Methods, systems, and apparatus, including computer programs encoded on a storage device, for filling gaps in electric grid models are enclosed. A method includes obtaining vector data representing first portions of paths of electric grid wires over a geographic region; converting the vector data to first raster image data that depicts an overhead view of the electric grid wires including a first set of line segments representing the first portions of the paths; processing the first raster image data using a gap filling model; obtaining, as output from the gap filling model, second raster image data including a second set of line segments corresponding to gaps included in the input raster image data and representing second portions of paths of the electric grid wires; and converting the second raster image data to vector data representing the first portions and the second portions of paths of the electric grid wires.

A method for providing cues to an aerial vehicle operator is disclosed. The method includes: determining when a vehicle is on final approach; processing a plurality of ground images of a ground path ahead of the vehicle; identifying a lane in the processed ground images; determining whether the identified lane corresponds to an assigned runway based on a relative position or a relative geometry of the identified lane; tracking during landing a left and a right side edge, a front edge, and a runway center line of the assigned runway; determining, relative to the runway center line, whether a relative position of the vehicle during landing is left of, right of, or aligned with the runway center line; and providing visual and/or audible guidance to the vehicle operator to take corrective action when the relative position of the vehicle during landing is not aligned with the runway center line.

A method, apparatus, and computer program product are provided for identifying on-street parking from aerial imagery. A method may include: receiving an aerial image of a geographic region; applying an object detection algorithm to the received aerial image to identify vehicle objects within the aerial image; identifying one or more clusters of vehicle objects within the aerial image; generating cluster lines for the one or more clusters of vehicle objects; map matching the cluster lines for the one or more clusters of vehicle objects to a map of the geographic region; and identifying on-street parking for a road segment in response to a cluster line of the cluster lines for the one or more clusters of vehicle objects satisfying predetermined criteria with respect to the road segment.

An apparatus and method for lane feature detection from an image is performed according to predetermined path geometry. An image including at least one path is received. The image may be an aerial image. Map data, corresponding to the at least one path and defining the predetermined path geometry is selected. The image is modified according to the selected map data including the predetermined path geometry. A lane feature prediction model is generated or configured based on the modified image. A subsequent image is provided to the lane feature prediction model for a prediction of at least one lane feature.

Embodiments are disclosed for ground plane estimation (GPE) using a LiDAR semantic network. In an embodiment, a method comprises: obtaining a point cloud from a depth sensor of a vehicle operating in an environment; encoding the point cloud; estimating, using a deep learning network with the encoded point cloud as input, a ground plane in the environment; planning a path through the environment based on a drivable area of the estimated ground plane; and operating the vehicle, the vehicle along the path. The deep learning network includes a two-dimensional (2D) convolutional backbone, a detection head for detecting objects and a GPE head for estimating the ground plane. In an embodiment, point pillars are used to encode the point cloud.

A method for processing a map, an electronic device, and a storage medium, which relate to a technical field of computer technology, in particular to computer vision technology and high-definition map technology. The method includes: segmenting a first road line to obtain a plurality of first sub-road lines, wherein the first road line is obtained according to a segmentation mask for an image, and the image corresponds to a target region; segmenting a second road line to obtain a plurality of second sub-road lines, wherein the second road line is obtained according to a trajectory information corresponding to the target region; and determining a target road line according to first similarities between the plurality of first sub-road lines and the plurality of second sub-road lines.

A method is provided to using a machine learning model to predict lane geometry where incorrect or missing lane line geometry is detected. Methods may include: receiving a representation of lane line geometry for one or more roads of a road network; identifying an area within the representation including broken lane line geometry; generating a masked area of the area within the representation including the broken lane line geometry; processing the representation with the masked area through an inpainting model, where the inpainting model includes a generator network, where the representation is processed through the generator network which includes dilated convolution layers for inpainting of the masked area with corrected lane line geometry in a corrected representation; and updating a map database to include the corrected lane line geometry in place of the area including the broken lane line geometry based on the corrected representation.

A method is provided to using a machine learning model to predict lane geometry where incorrect or missing lane line geometry is detected. Methods may include: receiving a representation of lane line geometry for one or more roads of a road network; identifying an area within the representation as broken lane line geometry of an intersection using a machine learning model; generating a masked area of the broken lane line geometry of the intersection within the representation; processing the representation with the masked area using an inpainting model to generate an inpainted result within the masked area of restored lane line geometry of the intersection, where the inpainting model is trained using a set of representations identified as lane line geometry of intersections; and updating a map database to include the restored lane line geometry of the intersection in place of the broken lane line geometry of the intersection.

Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.

A method for detecting road edges at a predetermined intersection, comprising: receiving, by the controller, aerial imagery data about the predetermined intersection; receiving, by the controller, vehicle telemetry data from at least one vehicle passing through the predetermined intersection; detecting, using the aerial imagery data and generative adversarial networks (GANs) executed on the controller, road edges at the predetermined intersection; classifying, using the vehicle telemetry data and a random forest classifier (RFC) executed on the controller, each vehicle trajectory passing through the predetermined intersection with a label corresponding to a unique maneuver to create a maneuver labeling at the predetermined intersection; constructing, using the maneuver labeling determined by the RFC and the road edges, a probabilistic finite state automata (PFSA) to pair inbound lanes with outbound lanes at the predetermined intersection; and determining lane edges at the predetermined intersection using a homotopy model.