公开(公告)号：US20140081573A1

公开(公告)日：2014-03-20

申请号：US13623397

申请日：2012-09-20

Applicant: Google Inc.

Inventor： Christopher Paul Urmson ,  Michael Steven Montemerlo ,  Jiajun Zhu

IPC: G01W1/02 ,  G06F19/00 ,  G01B11/30

CPC classification number: G01W1/02 ,  G01S7/4802 ,  G01S17/42 ,  G01S17/89 ,  G01S17/95 ,  G01W1/10 ,  Y02A90/19

Abstract: Aspects of the disclosure relate generally to detecting road weather conditions. Vehicle sensors including a laser, precipitation sensors, and/or camera may be used to detect information such as the brightness of the road, variations in the brightness of the road, brightness of the world, current precipitation, as well as the detected height of the road. Information received from other sources such as networked based weather information (forecasts, radar, precipitation reports, etc.) may also be considered. The combination of the received and detected information may be used to estimate the probability of precipitation such as water, snow or ice in the roadway. This information may then be used to maneuver an autonomous vehicle (for steering, accelerating, or braking) or identify dangerous situations.

Abstract translation: 本公开的方面通常涉及检测道路天气状况。 可以使用包括激光，降水传感器和/或照相机的车辆传感器来检测诸如道路的亮度，道路亮度的变化，世界的亮度，当前的降水以及检测到的高度 马路。 也可以考虑从其他来源获得的信息，例如网络天气信息（预测，雷达，降水报告等）。 接收和检测信息的组合可用于估计巷道中的降水概率，例如水，雪或冰。 然后可以使用该信息来操纵自主车辆（用于转向，加速或制动）或识别危险情况。

公开(公告)号：US09632210B2

公开(公告)日：2017-04-25

申请号：US13888634

申请日：2013-05-07

Applicant: Google Inc.

Inventor： Jiajun Zhu ,  Dmitri Dolgov ,  Dave Ferguson

IPC: G06F19/00 ,  G01W1/00 ,  G01W1/14

CPC classification number: G01W1/00 ,  G01N21/4738 ,  G01S17/023 ,  G01S17/87 ,  G01W1/14 ,  G05D1/0088 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0257 ,  G05D1/0276 ,  H04N7/183

Abstract: Example methods and systems for detecting weather conditions using vehicle onboard sensors are provided. An example method includes receiving laser data collected for an environment of a vehicle, and the laser data includes a plurality of laser data points. The method also includes associating, by a computing device, laser data points of the plurality of laser data points with one or more objects in the environment, and determining given laser data points of the plurality of laser data points that are unassociated with the one or more objects in the environment as being representative of an untracked object. The method also includes based on one or more untracked objects being determined, identifying by the computing device an indication of a weather condition of the environment.

公开(公告)号：US20160350964A1

公开(公告)日：2016-12-01

申请号：US15236852

申请日：2016-08-15

Applicant: Google Inc.

Inventor： Jiajun Zhu

IPC: G06T15/20 ,  G06T19/00 ,  G06F17/30 ,  G06T15/04

Abstract: A system and method of displaying transitions between street level images is provided. In one aspect, the system and method creates a plurality of polygons that are both textured with images from a 2D street level image and associated with 3D positions, where the 3D positions correspond with the 3D positions of the objects contained in the image. These polygons, in turn, are rendered from different perspectives to convey the appearance of moving among the objects contained in the original image.

Abstract translation: 提供了一种在街道图像之间显示过渡的系统和方法。 在一个方面，系统和方法创建多个多边形，它们都与来自2D街道级图像的图像纹理化并与3D位置相关联，其中3D位置对应于包含在图像中的对象的3D位置。 反过来，这些多边形从不同的角度呈现出来，以传达在原始图像中包含的对象之间移动的外观。

公开(公告)号：US20160274589A1

公开(公告)日：2016-09-22

申请号：US15170470

申请日：2016-06-01

Applicant: Google Inc.

Inventor： Bradley Templeton ,  Pierre-yves Droz ,  Jiajun Zhu

IPC: G05D1/02 ,  G01S17/93 ,  G01S17/10 ,  G01S7/486

CPC classification number: G05D1/0231 ,  G01S7/4802 ,  G01S7/484 ,  G01S7/4865 ,  G01S17/023 ,  G01S17/10 ,  G01S17/42 ,  G01S17/89 ,  G01S17/936 ,  G05D1/024 ,  G05D1/0246 ,  G05D2201/0213

Abstract: A system and method include scanning a light detection and ranging (LIDAR) device through a range of orientations corresponding to a scanning zone while emitting light pulses from the LIDAR device. The method also includes receiving returning light pulses corresponding to the light pulses emitted from the LIDAR device and determining initial point cloud data based on time delays between emitting the light pulses and receiving the corresponding returning light pulses and the orientations of the LIDAR device. The initial point cloud data has an initial angular resolution. The method includes identifying, based on the initial point cloud data, a reflective feature in the scanning zone and determining an enhancement region and an enhanced angular resolution for a subsequent scan to provide a higher spatial resolution in at least a portion of subsequent point cloud data from the subsequent scan corresponding to the reflective feature.

Abstract translation: 一种系统和方法包括在发射来自激光雷达装置的光脉冲的同时扫描光检测和测距（LIDAR）装置通过与扫描区对应的一系列取向。 该方法还包括接收对应于从激光雷达装置发射的光脉冲的返回光脉冲，并且基于发射光脉冲之间的时间延迟并接收相应的返回光脉冲和激光雷达装置的取向来确定初始点云数据。 初始点云数据具有初始角分辨率。 该方法包括基于初始点云数据识别扫描区域中的反射特征并且确定增强区域和增强的角度分辨率用于随后的扫描以在后续点云数据的至少一部分中提供更高的空间分辨率 从随后的扫描对应于反射特征。

公开(公告)号：US09438934B1

公开(公告)日：2016-09-06

申请号：US14528437

申请日：2014-10-30

Applicant: Google Inc.

Inventor： Jiajun Zhu

IPC: H04N7/00 ,  H04N9/64 ,  H04N21/218 ,  G11B27/031 ,  H04N5/14 ,  H04N5/262

CPC classification number: H04N21/21805 ,  G06T19/003 ,  G11B27/031 ,  H04N5/147 ,  H04N5/2628 ,  H04N21/472

Abstract: Methods and systems for generating video from panoramic images using transition trees are provided. According to an embodiment, a method for generating a video from panoramic images may include receiving a transition tree corresponding to a current panoramic image from a server. The method may also include determining a path of the transition tree to a next panoramic image based on a user navigation request. The method may further include requesting and receiving a video chunk from the server for each edge of the determined path of the transition tree. The method may also include displaying the requested video chunks in sequence according to the transition tree. According to another embodiment, a system for generating a video from panoramic images may include a transition tree module and a video display module.

Abstract translation: 提供了使用过渡树从全景图像生成视频的方法和系统。 根据实施例，用于从全景图像生成视频的方法可以包括从服务器接收与当前全景图像相对应的过渡树。 该方法还可以包括基于用户导航请求来确定转换树到下一个全景图像的路径。 该方法还可以包括从转发树的确定路径的每个边缘向服务器请求和接收视频块。 该方法还可以包括根据转换树依次显示所请求的视频块。 根据另一个实施例，用于从全景图像生成视频的系统可以包括转换树模块和视频显示模块。

公开(公告)号：US20150310281A1

公开(公告)日：2015-10-29

申请号：US14791725

申请日：2015-07-06

Applicant: Google Inc.

Inventor： Jiajun Zhu ,  Pratik Agarwal

IPC: G06K9/00 ,  G06T7/20 ,  G06K9/52 ,  G06K9/46

CPC classification number: G06K9/00791 ,  G05D1/0246 ,  G06K9/00805 ,  G06K9/46 ,  G06K9/52 ,  G06T7/20 ,  G06T7/246 ,  G06T2200/04 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30241 ,  G06T2207/30252

Abstract: Methods and systems for object detection using multiple sensors are described herein. In an example embodiment, a vehicle's computing device may receive sensor data frames indicative of an environment at different rates from multiple sensors. Based on a first frame from a first sensor indicative of the environment at a first time period and a portion of a first frame that corresponds to the first time period from a second sensor, the computing device may estimate parameters of objects in the vehicle's environment. The computing device may modify the parameters in response to receiving subsequent frames or subsequent portions of frame of sensor data from the sensors even if the frames arrive at the computing device out of order. The computing device may provide the parameters of the objects to systems of the vehicle for object detection and obstacle avoidance.

Abstract translation: 本文描述了使用多个传感器进行物体检测的方法和系统。 在示例性实施例中，车辆的计算设备可以接收指示与多个传感器不同的速率的环境的传感器数据帧。 基于来自第一传感器的指示第一时间段的环境的第一帧和对应于从第二传感器的第一时间段的第一帧的一部分，计算设备可以估计车辆环境中的对象的参数。 响应于从传感器接收传感器数据的帧的后续帧或后续部分，计算设备可以修改参数，即使帧无序地到达计算设备。 计算设备可以将对象的参数提供给车辆的系统以用于物体检测和障碍物避免。

公开(公告)号：US09098753B1

公开(公告)日：2015-08-04

申请号：US14262269

申请日：2014-04-25

Applicant: Google Inc.

Inventor： Jiajun Zhu ,  Pratik Agarwal

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06K9/00791 ,  G05D1/0246 ,  G06K9/00805 ,  G06K9/46 ,  G06K9/52 ,  G06T7/20 ,  G06T7/246 ,  G06T2200/04 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30241 ,  G06T2207/30252

Abstract: Methods and systems for object detection using multiple sensors are described herein. In an example embodiment, a vehicle's computing device may receive sensor data frames indicative of an environment at different rates from multiple sensors. Based on a first frame from a first sensor indicative of the environment at a first time period and a portion of a first frame that corresponds to the first time period from a second sensor, the computing device may estimate parameters of objects in the vehicle's environment. The computing device may modify the parameters in response to receiving subsequent frames or subsequent portions of frame of sensor data from the sensors even if the frames arrive at the computing device out of order. The computing device may provide the parameters of the objects to systems of the vehicle for object detection and obstacle avoidance.

Abstract translation: 本文描述了使用多个传感器进行物体检测的方法和系统。 在示例性实施例中，车辆的计算设备可以接收指示与多个传感器不同的速率的环境的传感器数据帧。 基于来自第一传感器的指示第一时间段的环境的第一帧和对应于从第二传感器的第一时间段的第一帧的一部分，计算设备可以估计车辆环境中的对象的参数。 响应于从传感器接收传感器数据的帧的后续帧或后续部分，计算设备可以修改参数，即使帧无序地到达计算设备。 计算设备可以将对象的参数提供给车辆的系统以用于物体检测和障碍物避免。

公开(公告)号：US09014905B1

公开(公告)日：2015-04-21

申请号：US14166502

申请日：2014-01-28

Applicant: Google Inc.

Inventor： Henrik Kretzschmar ,  Jiajun Zhu

IPC: G05D1/02

CPC classification number: G05D1/021 ,  B60W30/0956 ,  B60W30/10 ,  B60W30/143 ,  B60W40/04 ,  B60W2420/42 ,  G06K9/00335 ,  G06K9/00369 ,  G06K9/00818 ,  G06K9/6293

Abstract: Methods and systems for detecting hand signals of a cyclist by an autonomous vehicle are described. An example method may involve a computing device receiving a plurality of data points corresponding to an environment of an autonomous vehicle. The computing device may then determine one or more subsets of data points from the plurality of data points indicative of at least a body region of a cyclist. Further, based on an output of a comparison of the one or more subsets with one or more predetermined sets of cycling signals, the computing device may determine an expected adjustment of one or more of a speed of the cyclist and a direction of movement of the cyclist. Still further, based on the expected adjustment, the computing device may provide instructions to adjust one or more of a speed of the autonomous vehicle and a direction of movement of the autonomous vehicle.

Abstract translation: 描述了通过自主车辆检测自行车者的手信号的方法和系统。 示例性方法可以涉及接收与自主车辆的环境相对应的多个数据点的计算设备。 计算设备然后可以从指示骑自行车者的至少身体区域的多个数据点确定数据点的一个或多个子集。 此外，基于一个或多个子集与一个或多个预定的循环信号集合的比较的输出，计算设备可以确定骑自行车者的速度和运动方向中的一个或多个的预期调整 骑自行车的人 此外，基于预期的调整，计算装置可以提供用于调整自主车辆的速度和自主车辆的移动方向中的一个或多个的指令。

公开(公告)号：US20140336935A1

公开(公告)日：2014-11-13

申请号：US13888634

申请日：2013-05-07

Applicant: Google Inc.

Inventor： Jiajun Zhu ,  Dmitri Dolgov ,  Dave Ferguson

IPC: G01W1/00

CPC classification number: G01W1/00 ,  G01N21/4738 ,  G01S17/023 ,  G01S17/87 ,  G01W1/14 ,  G05D1/0088 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0257 ,  G05D1/0276 ,  H04N7/183

Abstract: Example methods and systems for detecting weather conditions using vehicle onboard sensors are provided. An example method includes receiving laser data collected for an environment of a vehicle, and the laser data includes a plurality of laser data points. The method also includes associating, by a computing device, laser data points of the plurality of laser data points with one or more objects in the environment, and determining given laser data points of the plurality of laser data points that are unassociated with the one or more objects in the environment as being representative of an untracked object. The method also includes based on one or more untracked objects being determined, identifying by the computing device an indication of a weather condition of the environment.

Abstract translation: 提供了使用车载传感器检测天气状况的示例方法和系统。 示例性方法包括接收针对车辆的环境收集的激光数据，并且激光数据包括多个激光数据点。 该方法还包括通过计算设备将多个激光数据点中的激光数据点与环境中的一个或多个对象相关联，并且确定与该一个或多个激光数据点不相关的多个激光数据点的给定激光数据点， 更多的对象在环境中代表未被追踪的对象。 该方法还包括基于确定的一个或多个未跟踪对象，由计算设备识别环境的天气状况的指示。

公开(公告)号：US08886387B1

公开(公告)日：2014-11-11

申请号：US14148874

申请日：2014-01-07

Applicant: Google Inc.

Inventor： Pratik Agarwal ,  Jiajun Zhu

IPC: G01C22/00 ,  G05D1/00

CPC classification number: G05D1/0251 ,  G05D1/0253 ,  G05D2201/0213 ,  G06K9/00791 ,  G06T7/33 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20068 ,  G06T2207/20076 ,  G06T2207/30252 ,  G06T2207/30256

Abstract: A computing device may identify an object in an environment of a vehicle and receive a first three-dimensional (3D) point cloud depicting a first view of the object. The computing device may determine a reference point on the object in the first 3D point cloud, and receive a second 3D point cloud depicting a second view of the object. The computing device may determine a transformation between the first view and the second view, and estimate a projection of the reference point from the first view relative to the second view based on the transformation so as to trace the reference point from the first view to the second view. The computing device may determine one or more motion characteristics of the object based on the projection of the reference point.

Abstract translation: 计算设备可以识别车辆环境中的对象，并且接收描绘对象的第一视图的第一三维（3D）点云。 计算设备可以确定第一3D点云中的对象上的参考点，并且接收描绘对象的第二视图的第二3D点云。 计算设备可以确定第一视图和第二视图之间的变换，并且基于变换来估计参考点从第一视图相对于第二视图的投影，以便将参考点从第一视图跟踪到第 第二观点。 计算设备可以基于参考点的投影来确定对象的一个​​或多个运动特征。