Here Global B.v.

Xiang Ma

Xin Chen

Roman Ostrovskiy

Di Ma

Xiaotao Zou

Vladimir Zhukov

Vlad Zhukov

Terence Zhao

Hang Dou

Sanjay Chand Sood

Qin Chen

Mark David Tabb

Chen Luo

Qilin Zhang

Sanjay Sood

An apparatus comprising a processor and memory including computer program code, the memory and computer program code configured to, with the processor, enable the apparatus at least to:

Apparatus and associated methods for use in lane-level mapping of road intersections

Lane level traffic levels are determined based on traffic camera images. A controller aligns a three-dimensional map with a traffic camera view, and identifies multiple lanes in the traffic camera view based on lane delineations of the three-dimensional map. The controller calculates a traffic parameter based on the multiple lanes in image frames from the traffic camera view and provides a traffic graphic based on the traffic parameter.

Lane level traffic

Apparatus and methods are described for generating geometries for stripe-shaped objects. An image is identified that includes a roadway having one or more stripe-shaped objects. The stripe-shaped objects may include lane lines for road edges or lanes of the roadway. The stripe-shaped objects may include a barrier. At least one targeted region within the image is determined. The at least one targeted region is shaped to intersect the one or more stripe-shaped objects and includes a plurality of pixels. An image analysis is performed on the image to determine when the at least one target region includes a pixel in common with the one or more stripe-shaped objects. A geometry is constructed using the pixel in common. The geometry may be used to update a map or subsequently perform localization.

Automatic localization geometry generator for stripe-shaped objects

Systems, methods, and apparatuses are disclosed for determining lane information of a roadway segment from vehicle probe data. Probe data is received from vehicle camera sensors at a road segment, wherein the probe data includes lane marking data on the road segment. Lane markings are identified, to the extent present, for the left and right boundaries of the lane of travel as well as the adjacent lane boundaries to the left and right of the lane of travel. The identified lane markings are coded, wherein solid lane lines, dashed lane lines, and unidentified or non-existing lane lines are differentiated. The coded lane markings are compiled in a database. A number of lanes are predicted at the road segment from the database of coded lane markings.

Learning lanes from vehicle probes

Systems, methods, and apparatuses are disclosed for determining lane information of a roadway segment from vehicle probe data. Probe data is received from radar sensors of vehicles at a road segment, where the probe data includes an identification of static objects and dynamic objects in proximity to the respective vehicles at the road segment, and geographic locations of the static objects and the dynamic objects. A reference point, such as a road boundary, at the road segment is determined from the identified static objects. Lateral distances between the identified dynamic objects and the reference point are calculated. A number of lanes at the road segment are ascertained from a distribution of the calculated distances of the identified dynamic objects from the reference point.

Learning lanes from radar sensors

Methods for rendering three-dimensional photo meshes having dynamic content include: (a) detecting a shadow in a three-dimensional photo mesh; (b) removing the shadow from the three-dimensional photo mesh to form a modified photo mesh having a shadow-free texture; (c) simulating a real-time condition in the modified photo mesh; and (d) rendering an image that shows an effect of the real-time condition. Systems for rendering three-dimensional photo meshes having dynamic content are described.

Photorealistic rendering of scenes with dynamic content

A method, apparatus and computer program product are provided for multi-resolution point of interest boundary identification in digital map rendering. A method is provided for receiving a point of interest selection indication. The method also includes receiving point of interest boundary data and map data associated with the selected point of interest from a memory. The boundary data is based on the physical shape of the structure or region associated with the point of interest. The method also includes overlaying point of interest boundary data on the map data; and causing the map data with point of interest boundary data overlay to be displayed on a user interface.

Method and apparatus for multi-resolution point of interest boundary identification in digital map rendering

Learning lanes from radar data

Constructing a three dimensional (3D) model of a structure may involve receiving a 3D surface representing a geographic area, the surface having elevation values associated with points of the surface and the geographic area comprises a structure having a geographic footprint smaller than the geographic area. Constructing a 3D model may also involve projecting the elevation values into a two dimensional (2D) plane. Further, a 3D model may be constructed of the structure by assigning model heights based on the elevation values projected into points of the 2D plane.

Structure model creation from a three dimensional surface

Systems, methods, and apparatuses are disclosed for identifying road signs along a roadway segment from vehicle probe data. Probe data is received from vehicle sensors at a road segment, wherein the probe data includes observed static objects along the road segment. Road signs are identified within the observed static objects of the probe data using a logistic regression algorithm. The geographic location of the identified road signs are determined using a linear regression algorithm.

Learning signs from vehicle probes

Systems/apparatuses and methods are provided for creating aerial images. A three-dimensional point cloud image is generated from an optical distancing system. Additionally, at least one two-dimensional street level image is generated from at least one camera. The three-dimensional point cloud image is colorized with the at least one two-dimensional street level image, thereby forming a colorized three-dimensional point cloud image. The colorized three-dimensional point cloud image is projected onto a two-dimensional plane, using a processor, thereby forming a synthetic aerial image.

Growing community of inventors

Chicago, IL, United States of America

Xiang Ma