公开(公告)号：US09836660B2

公开(公告)日：2017-12-05

申请号：US14957983

申请日：2015-12-03

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Qingrong Zhao ,  Qi Zhang ,  Jinsong Wang ,  Bakhtiar B. Litkouhi

IPC: G06K9/00 ,  B60W40/06 ,  G06K9/32 ,  G06K9/46 ,  G06T7/00 ,  H04N7/18

CPC classification number: G06K9/00798 ,  B60W40/06 ,  B60W2420/42 ,  B60W2550/14 ,  B60W2710/06 ,  B60W2710/18 ,  B60W2720/40 ,  B60W2750/40 ,  G06K9/00791 ,  G06K9/3233 ,  G06K9/4604 ,  G06T7/30 ,  G06T2207/20024 ,  G06T2207/30256 ,  H04N7/183

Abstract: A method of determining a wet surface condition of a road. An image of a road surface is captured by an image capture device of the host vehicle. The image capture device is mounted on a side of the host vehicle and an image is captured in a downward direction. A region of interest is identified in the captured image by a processor. The region of interest is in a region rearward of a tire of a host vehicle. The region of interest is representative of where a tire track as generated by the tire rotating on the road when the road surface is wet. A determination is made whether water is present in the region of interest as a function of identifying the tire track. A wet road surface signal is generated in response to the identification of water in the region of interest.

公开(公告)号：US09834143B2

公开(公告)日：2017-12-05

申请号：US14280489

申请日：2014-05-16

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Wende Zhang ,  Jinsong Wang ,  Kent S. Lybecker ,  Jeffrey S. Piasecki ,  Bakhtiar Brian Litkouhi ,  Ryan M. Frakes

IPC: H04N7/18 ,  B60R1/00 ,  B60R11/04 ,  G06T5/00 ,  G06T3/00 ,  B60R11/00

CPC classification number: B60R1/002 ,  B60R1/00 ,  B60R11/04 ,  B60R2011/004 ,  B60R2300/303 ,  B60R2300/607 ,  B60R2300/802 ,  G06T3/0093 ,  G06T5/006 ,  G06T2207/10016 ,  G06T2207/30252 ,  H04N7/181 ,  H04N7/183

Abstract: A system and method for creating an enhanced perspective view of an area in front of a vehicle, using images from left-front and right-front cameras. The enhanced perspective view removes the distortion and exaggerated perspective effects which are inherent in wide-angle lens images. The enhanced perspective view uses a camera model including a virtual image surface and other processing techniques which provide corrections for two types of problems which are typically present in de-warped perspective images—including a stretching effect at the peripheral area of a wide-angle image de-warped by rectilinear projection, and double image of objects in an area where left-front and right-front camera images overlap.

公开(公告)号：US09812008B2

公开(公告)日：2017-11-07

申请号：US15047959

申请日：2016-02-19

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Wei Tong ,  Shuqing Zeng ,  Jinsong Wang ,  Wende Zhang

IPC: G08G1/04

CPC classification number: B60W30/0956 ,  G08G1/167

Abstract: A system and method are provided for detecting remote vehicles relative to a host vehicle using wheel detection. The system and method include tracking wheel candidates based on wheel detection data received from a plurality of object detection devices, comparing select parameters relating to the wheel detection data for each of the tracked wheel candidates, and identifying a remote vehicle by determining if a threshold correlation exists between any of the tracked wheel candidates based on the comparison of select parameters.

公开(公告)号：US09661319B2

公开(公告)日：2017-05-23

申请号：US14283508

申请日：2014-05-21

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shuqing Zeng ,  Wende Zhang ,  Jinsong Wang

IPC: H04N9/47 ,  H04N7/18 ,  H04N17/00 ,  G06K9/00 ,  G06K9/46 ,  H04N5/262 ,  H04N5/265 ,  B60R1/00 ,  G06T7/00

CPC classification number: H04N17/002 ,  B60R1/00 ,  B60R2300/402 ,  G06K9/00791 ,  G06K9/4604 ,  G06T7/33 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/30244 ,  G06T2207/30252 ,  H04N5/2628 ,  H04N5/265

Abstract: An embodiment contemplates a method of calibrating multiple image capture devices of a vehicle. A plurality of image capture devices having different poses are provided. At least one of the plurality of image capture devices is identified as a reference device. An image of a patterned display exterior of the vehicle is captured by the plurality of image capture devices. The vehicle traverses across the patterned display to capture images at various instances of time. A processor identifies common landmarks of the patterned display between each of the images captured by the plurality of image capture devices and the reference device. Images of the patterned display captured by each of the plurality of image devices are stitched using the identified common landmarks. Extrinsic parameters of each image capture device are adjusted relative to the reference device based on the stitched images for calibrating the plurality of image capture devices.

公开(公告)号：US09621798B2

公开(公告)日：2017-04-11

申请号：US14790394

申请日：2015-07-02

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Wende Zhang ,  Jinsong Wang ,  Brunno L. Moretti

IPC: H04N5/262 ,  H04N5/232 ,  B60R1/00 ,  H04N5/357 ,  G06T3/00

CPC classification number: H04N5/23235 ,  B60R1/00 ,  G06T3/0093 ,  H04N5/23216 ,  H04N5/2628 ,  H04N5/3572

Abstract: A method for providing a high resolution display image that includes providing a camera image that can be processed into at least two different camera views. The method also includes identifying a warped grid in each of the at least two different camera views and identifying a minimum field of view for displaying each of the at least two different camera views. The method further includes cropping the camera image based on the identified minimum field of view and de-warping the at least two different camera views to provide the high resolution display image.

公开(公告)号：US09405104B2

公开(公告)日：2016-08-02

申请号：US14041083

申请日：2013-09-30

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Wende Zhang ,  Jinsong Wang ,  Kent S. Lybecker ,  Jeffrey S. Piasecki ,  Ryan M. Frakes ,  Travis S. Hester

IPC: H04N5/33 ,  G02B13/14 ,  H01L27/146 ,  G02B13/18 ,  H04N7/18 ,  B60R1/00 ,  H04N9/00 ,  H04N5/355 ,  G02B19/00 ,  G02B5/20

CPC classification number: G02B13/14 ,  B60R1/00 ,  G02B5/208 ,  G02B13/18 ,  G02B19/0076 ,  G02B19/009 ,  H01L27/14618 ,  H01L27/14625 ,  H01L2924/0002 ,  H04N5/332 ,  H04N5/35563 ,  H04N7/18 ,  H04N9/00 ,  H01L2924/00

Abstract: An apparatus for capturing an image includes a plurality of lens elements coaxially encompassed within a lens housing. A split-sub-pixel imaging chip includes an IR-pass filter coating applied on selected sub-pixels. The sub-pixels include a long exposure sub-pixel and a short-exposure sub-pixel for each of a plurality of green blue and red pixels.

Abstract translation: 用于捕获图像的装置包括同轴地包围在透镜壳体内的多个透镜元件。 分割子像素成像芯片包括施加在所选子像素上的IR通过滤光镜涂层。 子像素包括用于多个绿色和红色像素中的每一个的长曝光子像素和短曝光子像素。

公开(公告)号：US09336574B2

公开(公告)日：2016-05-10

申请号：US14041058

申请日：2013-09-30

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Wende Zhang ,  Jinsong Wang ,  Kent S. Lybecker ,  Jeffrey S. Piasecki ,  Ryan M. Frakes ,  Travis S. Hester

IPC: G06K9/32 ,  G06T5/00 ,  G06T3/00

CPC classification number: G06T5/003 ,  G06T3/0012 ,  G06T2207/10016 ,  G06T2207/20012 ,  G06T2207/30252

Abstract: Method for applying super-resolution to images captured by a camera device of a vehicle includes receiving a plurality of image frames captured by the camera device. For each image frame, a region of interest is identified within the image frame requiring resolution related to detail per pixel to be increased. Spatially-implemented super-resolution is applied to the region of interest within each image to enhance image sharpness within the region of interest.

Abstract translation: 将超分辨率应用于由车辆的相机装置拍摄的图像的方法包括接收由相机装置捕获的多个图像帧。 对于每个图像帧，在图像帧内识别出需要增加与每个像素的细节有关的分辨率的感兴趣区域。 空间实现的超分辨率被应用于每个图像内的感兴趣区域，以增强感兴趣区域内的图像清晰度。

公开(公告)号：US20160006932A1

公开(公告)日：2016-01-07

申请号：US14790394

申请日：2015-07-02

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： WENDE ZHANG ,  Jinsong Wang ,  Brunno L. Moretti

IPC: H04N5/232 ,  B60R1/00 ,  H04N5/262

CPC classification number: H04N5/23235 ,  B60R1/00 ,  G06T3/0093 ,  H04N5/23216 ,  H04N5/2628 ,  H04N5/3572

Abstract: A method for providing a high resolution display image that includes providing a camera image that can be processed into at least two different camera views. The method also includes identifying a warped grid in each of the at least two different camera views and identifying a minimum field of view for displaying each of the at least two different camera views. The method further includes cropping the camera image based on the identified minimum field of view and de-warping the at least two different camera views to provide the high resolution display image.

Abstract translation: 一种用于提供高分辨率显示图像的方法，其包括提供可被处理成至少两个不同相机视图的相机图像。 所述方法还包括识别所述至少两个不同相机视图中的每一个中的翘曲网格，并且识别用于显示所述至少两个不同相机视图中的每一个的最小视场。 该方法还包括基于所识别的最小视场裁剪摄像机图像，并且对至少两个不同的摄像机视图进行去翘曲以提供高分辨率显示图像。

公开(公告)号：US09139204B1

公开(公告)日：2015-09-22

申请号：US14302642

申请日：2014-06-12

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Qingrong Zhao ,  Jinsong Wang ,  Wende Zhang ,  Bakhtiar Brian Litkouhi

IPC: G01C21/00 ,  B60W40/064 ,  G06K9/00 ,  G06K9/62

CPC classification number: G01C21/00 ,  B60W40/06 ,  B60W40/068 ,  B60W50/0098 ,  B60W2050/0088 ,  B60W2420/42 ,  B60W2550/12 ,  B60W2550/141 ,  B60W2550/20 ,  Y02T10/6286

Abstract: A method of determining a road surface condition for a vehicle driving on a road. Probabilities associated with a plurality of road surface conditions based on an image of a capture scene are determined by a first probability module. Probabilities associated with the plurality of road surface conditions based on vehicle operating data are determined by a second probability module. The probabilities determined by the first and second probability modules are input to a data fusion unit for fusing the probabilities and determining a road surface condition. A refined probability is output from the data fusion unit that is a function of the fused first and second probabilities. The refined probability from the data fusion unit is provided to an adaptive learning unit. The adaptive learning unit generates output commands that refine tunable parameters of at least the first probability and second probability modules for determining the respective probabilities.

Abstract translation: 一种确定用于在道路上行驶的车辆的路面状况的方法。 基于捕获场景的图像与多个路面条件相关联的概率由第一概率模块确定。 基于车辆操作数据与多个路面条件相关联的概率由第二概率模块确定。 将由第一和第二概率模块确定的概率输入到数据融合单元，用于融合概率并确定路面状况。 从作为融合的第一和第二概率的函数的数据融合单元输出精确概率。 将来自数据融合单元的精确概率提供给自适应学习单元。 自适应学习单元产生输出命令，其精细化至少第一概率和第二概率模块的可调参数，以确定相应的概率。

公开(公告)号：US20150109444A1

公开(公告)日：2015-04-23

申请号：US14071982

申请日：2013-11-05

Applicant: GM Global Technology Operations LLC

Inventor： Wende Zhang ,  Jinsong Wang ,  Bakhtiar B. Litkouhi ,  Dennis B. Kazensky ,  Jeffrey S. Piasecki ,  Charles A. Green ,  Ryan M. Frakes ,  Raymond J. Kiefer

IPC: B60Q9/00

CPC classification number: B60Q9/008 ,  G06K9/00805 ,  H04N7/188

Abstract: A method of displaying a captured image on a display device of a driven vehicle. A scene exterior of the driven vehicle is captured by an at least one vision-based imaging and at least one sensing device. A time-to-collision is determined for each object detected. A comprehensive time-to-collision is determined for each object as a function of each of the determined time-to-collisions for each object. An image of the captured scene is generated by a processor. The image is dynamically expanded to include sensed objects in the image. Sensed objects are highlighted in the dynamically expanded image. The highlighted objects identifies objects proximate to the driven vehicle that are potential collisions to the driven vehicle. The dynamically expanded image with highlighted objects and associated collective time-to-collisions are displayed for each highlighted object in the display device that is determined as a potential collision.

Abstract translation: 一种在被驱动车辆的显示装置上显示拍摄图像的方法。 驱动车辆的场景外部被至少一个基于视觉的成像和至少一个感测装置捕获。 确定检测到的每个物体的碰撞时间。 根据每个对象的每个确定的时间间隔来确定每个对象的综合时间到冲突。 捕获的场景的图像由处理器生成。 图像被动态扩展以包括图像中的感测对象。 感觉对象在动态扩展的图像中突出显示。 突出显示的对象识别靠近从动车辆的物体是与被驱动车辆的潜在碰撞的物体。 对于被确定为潜在碰撞的显示设备中的每个突出显示的对象，显示具有突出显示的对象和关联的集体时间到冲突的动态扩展图像。