-
公开(公告)号:US11170228B2
公开(公告)日:2021-11-09
申请号:US16135848
申请日:2018-09-19
Applicant: HERE Global B.V.
Inventor: Victor Lu
Abstract: A vehicle ranging system includes a ranging scanner, a ranging data processor, and an object classifier. The ranging scanner may be configured to generate a series of ranging data. The ranging data processor may be configured to apply a scale invariant ranging template to the series of ranging data and determine a difference between the ranging template and the series of ranging data. The object classifier may be configured to identify an object corresponding to the series of ranging data based on the difference between the ranging template and the series of ranging data.
-
公开(公告)号:US20200088883A1
公开(公告)日:2020-03-19
申请号:US16135864
申请日:2018-09-19
Applicant: HERE Global B.V.
Inventor: Victor Lu
Abstract: A ranging template system includes a ranging data interface, a sampler, a processor, and a database. The ranging data interface may be configured to receive a series of ranging data. The sampler may be configured to identify a subset of the series of ranging data. The processor may be configured to associate an object with the subset of ranging data and generate a scale invariant ranging template based on the subset of ranging. The database may be configured to store the scale invariant ranging template.
-
3.
公开(公告)号:US10223829B2
公开(公告)日:2019-03-05
申请号:US15366670
申请日:2016-12-01
Applicant: HERE Global B.V.
Inventor: Guangli Wu , Jeffrey Adachi , Ian Endres , Victor Lu , Antonio Haro
Abstract: An approach is provided for generating a cleaned object model to represent an object in a mapping database. The approach includes receiving point cloud data depicting the object. The approach also includes processing the point cloud data to determine one or more surface points of the point cloud data. The one or more surface points represent one or more surfaces of the object. The approach further includes cutting a model of the object into one or more fragments using the one or more surface points. The one or more fragments include one or more object fragments and one or more non-object fragments. The approach further includes designating the one or more object fragments as the cleaned object model to represent the object in the mapping database.
-
公开(公告)号:US10438362B2
公开(公告)日:2019-10-08
申请号:US15609781
申请日:2017-05-31
Applicant: HERE Global B.V.
Inventor: Victor Lu , Ian Endres
Abstract: Embodiments described herein relate generally to determining correspondence between a template and an object in an image. A method may include: receiving an image of an environment including an image of an object within the image of the environment; resizing the first template to obtain a scaled first template having a size corresponding to a size of the image of the object; calculating a number of correspondences between the scaled first template and the image of the object; receiving a candidate homography; testing the candidate homography; and replacing the image of the object with a second template of a different object according to the candidate homography in response to the candidate homography being established as corresponding to the image of the object.
-
公开(公告)号:US20180350085A1
公开(公告)日:2018-12-06
申请号:US15609781
申请日:2017-05-31
Applicant: HERE Global B.V.
Inventor: Victor Lu , Ian Endres
CPC classification number: G06T7/337 , G06T7/74 , G06T11/60 , G06T2207/10028 , G06T2207/20076 , G06T2207/30252
Abstract: Embodiments described herein relate generally to determining correspondence between a template and an object in an image. A method may include: receiving an image of an environment including an image of an object within the image of the environment; resizing the first template to obtain a scaled first template having a size corresponding to a size of the image of the object; calculating a number of correspondences between the scaled first template and the image of the object; receiving a candidate homography; testing the candidate homography; and replacing the image of the object with a second template of a different object according to the candidate homography in response to the candidate homography being established as corresponding to the image of the object.
-
公开(公告)号:US20150379377A1
公开(公告)日:2015-12-31
申请号:US14851677
申请日:2015-09-11
Applicant: HERE Global B.V.
Inventor: Victor Lu
CPC classification number: G06K9/6282 , G06K9/4642 , G06K9/6256 , G06K9/6269 , G06K2209/25
Abstract: In one embodiment, image detection is improved or accelerated using an approximate range query to classify images. A controller is trained on a set of training feature vectors. The training feature vectors represent an image. The feature vectors are normalized to a uniform length. The controller defines a matching space that includes the set of training feature vectors. The controller is configured to identify whether an input vector for a tested image falls within the matching space based on a range query. When the input vector falls within the matching space, the tested image substantially matches the portion of the image used to train the controller.
Abstract translation: 在一个实施例中,使用近似范围查询对图像进行分类来改进或加速图像检测。 对一组训练特征向量训练控制器。 训练特征向量表示图像。 将特征向量归一化为均匀长度。 控制器定义包括训练特征向量集合的匹配空间。 控制器被配置为基于范围查询来识别测试图像的输入向量是否落入匹配空间内。 当输入矢量落在匹配空间内时,测试图像基本上与用于训练控制器的图像部分匹配。
-
公开(公告)号:US20200089968A1
公开(公告)日:2020-03-19
申请号:US16135848
申请日:2018-09-19
Applicant: HERE Global B.V.
Inventor: Victor Lu
Abstract: A vehicle ranging system includes a ranging scanner, a ranging data processor, and an object classifier. The ranging scanner may be configured to generate a series of ranging data. The ranging data processor may be configured to apply a scale invariant ranging template to the series of ranging data and determine a difference between the ranging template and the series of ranging data. The object classifier may be configured to identify an object corresponding to the series of ranging data based on the difference between the ranging template and the series of ranging data.
-
公开(公告)号:US09858503B2
公开(公告)日:2018-01-02
申请号:US14851677
申请日:2015-09-11
Applicant: HERE Global B.V.
Inventor: Victor Lu
CPC classification number: G06K9/6282 , G06K9/4642 , G06K9/6256 , G06K9/6269 , G06K2209/25
Abstract: In one embodiment, image detection is improved or accelerated using an approximate range query to classify images. A controller is trained on a set of training feature vectors. The training feature vectors represent an image. The feature vectors are normalized to a uniform length. The controller defines a matching space that includes the set of training feature vectors. The controller is configured to identify whether an input vector for a tested image falls within the matching space based on a range query. When the input vector falls within the matching space, the tested image substantially matches the portion of the image used to train the controller.
-
-
-
-
-
-
-