A method includes defining a disparity range having discrete disparities and taking first, second, and third images of a spatial region using first, second, and third imaging units. The imaging units are arranged in an isosceles triangle geometry. The method includes determining first similarity values for a pixel of the first image for all the discrete disparities along a first epipolar line associated with the pixel in the second image. The method includes determining second similarity values for the pixel for all discrete disparities along a second epipolar line associated with the pixel in the third image. The method includes combining the first and second similarity values and determining a common disparity based on the combined similarity values. The method includes determining a distance to a point within the spatial region for the pixel from the common disparity and the isosceles triangle geometry.

A vehicle computing system performs enhances relatively sparse data collected by a LiDAR sensor by increasing the density of points in certain portions of the scan. For instance, the system generates 3D triangles based on a point cloud collected by the LiDAR sensor and filters the 3D triangles to identify a subset of 3D triangles that are proximate to the ground. The system interpolates points within the subset of 3D triangles to identify additional points on the ground. As another example, the system uses data collected by the LiDAR sensor to identify vertical structures and interpolate additional points on those vertical structures. The enhanced data can be used for a variety of applications related to autonomous vehicle navigation and HD map generation, such as detecting lane markings on the road in front of the vehicle or determining a change in the vehicle's position and orientation.

A vehicle computing system performs enhances relatively sparse data collected by a LiDAR sensor by increasing the density of points in certain portions of the scan. For instance, the system generates 3D triangles based on a point cloud collected by the LiDAR sensor and filters the 3D triangles to identify a subset of 3D triangles that are proximate to the ground. The system interpolates points within the subset of 3D triangles to identify additional points on the ground. As another example, the system uses data collected by the LiDAR sensor to identify vertical structures and interpolate additional points on those vertical structures. The enhanced data can be used for a variety of applications related to autonomous vehicle navigation and HD map generation, such as detecting lane markings on the road in front of the vehicle or determining a change in the vehicle's position and orientation.

As an autonomous vehicle moves through a local area, pairwise alignment may be performed to calculate changes in the pose of the vehicle between different points in time. The vehicle comprises an imaging system configured to capture image frames depicting a portion of the surrounding area. Features are identified from the captured image frames, and a 3-D location is determined for each identified feature. The features of different image frames corresponding to different points in time are analyzed to determine a transformation in the pose of the vehicle during the time period between the image frames. The determined poses of the vehicle are used to generate an HD map of the local area.

As an autonomous vehicle moves through a local area, pairwise alignment may be performed to calculate changes in the pose of the vehicle between different points in time. The vehicle comprises an imaging system configured to capture image frames depicting a portion of the surrounding area. Features are identified from the captured image frames, and a 3-D location is determined for each identified feature. The features of different image frames corresponding to different points in time are analyzed to determine a transformation in the pose of the vehicle during the time period between the image frames. The determined poses of the vehicle are used to generate an HD map of the local area.

A method and a device for determining a highly precise position and for operating an automated vehicle, including: detecting surroundings data values, the surroundings data values representing surroundings of the automated vehicle, the surroundings encompassing at least two surroundings features, determining a pattern, as a function of the at least two surroundings features, reading in map data values, the map data values representing a map, the map representing at least the surroundings of the automated vehicle, the map encompassing a reference pattern, determining the highly precise position of the automated vehicle, proceeding from a comparison of the pattern to the reference pattern, and operating the automated vehicle, as a function of the highly precise position.

This disclosure relates to calibrating a volumetric estimation device for determining dimensions of an object. Two laser sources project two laser lines onto the object to form a rectangular calibration target. A camera captures an image of the rectangular calibration target and has a camera image plane and a camera image plane centre point. A processor measures the camera distortion effects to generate a filter to remove the distortion effects to approximate a pinhole camera. The camera image plane centre point and the points of projection of the laser sources are not collinear. The point of laser projection are not collinear with the camera image plane centre point. The processor uses locations of laser projected crosslines to determine a deviation angle from a direction perpendicular to the camera image plane and the distance between the camera image plane centre point and each laser source.

This disclosure relates to calibrating a volumetric estimation device for determining dimensions of an object. Two laser sources project two laser lines onto the object to form a rectangular calibration target. A camera captures an image of the rectangular calibration target and has a camera image plane and a camera image plane centre point. A processor measures the camera distortion effects to generate a filter to remove the distortion effects to approximate a pinhole camera. The camera image plane centre point and the points of projection of the laser sources are not collinear. The point of laser projection are not collinear with the camera image plane centre point. The processor uses locations of laser projected crosslines to determine a deviation angle from a direction perpendicular to the camera image plane and the distance between the camera image plane centre point and each laser source.

A high-definition map system receives sensor data from vehicles traveling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date

A high-definition map system receives sensor data from vehicles traveling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date