The present disclosure relates to systems and methods for road edge detection and mapping, for vehicle wheel identification and navigation based thereon, and for classification of objects as moving or non-moving. Such systems and methods may include the use of trained systems, such as one or more neural networks. Further, autonomous vehicle systems may incorporate aspects of one or more of the disclosed systems and methods.

Disclosed are devices, systems and methods for incorporating a smoothness constraint for camera pose estimation. One method for robust camera pose estimation includes determining a first bounding box based on a previous frame, determining a second bounding box based on a current frame that is temporally subsequent to the previous frame, estimating the camera pose by minimizing a weighted sum of a camera pose function and a constraint function, where the camera pose function tracks a position and an orientation of the camera in time, and where the constraint function is based on coordinates of the first bounding box and coordinates of the second bounding box, and using the camera pose for navigating the vehicle. The method may further include generating an initial estimate of the camera pose is based on a Global Positioning System (GPS) sensor or an Inertial Measurement Unit (IMU).

An image processing device includes: a delimiting line detection unit configured to detect a delimiting line candidate based on image data obtained by capturing a surrounding of a vehicle, the delimiting line candidate being a candidate of a delimiting line that delimits a parking space; and an exclusion determination unit configured to determine whether or not to exclude the delimiting line candidate detected by the delimiting line detection unit from the candidate of the delimiting line. In a case where a plurality of the delimiting line candidates is detected within a predetermined range in the image data, the exclusion determination unit determines whether or not to exclude the delimiting line candidate from the candidate of the delimiting line by comparing edge strength of the plurality of delimiting line candidates.

A method includes receiving image data associated with an image of a roadway including a crosswalk, generating a plurality of different characteristics of the image based on the image data, determining a position of the crosswalk on the roadway based on the plurality of different characteristics, the position including a first boundary and a second boundary of the crosswalk in the roadway, and providing map data associated with a map of the roadway, the map data including the position of the crosswalk on the roadway in the map. The plurality of different characteristics include a classification of one or more elements of the image, a segmentation of the one or more elements of the image, and one or more angles of the one or more elements of the image with respect to a line in the roadway.

A system may include at least one processor including circuitry and a memory. The memory may include instructions executable by the circuitry to cause the at least one processor programmed to receive at least one identifier associated with a condition having at least one dynamic characteristic. The at least one identifier may be determined based on acquisition, from a camera associated with a host vehicle, of at least one image representative of an environment of the host vehicle, and analysis of the at least one image to identify the condition in the environment, and analysis of the at least one image to determine the at least one identifier associated with the condition. The at least one processor may also be programmed to update a database record to include the at least one identifier associated with the condition, and distribute the database record to at least one entity.

An operating method of a slope estimating apparatus is provided. The operating method of the slope estimating apparatus including at least one camera includes obtaining a forward image through the at least one camera, detecting a lane included in the forward image, dividing the forward image into a plurality of smaller regions in a horizontal direction, identifying a plurality of lane segments included in each of the plurality of smaller regions, obtaining a plurality of coordinate values forming each of the plurality of lane segments, and obtaining a pitch angle of each of the plurality of smaller regions based on the obtained plurality of coordinate values.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining an alignment between cross-modal sensor data. In one aspect, a method comprises: obtaining (i) an image that characterizes a visual appearance of an environment, and (ii) a point cloud comprising a collection of data points that characterizes a three-dimensional geometry of the environment; processing each of a plurality of regions of the image using a visual embedding neural network to generate a respective embedding of each of the image regions; processing each of a plurality of regions of the point cloud using a shape embedding neural network to generate a respective embedding of each of the point cloud regions; and identifying a plurality of region pairs using the embeddings of the image regions and the embeddings of the point cloud regions.

A high-definition map system receives sensor data from vehicles travelling 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 sub-graphs for incrementally improving the high-definition map for keeping it up to date

A vehicle control system includes an imaging device, a map generating unit, and an own lane identifying unit. The own lane identifying unit is configured to identify one lane as an own lane on a map in a case where the one lane is an only lane present in a specific area on the map, compare a type of a delimiting line of a captured own lane with types of delimiting lines of a plurality of lanes on the map in a case where the plurality of lanes are present in the specific area on the map, and identify one of the plurality of lanes on the map as the own lane on the map in a case where the type of the delimiting line of the captured own lane matches only a type of a delimiting line of the one of the plurality of lanes on the map.

A road gradient determining method includes obtaining a three-dimensional road image formed by a two-dimensional road image of a road and laser point cloud data of the road and selecting a plurality of nodes from the three-dimensional road image as control points. The method further includes generating, according to the control points, a first spline curve indicating a road elevation and converting the first spline curve into a second spline curve indicating a road gradient. Finally, the method includes obtaining location information and determining a first road gradient according to the location information and the second spline curve. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.