公开(公告)号：US20140111647A1

公开(公告)日：2014-04-24

申请号：US14115302

申请日：2012-05-03

申请人： Alon Atsmon ,  Dan Atsmon ,  Ram Dayan ,  Hilla Bass ,  Nimrod Shkedy

发明人： Alon Atsmon ,  Dan Atsmon ,  Ram Dayan ,  Hilla Bass ,  Nimrod Shkedy

IPC分类号： G06K9/00 ,  H04N5/225 ,  B60R11/04 ,  G01C21/34 ,  H04N7/18

CPC分类号： G06K9/00812 ,  B60R11/04 ,  G01C21/34 ,  G01C21/362 ,  G01C21/3647 ,  G01C21/3697 ,  G06F17/30241 ,  G06K9/00221 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/00818 ,  G06K9/00825 ,  G06K9/00832 ,  G06Q30/0261 ,  G08G1/143 ,  H04N5/2252 ,  H04N7/181 ,  H04N7/185 ,  H04N21/2146

摘要： A system and method for analyzing and wirelessly transmitting information in real-time, comprising capturing snapshots and videos, by utilizing for example a smartphone. The images are analyzed in conjunction with other system data to provide the user: 3 dimensional images, GPS coordinates, safety alerts, etc. In particular, the system is mountable within a vehicle interior to provide: road conditions, dangerous driving situations, the make/model/manufacturer of surrounding cars, GPS coordinates, and the identity of local businesses. The user may also share the information via wireless transmissions with surrounding users possessing the same system, such as for real-time video gaming systems. And the system may also be detached from the vehicle for use in other scenarios, such as searching a merchant database for matching items and wirelessly sending the information to other system users.

摘要翻译： 一种用于分析和无线地实时传输信息的系统和方法，包括通过利用例如智能电话来捕获快照和视频。 与其他系统数据一起分析图像以提供用户：3维图像，GPS坐标，安全警报等。特别地，该系统可安装在车辆内部，以提供：路况，危险驾驶情况，制造 周边汽车的模型/制造商，GPS坐标以及当地企业的身份。 用户还可以通过与具有相同系统的周边用户（例如用于实时视频游戏系统）的无线传输共享信息。 并且系统也可以与车辆分离以用于其他情况，例如搜索商家数据库以匹配项目并将信息无线发送到其他系统用户。

公开(公告)号：US08643721B2

公开(公告)日：2014-02-04

申请号：US12670285

申请日：2008-07-17

申请人： Lars-Peter Becker

发明人： Lars-Peter Becker

IPC分类号： H04N7/18 ,  G06K9/00 ,  G06K9/62

CPC分类号： G06K9/00818 ,  G06K9/6807

摘要： In a method and a device for traffic sign recognition, at least one significant feature for a traffic sign is determined which is standardized for a region. The region that corresponds to the determined feature is determined. At least one classification feature and/or at least one classification method is defined depending on the determined region for the recognition of the traffic sign and/or at least one further traffic sign. The recognition of the traffic sign and/or the at least one further traffic sign is performed by using the defined classification feature and/or the defined classification method.

摘要翻译： 在用于交通标志识别的方法和装置中，确定用于交通标志的至少一个显着特征，其对于区域是标准化的。 确定对应于确定的特征的区域。 取决于用于识别交通标志的确定区域和/或至少一个其他交通标志来定义至少一个分类特征和/或至少一个分类方法。 通过使用定义的分类特征和/或所定义的分类方法来执行对交通标志的识别和/或至少一个另外的交通标志。

公开(公告)号：US20130318078A1

公开(公告)日：2013-11-28

申请号：US13954612

申请日：2013-07-30

申请人： Navteq B.V.

发明人： James Lynch ,  William Gale

IPC分类号： G06F17/30

CPC分类号： G06T19/003 ,  G06F17/30241 ,  G06F17/30256 ,  G06F17/30277 ,  G06K9/00798 ,  G06K9/00818 ,  G06K9/00825 ,  G06T3/4038 ,  G06T15/205 ,  G06T19/00 ,  G06T19/006 ,  G06T2200/32 ,  H04N5/3696

摘要： Disclosed are a system and method for creating multi-angle views of an object-of-interest from images stored in a dataset. A user specifies the location of an object-of-interest. As the user virtually navigates through the locality represented by the image dataset, his current virtual position is determined. Using the user's virtual position and the location of the object-of-interest, images in the image dataset are selected and interpolated or stitched together, if necessary, to present to the user a view from his current virtual position looking toward the object-of-interest. The object-of-interest remains in the view no matter where the user virtually travels. From the same image dataset, another user can select a different object-of-interest and virtually navigate in a similar manner, with his own object-of-interest always in view. The object-of-interest also can be “virtual,” added by computer-animation techniques to the image dataset. For some image datasets, the user can virtually navigate through time as well as through space.

摘要翻译： 公开了一种用于从存储在数据集中的图像创建感兴趣对象的多角度视图的系统和方法。 用户指定感兴趣对象的位置。 当用户虚拟地浏览由图像数据集表示的位置时，确定他当前的虚拟位置。 使用用户的虚拟位置和感兴趣对象的位置，如果需要，图像数据集中的图像被选择并插值或缝合在一起，以向用户呈现从他当前的虚拟位置看待朝向对象 -利益。 无论用户虚拟旅行的位置，感兴趣的对象仍然在视图中。 从同一个图像数据集，另一个用户可以选择一个不同的感兴趣的对象，并以类似的方式进行虚拟导航，而他自己的兴趣对象总是在视图中。 感兴趣的对象也可以通过计算机动画技术添加到图像数据集中来“虚拟”。 对于某些图像数据集，用户可以虚拟地浏览时间和空间。

公开(公告)号：US20130300871A1

公开(公告)日：2013-11-14

申请号：US13942757

申请日：2013-07-16

申请人： Magna Electronics Inc.

发明人： Kenneth Schofield ,  Mark L. Larson ,  Keith J. Vadas

IPC分类号： H04N7/18

CPC分类号： B60Q1/143 ,  B60Q1/14 ,  B60Q2300/052 ,  B60Q2300/312 ,  B60Q2300/314 ,  B60Q2300/3321 ,  B60Q2300/41 ,  B60Q2300/42 ,  B60Q2400/30 ,  G05D1/0244 ,  G05D2201/0213 ,  G06K9/00791 ,  G06K9/00818 ,  G06K9/00825 ,  G06K9/2018 ,  H04N7/18

摘要： A driver assistance system for a vehicle includes an imager disposed in a housing and a control. The imager includes a CMOS photosensor array of photosensor elements and a lens. With the housing disposed in a vehicle, the imager views forwardly to the exterior of the vehicle through the vehicle windshield at a region of the windshield that is swept by a windshield wiper of the vehicle. The CMOS photosensor array is operable to capture image data. The control includes an image processor disposed in the housing. The driver assistance system identifies objects viewed by the imager via processing by the image processor of captured image data. At least in part responsive to processing of captured image data by the image processor, streetlights present exterior of the vehicle and viewed by imager are discriminated from other objects present exterior the vehicle and viewed by imager.

摘要翻译： 用于车辆的驾驶员辅助系统包括设置在壳体和控制器中的成像器。 该成像器包括光电传感器元件和透镜的CMOS光电传感器阵列。 当车辆设置在车辆中时，成像器在由车辆的挡风玻璃刮水器扫掠的挡风玻璃的区域处通过车辆挡风玻璃向前看到车辆的外部。 CMOS光电传感器阵列可操作以捕获图像数据。 控制器包括设置在壳体中的图像处理器。 驾驶员辅助系统通过图像处理器对拍摄图像数据的处理来识别由成像器观看的对象。 至少部分地响应于图像处理器对拍摄图像数据的处理，存在车辆外部的路灯并且由成像器观看的路灯与存在于车辆外部并由成像器观看的其它物体区分开。

公开(公告)号：US08452524B2

公开(公告)日：2013-05-28

申请号：US12601416

申请日：2008-05-16

申请人： Stephan Groitzsch ,  Matthias Schorn

发明人： Stephan Groitzsch ,  Matthias Schorn

IPC分类号： G01C21/26

CPC分类号： G01C21/26 ,  G06K9/00818 ,  G08G1/163

摘要： A method is presented for recognizing traffic-related information (I) in a driving motor vehicle, in which sensor data (B) from a sensor and map data (K) from a navigation system are interpreted for recognition purposes, wherein the sensor data (B) is inspected in a first scene interpretation for the presence of traffic-related information (I) and is compacted to relevant sensor data (Br), the map data (K) is inspected in a second scene interpretation for the presence of traffic-related information (I) and is compacted to relevant map data (Kr), and the relevant sensor data (Br) and relevant map data (Kr) is fed to a regulator for interpreting the sensor and map data, wherein the regulator evaluates the sensor data (Br) and the map data (Kr) and then issues an output signal which corresponds to the evaluation.

摘要翻译： 提出了一种用于识别来自传感器的传感器数据（B）和来自导航系统的地图数据（K）的驾驶汽车中的交通相关信息（I）的方法，用于识别目的，其中传感器数据 B）在第一场景解释中对于交通相关信息（I）的存在进行检查，并且被压缩到相关传感器数据（Br），在第二场景解释中对地图数据（K）进行检查， 相关信息（I）并被压缩到相关地图数据（Kr），并且相关传感器数据（Br）和相关地图数据（Kr）被馈送到用于解释传感器和地图数据的调节器，其中调节器评估传感器 数据（Br）和地图数据（Kr），然后发出与评估对应的输出信号。

公开(公告)号：US20130131922A1

公开(公告)日：2013-05-23

申请号：US13813037

申请日：2011-07-20

申请人： Takehito Ogata ,  Yuji Otsuka ,  Shinya Ohtsuji

发明人： Takehito Ogata ,  Yuji Otsuka ,  Shinya Ohtsuji

IPC分类号： G06F17/00

CPC分类号： G06F17/00 ,  B60Q1/143 ,  B60Q2300/056 ,  B60Q2300/41 ,  B60Q2300/42 ,  G06K9/00791 ,  G06K9/00805 ,  G06K9/00818 ,  G06K9/00825 ,  G06K9/3233 ,  G08G1/165 ,  G08G1/166

摘要： An external environment recognizing device for vehicle includes an image acquiring unit configured to acquire image obtained by picking up image of an area ahead of an own vehicle, a light-source extracting unit configured to extract light source from the acquired image, an own-vehicle-speed acquiring unit configured to acquire own vehicle speed, an oncoming-vehicle-presence-possible-region estimating unit configured to estimate oncoming vehicle presence possible region on the basis of own vehicle speed, and an oncoming-vehicle detecting unit configured to detect an oncoming vehicle on the basis of the oncoming vehicle presence possible region and the light source. The oncoming-vehicle-presence-possible-region estimating unit estimates oncoming vehicle presence possible region on the basis of the own vehicle speed, a minimum curvature radius of traveling road corresponding to a speed limit determined in advance, and traffic information indicating whether driving on the traveling road is driving on the right side or the left side.

摘要翻译： 一种用于车辆的外部环境识别装置，包括图像获取单元，其被配置为获取通过拾取本车辆前方的区域的图像获得的图像;光源提取单元，被配置为从获取的图像中提取光源;自身车辆 被配置为获取车辆速度的速度获取单元，被配置为基于本车速估计对方车辆存在可能区域的迎面而来可能区域估计单元，以及被配置为检测自身车速的对方车辆检测单元 在即将到来的车辆存在可能区域和光源的基础上迎面而来的车辆。 迎面车存在可能区域估计单元基于本车速，相应于预先确定的速度限制的行驶道路的最小曲率半径和指示是否开车的交通信息来估计对方车辆存在可能区域 行驶的道路正在右侧或左侧行驶。

公开(公告)号：US20130101157A1

公开(公告)日：2013-04-25

申请号：US13277936

申请日：2011-10-20

申请人： Ying LI ,  Sharathchandra PANKANTI

发明人： Ying LI ,  Sharathchandra PANKANTI

IPC分类号： G06K9/00

CPC分类号： G06K9/00805 ,  B60W2550/10 ,  B60W2550/402 ,  G06K9/00818 ,  G06T7/70 ,  G06T2207/30261 ,  H04N5/2256 ,  H04N5/2354 ,  H04N7/185

摘要： A system and method detect objects in a digital image. At least positional data associated with a vehicle is received. Geographical information associated with the positional data is received. A probability of detecting a target object within a corresponding geographic area associated with the vehicle is determined based on the geographical data. The probability is compared to a given threshold. An object detection process is at least one of activated and maintained in an activated state in response to an object detection process in response to the probability being one of above and equal to the given threshold. The object detection process detects target objects within at least one image representing at least one frame of a video sequence of an external environment. The object detection process is at least one of deactivated and maintained in a deactivated state in response to the probability being below the given threshold.

摘要翻译： 系统和方法检测数字图像中的对象。 至少接收到与车辆相关联的位置数据。 接收与位置数据相关联的地理信息。 基于地理数据确定检测与车辆相关联的相应地理区域内的目标对象的概率。 将概率与给定阈值进行比较。 对象检测处理是响应于上述等于给定阈值的概率而响应于对象检测处理而被激活并保持在激活状态中的至少一个。 对象检测处理检测表示外部环境的视频序列的至少一帧的至少一个图像内的目标对象。 响应于低于给定阈值的概率，对象检测处理是去激活和维持在去激活状态中的至少一个。

公开(公告)号：US20130058534A1

公开(公告)日：2013-03-07

申请号：US13696851

申请日：2011-04-28

申请人： Matthias Zobel

发明人： Matthias Zobel

IPC分类号： G06K9/00

CPC分类号： G06K9/50 ,  G06K9/00818

摘要： The invention relates to a method and to a device for the recognition of road signs (1). According to an inventive method for road sign recognition, images of a region surrounding the vehicle are acquired by means of a camera. The image data of the camera are analyzed, wherein at least one image region (10) that contains a potential road sign is determined. The image region is submitted to a first classification unit that identifies the potential road sign, on the basis of at least one class-specific feature, as a road sign (1) belonging to this particular class. After that, the brightness of the or the color intensity of the surface of the road sign (1) is analyzed along radially extending scanning beams (5) starting from a defined starting point. Potential contour points (6) of an information-bearing part (3) of the road sign (1) are determined from the results of brightness or color intensity analysis. A region of the surface of the road sign (1) is extracted as an information-bearing part (3) of the road sign (1) that includes all determined potential contour points (6). The extracted region is submitted to a second classification unit for semantic interpretation. The inventive method stands out due to a fast performance of the method on account of the brightness or color intensity analysis performed along scanning beams (5) that makes considerably lower demands on the control unit of a vehicle than two-dimensional edge detection operators (e.g., Sobel or Canny operators) that are usually employed for road sign recognition.

摘要翻译： 本发明涉及一种用于识别道路标志（1）的方法和装置。 根据用于道路标识识别的创造性方法，通过照相机获取车辆周围区域的图像。 分析相机的图像数据，其中确定包含潜在道路标志的至少一个图像区域（10）。 图像区域被提交到第一分类单元，其基于至少一个类别特征来识别潜在的路标，作为属于该特定类别的道路标志（1）。 之后，从规定的起点开始沿着径向延伸的扫描光束（5）分析道路标志（1）的表面的亮度或颜色强度。 根据亮度或颜色强度分析的结果确定道路标志（1）的信息承载部分（3）的潜在轮廓点（6）。 提取道路标志（1）的表面的区域作为包括所有确定的电位轮廓点（6）的道路标志（1）的信息承载部分（3）。 提取的区域被提交到用于语义解释的第二分类单元。 本发明的方法由于由沿着扫描光束（5）执行的亮度或颜色强度分析的方法的快速表现，与对比车辆的控制单元相比，对二维边缘检测算子（例如， ，Sobel或Canny运营商），通常用于道路标志识别。

公开(公告)号：US20130046762A1

公开(公告)日：2013-02-21

申请号：US13142650

申请日：2010-05-13

申请人： Tieniu Tan ,  Kaiqi Huang ,  Yongzhen Huang

发明人： Tieniu Tan ,  Kaiqi Huang ,  Yongzhen Huang

IPC分类号： G06F17/30

CPC分类号： G06K9/629 ,  G06K9/00818 ,  G06K9/4671 ,  G06K9/482 ,  G06K9/6251

摘要： A shape classification method based on the topological perceptual organization (TPO) theory, comprising steps of: extracting boundary points of shapes (S1); constructing topological space and computing the representation of extracted boundary points (S2); extracting global features of shapes from the representation of boundary points in topological space (S3); extracting local features of shapes from the representation of boundary points in Euclidean space (S4); combining global features and local features through adjusting the weight of local features according to the performance of global features (S5); classifying shapes using the combination of global features and local features (S6). The invention is applicable for intelligent video surveillance, e.g., objects classification and scene understanding. The invention can also be used for the automatic driving system wherein robust recognition of traffic signs plays an important role in enhancing the intelligence of the system.

摘要翻译： 一种基于拓扑感知组织（TPO）理论的形状分类方法，包括以下步骤：提取形状边界点（S1）; 构建拓扑空间并计算提取的边界点的表示（S2）; 从拓扑空间中的边界点的表示中提取形状的全局特征（S3）; 从欧几里德空间中的边界点的表示中提取形状的局部特征（S4）; 通过根据全局特性的性能调整局部特征的权重，结合全局特征和局部特征（S5）; 使用全局特征和局部特征的组合对形状进行分类（S6）。 本发明适用于智能视频监控，例如对象分类和场景理解。 本发明还可以用于自动驾驶系统，其中对交通标志的鲁棒识别在增强系统的智能方面起重要作用。

公开(公告)号：US08335352B2

公开(公告)日：2012-12-18

申请号：US12581375

申请日：2009-10-19

申请人： Yun-hee Lee

发明人： Yun-hee Lee

IPC分类号： G06K9/00

CPC分类号： G06K9/00798 ,  G06K9/00818

摘要： A method and an apparatus for detecting a lane are disclosed. The lane detecting apparatus includes: a region of ID setup setting a region of ID including a road region of a current lane in an acquired image; a road sign verifier verifying existence of a road sign within the set region of ID; an ROI setup calculating a difference value between a lane prediction result and previous lane information when there exists a road sign and setting an ROI based on the calculated difference value; and a lane detector detecting a lane by extracting lane markings based on the set ROI. Accordingly, a lane can be more accurately detected even in a road environment including a road sign by removing the road sign to extract only necessary lane markings.

摘要翻译： 公开了一种用于检测车道的方法和装置。 车道检测装置包括：ID建立区域，其设置包括获取图像中当前车道的道路区域的ID区域; 验证ID的设定区域内的道路标志的存在的道路标志验证器; ROI设置，当存在道路标志并基于所计算的差值设置ROI时，计算车道预测结果和前一车道信息之间的差值; 以及通过基于所设置的ROI提取车道标记来检测车道的车道检测器。 因此，即使在包括道路标志的道路环境中，除去道路标志也能够更精确地检测车道，仅提取必要的车道标记。