公开(公告)号：US20190034740A1

公开(公告)日：2019-01-31

申请号：US15661915

申请日：2017-07-27

Applicant: HERE GLOBAL B.V.

Inventor： Richard KWANT ,  Anish MITTAL ,  Nicholas POJMAN ,  Yangyang CHEN

IPC: G06K9/00 ,  G06K9/46

CPC classification number: G06K9/00798 ,  G06K9/4628 ,  G06K9/4671 ,  G06K9/6274

Abstract: An approach is provided for estimating a vanishing point or horizon in an image depicting one or more lanes of a roadway. The approach involves processing the image to construct one or more lane models of the one or more road lanes depicted in the image. The approach also involves extending the one or more road lanes through the image using the one or more lane models. The approach further involves determining a horizontal line in the image at which a maximum number of the one or more extended road lanes crosses over a minimum horizontal extent of the horizontal line. The approach further involves designating the horizontal line as the horizon of the image.

公开(公告)号：US20200167603A1

公开(公告)日：2020-05-28

申请号：US16201527

申请日：2018-11-27

Applicant: HERE GLOBAL B.V.

Inventor： Alex UNG ,  Zhanwei CHEN ,  Anish MITTAL ,  Nicholas POJMAN ,  David LAWLOR

IPC: G06K9/62 ,  G06T7/70 ,  G06T7/20 ,  G06T11/60 ,  G06F3/0484 ,  G06T7/73

Abstract: An approach is provided for image labeling for cross view alignment. The approach, for example, involves determining camera pose data, camera trajectory data, or a combination thereof for a first image depicting an area from a first perspective view. The approach also involves processing the camera pose data, the camera trajectory data, or a combination thereof to generate meta data indicating a position, an orientation, or a combination thereof of the first perspective view of the area relative to a second image depicting the area from a second perspective view. The approach further involves providing data for presenting the meta data in a user interface as an overlay on the second perspective view.

公开(公告)号：US20190102656A1

公开(公告)日：2019-04-04

申请号：US15720974

申请日：2017-09-29

Applicant: HERE GLOBAL B.V.

Inventor： Richard KWANT ,  Anish MITTAL ,  Nicholas POJMAN ,  Yangyang CHEN

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G01C21/36 ,  G05D1/02

Abstract: An approach is provided for providing quality assurance for training a feature prediction model. The approach involves training the feature prediction model to label one or more features by using a training data set comprising a plurality of data items with manually marked feature labels. The approach also involves processing the training data set using the trained feature prediction model to generate automatically marked feature labels for the plurality of data items. The approach further involves computing precision data indicating a respective precision between the manually marked feature labels and the automatically marked feature labels for each of the plurality of data items in the training data set. The approach further involves initiating a quality assurance procedure on said each of the plurality of data items based on a determination that the precision data does not satisfy a quality assurance criterion.

公开(公告)号：US20200285862A1

公开(公告)日：2020-09-10

申请号：US16293328

申请日：2019-03-05

Applicant: HERE GLOBAL B.V.

Inventor： Nicholas POJMAN ,  Anish MITTAL ,  David LAWLOR ,  Zhanwei CHEN

IPC: G06K9/00 ,  G06T7/00 ,  G06T5/00 ,  G06T7/10

Abstract: An approach is provided for detecting degraded ground paint in an image. The approach, for example, involves performing semantic segmentation on the image to determine one or more pixels of the image that are classified in a ground paint category. The approach also involves generating a binary image that contains the one or more pixels of the image that are classified in the ground paint category. The approach further involves generating a hole-filled binary image by filling in the binary image to generate one or more curvilinear structures from the one or more pixels. The approach further involves determining a difference between the image and the hole-filled binary image to identify one or more degraded ground paint pixels of the image and providing the one or more degraded ground paint pixels as an output.

公开(公告)号：US20200167689A1

公开(公告)日：2020-05-28

申请号：US16203087

申请日：2018-11-28

Applicant: HERE GLOBAL B.V.

Inventor： Nicholas POJMAN ,  Anish MITTAL ,  Zhanwei CHEN

IPC: G06N20/00 ,  G06K9/62 ,  G06F3/0484

Abstract: An approach is provided for selecting machine learning training observations. The approach, for example, involves providing data for presenting a user interface displaying a plurality of training images and specifying a feature to label in the plurality of training images. The feature is selected based on an image selection criterion. The approach also involves receiving a set of feature labels for the plurality of training images via the user interface based on crowd-sourced input data. The approach further involves training a machine learning based image selector to select a plurality of images, a plurality of patches of a larger image, or a combination thereof for labeling based on the set of feature labels and the plurality of training images.