动”状态。 当瓦片的像素的亮度或边缘值根据预定标准与参考帧中的相应瓦片的相应亮度或边缘值不同时，瓦片变为活动的。 当瓦片的像素的亮度或边缘值根据预定标准与对应的参考帧瓦片不相同时，瓦片变得不活动。 使用软件和神经网络分析活动瓦片组（“量子”）的形状和运动，以检测和跟踪车辆。

公开(公告)号：US06188329B1

公开(公告)日：2001-02-13

申请号：US09447010

申请日：1999-11-22

申请人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel ,  Steven S. Hsieh ,  Greg D. Johnson ,  Lalitha R. Coimbatore

发明人： Michael T. Glier ,  Mark D. Laird ,  Michael T. Tinnemeier ,  Steven I. Small ,  Randall T. Sybel ,  Steven S. Hsieh ,  Greg D. Johnson ,  Lalitha R. Coimbatore

IPC分类号： G08G1017

CPC分类号： G08G1/054 ,  G07B15/06 ,  G08G1/0175 ,  G08G1/07 ,  G08G1/08 ,  G08G1/164 ,  Y10S707/99932 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A system and method for integrating traffic light violation related vehicle information with court date scheduling information, which employs one or more digitized video recordings of alleged violations. The system provides end-to-end violation processing using the digitized video recordings of the event, and using vehicle database information, as may for example be provided from a department of motor vehicles (DMV) database. The system potentially also interfaces to a court date scheduling database, which includes indications of various available times at which hearings regarding traffic violations may be scheduled. A user interface may provide a display of one or more perspectives on the violation event, as well as access to the vehicle and court date scheduling database. An evaluator, for example a police officer, uses the interface to 1) view the recorded views of the event, 2) determine whether a citationable violation has occurred, 3) extract any necessary vehicle identification information from the recording, 4) obtain owner information regarding the vehicle from the vehicle database, based on the extracted vehicle identification, 5) generate a citation with regard to the violation, and 6) schedule a hearing date with regard to the violation in response to the available court dates in the court date database.

摘要翻译： 一种将交通违章相关车辆信息与法庭日期调度信息相结合的系统和方法，其采用一个或多个所谓违规的数字化视频记录。 该系统使用事件的数字化视频记录和使用车辆数据库信息提供端到端违规处理，例如可以从机动车辆（DMV）数据库提供。 该系统还可以与法庭日期调度数据库相连接，其中包括可能安排有关违反交通事项的听证会的各种可用时间的指示。 用户界面可以提供关于违反事件的一个或多个观点的显示，以及对车辆和法庭日期调度数据库的访问。 评估员，例如警务人员，使用界面1）查看记录的事件视图，2）确定是否发生可引证违规，3）从记录中提取必要的车辆识别信息，4）获取所有者信息 关于来自车辆数据库的车辆，基于所提取的车辆标识，5）产生关于违规的引用，以及6）根据法院日期数据库中的可用法庭日期来安排关于违规的听证日期 。

公开(公告)号：US5479574A

公开(公告)日：1995-12-26

申请号：US42232

申请日：1993-04-01

申请人： Michael T. Glier ,  Linda I. Mensinger Nunez ,  Christopher L. Scofield

发明人： Michael T. Glier ,  Linda I. Mensinger Nunez ,  Christopher L. Scofield

IPC分类号： G06N3/063 ,  G06N3/08 ,  G06F15/18

CPC分类号： G06K9/6274 ,  G06N3/063 ,  G06N3/08

摘要： A neural network and method for pipeline operation within a neural network which permits rapid classification of input vectors provided thereto is disclosed. In a training mode, a plurality of training input features are presented to the neural network and distances between the plurality of training features and a plurality of prototype weight values are concurrently computed. In response to an indication of a last training epoch count values for each of the prototype weight values are stored in a memory to thereby allow the neural network to operate in a probabilistic classification mode.

摘要翻译： 公开了一种允许对其提供的输入向量的快速分类的神经网络内的管线操作的神经网络和方法。 在训练模式中，向神经网络呈现多个训练输入特征，同时计算多个训练特征与多个原型权重值之间的距离。 响应于最后训练的指示，每个原型权重值的计数值存储在存储器中，从而允许神经网络以概率分类模式操作。

公开(公告)号：US4755937A

公开(公告)日：1988-07-05

申请号：US829329

申请日：1986-02-14

申请人： Michael T. Glier

发明人： Michael T. Glier

IPC分类号： G06F13/18 ,  G06F13/28 ,  G06F15/167 ,  G06F13/00

CPC分类号： G06F15/167 ,  G06F13/18 ,  G06F13/28

摘要： A method and apparatus for providing high speed communications with a shared memory from both a processing control unit and a plurality of auxiliary processing devices employs a video random access memory. The processing control unit or units require random access of the memory and are operatively connected to a random access port of the video random access memory. Each auxiliary processing device is operatively connected for data transfer in a burst mode to a serial access port of the video random access memory. The method and apparatus control transfer of data to and from the serial and random access ports for effecting high speed communications at both I/O access ports of the memory. Data communication at the serial access port is in a bit serial/word parallel burst mode and occurs in one CPU cycle. The memory operates like a dynamic RAM from the random access port.

摘要翻译： 用于从处理控制单元和多个辅助处理设备提供与共享存储器的高速通信的方法和装置采用视频随机存取存储器。 处理控制单元或单元需要存储器的随机存取，并可操作地连接到视频随机存取存储器的随机存取端口。 每个辅助处理装置可操作地连接以用于以突发模式进行数据传输到视频随机存取存储器的串行访问端口。 该方法和装置控制向串行和随机接入端口传送数据以及从存储器的两个I / O访问端口进行高速通信。 串行访问端口的数据通信处于串行/字并行突发模式，并在一个CPU周期内发生。 存储器的操作类似于随机存取端口的动态RAM。