专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09852542B1 Methods and apparatus related to georeferenced pose of 3D models 有权
公开(公告)号：US09852542B1
公开(公告)日：2017-12-26
申请号：US13774051
申请日：2013-02-22
申请人： Google Inc.
发明人： Abhijit Ogale
IPC分类号： G06T17/00 , G06T17/10
CPC分类号： G06T17/10 , G06F3/14 , G09G2340/0464
摘要： In one general aspect, a method can include accessing, from a database, a plurality of user-specified planar indicators within a real-world space where the plurality of user-specified planar indicators can be associated with a plurality of images of an object and identifying planar locations for the plurality of images within the real-world space. The method can include accessing, from the database, a plurality of model planar indicators within a model space where the plurality of model planar indicators can be associated, during modeling of the object as a three-dimensional model within the model space, with a plurality of locations of a plurality of image capture devices associated with the plurality of images. The method can also include aligning, at a computing device, at least a portion of the plurality of model planar indicators with at least a portion of the plurality of user-specified planar indicators.

2. 发明授权

US09489601B2 Construction zone sign detection 有权
公开(公告)号：US09489601B2
公开(公告)日：2016-11-08
申请号：US14883956
申请日：2015-10-15
申请人： Google Inc.
发明人： Nathaniel Fairfield , David Ian Ferguson , Abhijit Ogale , Matthew Wang , Yangli Hector Yee
IPC分类号： G01C22/00 , G05D1/00 , G06K9/78 , H04N7/18 , G06K9/00 , B62D6/00 , B60T7/12 , B60W30/10 , B60W30/14 , B60W40/06 , G05D1/02 , B62D15/02 , B60T1/10 , B60T7/18 , B60T7/22
CPC分类号： G06K9/78 , B60T1/10 , B60T7/12 , B60T7/18 , B60T7/22 , B60T2201/08 , B60W30/10 , B60W30/143 , B60W40/06 , B60W2420/42 , B60W2550/14 , B60W2550/22 , B62D6/00 , B62D15/025 , B62D15/0255 , B62D15/0265 , G01S7/4802 , G01S7/4808 , G01S13/865 , G01S13/867 , G01S13/931 , G01S17/89 , G01S17/936 , G01S2013/9353 , G01S2013/936 , G05D1/0088 , G05D1/0214 , G05D1/024 , G05D1/0246 , G05D1/0257 , G05D1/027 , G05D1/0278 , G05D2201/0213 , G06K9/00798 , G06K9/00805 , G06K9/00818 , H04N7/18
摘要： Methods and systems for detection of a construction zone sign are described. A computing device, configured to control the vehicle, may be configured to receive, from an image-capture device coupled to the computing device, images of a vicinity of the road on which the vehicle is travelling. Also, the computing device may be configured to determine image portions in the images that may depict sides of the road at a predetermined height range. Further, the computing device may be configured to detect a construction zone sign in the image portions, and determine a type of the construction zone sign. Accordingly, the computing device may be configured to modify a control strategy associated with a driving behavior of the vehicle; and control the vehicle based on the modified control strategy.

3. 发明申请

US20160231748A1 Real-Time Image-Based Vehicle Detection based on a Multi-Stage Classification 有权
标题翻译：基于多阶段分类的实时图像车辆检测
公开(公告)号：US20160231748A1
公开(公告)日：2016-08-11
申请号：US15134570
申请日：2016-04-21
申请人： Google Inc.
发明人： Abhijit Ogale
IPC分类号： G05D1/02 , G06K9/62 , G06K9/00
CPC分类号： G05D1/0231 , B60W30/17 , B60W2420/42 , G06K9/00791 , G06K9/00805 , G06K9/3241 , G06K9/6293 , G06K2209/23
摘要： The present disclosure is directed to an autonomous vehicle having a vehicle control system. The vehicle control system includes a vehicle detection system. The vehicle detection system includes receiving an image of a field of view of the vehicle and identifying a region-pair in the image with a sliding-window filter. The region-pair is made up of a first region and a second region. Each region is determined based on a color of pixels within the sliding-window filter. The vehicle detection system also determines a potential second vehicle in the image based on the region-pair. In response to determining the potential second vehicle in the image, the vehicle detection system performs a multi-stage classification of the image to determine whether the second vehicle is present in the image. Additionally, the vehicle detection system provides instructions to control the first vehicle based at least on the determined second vehicle.
摘要翻译：本公开涉及具有车辆控制系统的自主车辆。车辆控制系统包括车辆检测系统。车辆检测系统包括接收车辆的视野的图像并且利用滑动窗口过滤器识别图像中的区域对。区域对由第一区域和第二区域构成。基于滑动窗口滤波器内的像素的颜色来确定每个区域。车辆检测系统还基于区域对来确定图像中的潜在的第二车辆。响应于确定图像中的潜在的第二车辆，车辆检测系统执行图像的多级分类，以确定第二车辆是否存在于图像中。另外，车辆检测系统至少基于所确定的第二车辆提供控制第一车辆的指令。

4. 发明申请

US20150154806A1 Aligning Digital 3D Models Using Synthetic Images 有权
标题翻译：使用合成图像对齐数字3D模型
公开(公告)号：US20150154806A1
公开(公告)日：2015-06-04
申请号：US13801810
申请日：2013-03-13
申请人： Google Inc.
发明人： Abhijit Ogale
IPC分类号： G06T19/20
CPC分类号： G06T19/20 , G06T7/593 , G06T15/20 , G06T17/00 , G06T2200/04 , G06T2207/10028
摘要： To align a first digital 3D model of a scene with a second digital 3D model of the scene, real-world photographs of the scene are received and synthetic photographs of the first digital 3D model are generated according to different camera poses of a virtual camera. Using the real-world photographs and the synthetic photographs as input photographs, points in a coordinate system of the second digital 3D model are generated. Camera poses of the input photographs in the coordinate system of the second 3D model also are determined. Alignment data for aligning the first 3D model with the second 3D model is generated using the camera poses of the virtual camera and the camera poses corresponding to the input photographs.
摘要翻译：为了将场景的第一数字3D模型与场景的第二数字3D模型对准，接收场景的真实世界照片，并且根据虚拟相机的不同相机姿态来生成第一数字3D模型的综合照片。使用真实世界照片和合成照片作为输入照片，生成第二数字3D模型的坐标系中的点。确定在第二3D模型的坐标系中的输入照片的相机姿态。用于使第一3D模型与第二3D模型对齐的对准数据使用虚拟摄像机的摄像头姿态和与输入照片相对应的姿势来生成。

5. 发明授权

US09026303B1 Object detection based on known structures of an environment of an autonomous vehicle 有权
标题翻译：基于自主车辆的环境的已知结构的对象检测
公开(公告)号：US09026303B1
公开(公告)日：2015-05-05
申请号：US14480377
申请日：2014-09-08
申请人： Google Inc.
发明人： David I. Ferguson , Abhijit Ogale
IPC分类号： G05D1/00
CPC分类号： G05D1/00 , G05D1/0214 , G05D1/0246 , G05D2201/0213 , G06K9/00805
摘要： An autonomous vehicle may be configured to detect objects based on known structures of an environment. The vehicle may be configured to obtain image data from a sensor and be configured to operate in an autonomous mode. The image data may include data indicative of a known structure in the environment. The vehicle may include a computer system. The computer system may determine, based on a first portion of the image data, information indicative of an appearance of the known structure. The computer system may determine, based on a second portion of the image data, information indicative of an appearance of an unknown object in the environment. The computer system may also compare the information indicative of the appearance of the known structure with the information indicative of the appearance of the unknown object and provide instructions to control the vehicle in the autonomous mode based on the comparison.
摘要翻译：自主车辆可以被配置为基于环境的已知结构来检测对象。车辆可以被配置为从传感器获得图像数据并且被配置为以自主模式操作。图像数据可以包括指示环境中的已知结构的数据。车辆可以包括计算机系统。计算机系统可以基于图像数据的第一部分来确定指示已知结构的外观的信息。计算机系统可以基于图像数据的第二部分来确定指示环境中的未知对象的外观的信息。计算机系统还可以将表示已知结构的外观的信息与指示未知对象的外观的信息进行比较，并且基于比较提供以自主模式控制车辆的指令。

6. 发明授权

US08977007B1 Detecting a vehicle signal through image differencing and filtering 有权
标题翻译：通过图像差分和滤波检测车辆信号
公开(公告)号：US08977007B1
公开(公告)日：2015-03-10
申请号：US13868353
申请日：2013-04-23
申请人： Google Inc.
发明人： David Ian Franklin Ferguson , Abhijit Ogale , Matthew Wang
IPC分类号： G06K9/00 , G08G1/123 , H04N5/225
CPC分类号： G06K9/00825
摘要： Methods and systems for detecting a vehicle signal through image differencing and filtering are described. A computing device may be configured to receive a sequence of images of an identified vehicle in a vicinity of a given vehicle. The computing device may be configured to determine, based on a comparison of a first image of a pair of images of the sequence of images to a second image of the pair of images, a portion of image data exhibiting a change in color and a change in brightness between the first image and the second image of the pair of images. The computing device may be configured to determine that the portion indicates a light signal for the identified vehicle; and provide instructions to control the given vehicle based on the light signal of the identified vehicle.
摘要翻译：描述了通过图像差分和滤波检测车辆信号的方法和系统。计算设备可以被配置为在给定车辆的附近接收识别的车辆的一系列图像。计算设备可以被配置为基于图像序列的一对图像的第一图像与该对图像的第二图像的比较来确定表现出颜色变化和变化的图像数据的一部分在第一图像和该对图像的第二图像之间的亮度。计算设备可以被配置为确定该部分指示用于所识别的车辆的光信号; 并提供基于识别的车辆的光信号来控制给定车辆的指令。

7. 发明授权

US09557737B1 Distribution decision trees 有权
标题翻译：分配决策树
公开(公告)号：US09557737B1
公开(公告)日：2017-01-31
申请号：US14885815
申请日：2015-10-16
申请人： Google Inc.
发明人： David Ian Franklin Ferguson , Abhijit Ogale
IPC分类号： G01C22/00 , G05D1/00
CPC分类号： G05D1/0088 , B60W30/00 , B60W30/08 , B60W30/09 , B60W30/095 , B60W2550/10 , G05D1/0055
摘要： The present disclosure is directed to autonomous vehicle having a vehicle control system. The vehicle control system includes a processing system that receives input values that indicate attributes of an object within a threshold distance of the autonomous vehicle and variance values indicating uncertainty associated with the input values. The processing system also provides a plurality of outcomes that are associated with combinations of split decisions. A given split decision indicates whether a particular input value is above or below a threshold value associated with the given split decision. The processing system further determines (i) a probability that the particular input value is above a threshold value and (ii) a probability that the particular input is below the threshold value for a given split decision. Additionally, the processing system determines one or more likelihoods associated with a given outcome. Further, the processing system provides instructions to control the autonomous vehicle.
摘要翻译：本公开涉及具有车辆控制系统的自主车辆。车辆控制系统包括处理系统，其接收指示自主车辆的阈值距离内的物体的属性的输入值和表示与输入值相关联的不确定性的方差值。处理系统还提供与分离决策的组合相关联的多个结果。给定的分割决定指示特定输入值是否高于或低于与给定分割决策相关联的阈值。处理系统还确定（i）特定输入值高于阈值的概率，以及（ii）特定输入低于给定分割决策的阈值的概率。另外，处理系统确定与给定结果相关联的一个或多个可能性。此外，处理系统提供控制自主车辆的指令。

8. 发明授权

US09507347B1 Vision-based indicator signal detection using spatiotemporal filtering 有权
标题翻译：基于视觉的指示信号检测采用时空滤波
公开(公告)号：US09507347B1
公开(公告)日：2016-11-29
申请号：US15056780
申请日：2016-02-29
申请人： Google Inc.
发明人： Abhijit Ogale , David Ian Franklin Ferguson
IPC分类号： G06K9/00 , G05D1/02 , G05D1/00 , B60R1/00 , G06K9/46
CPC分类号： G06K9/00791 , B60R1/00 , B60R2300/80 , G05D1/0088 , G05D1/0246 , G06K9/00825 , G06K9/4604 , G06K9/4652 , G06K9/4661 , H04N5/2353
摘要： An autonomous vehicle is configured to detect an active turn signal indicator on another vehicle. An image-capture device of the autonomous vehicle captures an image of a field of view of the autonomous vehicle. The autonomous vehicle captures the image with a short exposure to emphasize objects having brightness above a threshold. Additionally, a bounding area for a second vehicle located within the image is determined. The autonomous vehicle identifies a group of pixels within the bounding area based on a first color of the group of pixels. The autonomous vehicle also calculates an oscillation of an intensity of the group of pixels. Based on the oscillation of the intensity, the autonomous vehicle determines a likelihood that the second vehicle has a first active turn signal. Additionally, the autonomous vehicle is controlled based at least on the likelihood that the second vehicle has a first active turn signal.
摘要翻译：自主车辆被配置为检测另一车辆上的主动转向信号指示器。自主车辆的图像捕获装置捕获自主车辆的视野的图像。自主车辆以短曝光捕获图像，以强调具有高于阈值的亮度的物体。另外，确定位于图像内的第二车辆的边界区域。自主车辆基于像素组的第一颜色识别边界区域内的一组像素。自主车辆还计算该组像素的强度的振荡。基于强度的振荡，自主车辆确定第二车辆具有第一主动转弯信号的可能性。另外，至少基于第二车辆具有第一主动转弯信号的可能性来控制自主车辆。

9. 发明授权

US09187088B1 Distribution decision trees 有权
标题翻译：分配决策树
公开(公告)号：US09187088B1
公开(公告)日：2015-11-17
申请号：US14585681
申请日：2014-12-30
申请人： Google Inc.
发明人： David Ian Franklin Ferguson , Abhijit Ogale
IPC分类号： G01C22/00 , G05D1/00 , B60W30/00 , B60W30/09
CPC分类号： G05D1/0088 , B60W30/00 , B60W30/08 , B60W30/09 , B60W30/095 , B60W2550/10 , G05D1/0055
摘要： The present disclosure is directed to autonomous vehicle having a vehicle control system. The vehicle control system includes a processing system that receives input values that indicate attributes of an object within a threshold distance of the autonomous vehicle and variance values indicating uncertainty associated with the input values. The processing system also provides a plurality of outcomes that are associated with combinations of split decisions. A given split decision indicates whether a particular input value is above or below a threshold value associated with the given split decision. The processing system further determines (i) a probability that the particular input value is above a threshold value and (ii) a probability that the particular input is below the threshold value for a given split decision. Additionally, the processing system determines one or more likelihoods associated with a given outcome. Further, the processing system provides instructions to control the autonomous vehicle.
摘要翻译：本公开涉及具有车辆控制系统的自主车辆。车辆控制系统包括处理系统，其接收指示自主车辆的阈值距离内的物体的属性的输入值和表示与输入值相关联的不确定性的方差值。处理系统还提供与分离决策的组合相关联的多个结果。给定的分割决定指示特定输入值是否高于或低于与给定分割决策相关联的阈值。处理系统还确定（i）特定输入值高于阈值的概率，以及（ii）特定输入低于给定分割决策的阈值的概率。另外，处理系统确定与给定结果相关联的一个或多个可能性。此外，处理系统提供控制自主车辆的指令。

10. 发明申请

US20170039435A1 Vision-Based Indicator Signal Detection Using Spatiotemporal Filtering 有权
标题翻译：基于视觉的指示信号检测使用时空滤波
公开(公告)号：US20170039435A1
公开(公告)日：2017-02-09
申请号：US15331079
申请日：2016-10-21
申请人： Google Inc.
发明人： Abhijit Ogale , Dave Ferguson
IPC分类号： G06K9/00 , G05D1/00 , G05D1/02 , H04N5/235 , G06K9/46
CPC分类号： G06K9/00791 , B60R1/00 , B60R2300/80 , G05D1/0088 , G05D1/0246 , G06K9/00825 , G06K9/4604 , G06K9/4652 , G06K9/4661 , H04N5/2353
摘要： An autonomous vehicle is configured to detect an active turn signal indicator on another vehicle. An image-capture device of the autonomous vehicle captures an image of a field of view of the autonomous vehicle. The autonomous vehicle captures the image with a short exposure to emphasize objects having brightness above a threshold. Additionally, a bounding area for a second vehicle located within the image is determined. The autonomous vehicle identifies a group of pixels within the bounding area based on a first color of the group of pixels. The autonomous vehicle also calculates an oscillation of an intensity of the group of pixels. Based on the oscillation of the intensity, the autonomous vehicle determines a likelihood that the second vehicle has a first active turn signal. Additionally, the autonomous vehicle is controlled based at least on the likelihood that the second vehicle has a first active turn signal.
摘要翻译：自主车辆被配置为检测另一车辆上的主动转向信号指示器。自主车辆的图像捕获装置捕获自主车辆的视野的图像。自主车辆以短曝光捕获图像，以强调具有高于阈值的亮度的物体。另外，确定位于图像内的第二车辆的边界区域。自主车辆基于像素组的第一颜色识别边界区域内的一组像素。自主车辆还计算该组像素的强度的振荡。基于强度的振荡，自主车辆确定第二车辆具有第一主动转弯信号的可能性。另外，至少基于第二车辆具有第一主动转弯信号的可能性来控制自主车辆。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式