Provided are methods for semantic annotation of sensor data using unreliable map annotation inputs, which can include training a machine learning model to accept inputs including images representing sensor data for a geographic area and unreliable semantic annotations for the geographic area. The machine learning model can be trained against validated semantic annotations for the geographic area, such that subsequent to training, additional images representing sensor data and additional unreliable semantic annotations can be passed through the neural network to provide predicted semantic annotations for the additional images. Systems and computer program products are also provided.

A method and an apparatus for supporting a camera-based environment recognition by a means of transport using road wetness information from a first ultrasonic sensor. The method includes: recording a first signal representing an environment of the means of transport by the first ultrasonic sensor of the means of transport; recording a second signal representing the environment of the means of transport by a camera of the means of transport; obtaining road wetness information on the basis of the first signal; selecting a predefined set of parameters from a plurality of predefined sets of parameters as a function of the road wetness information; and performing an environment recognition on the basis of the second signal in conjunction with the predefined set of parameters.

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.

In one embodiment, a method is provided. The method comprises determining a first value of a coefficient of an edge-determining algorithm in response to a spatial resolution of a first image acquired with an image capture device onboard a vehicle, a spatial resolution of a second image, and a second value of the coefficient in response to which the edge-determining algorithm generated a second edge map corresponding to the second image. The method further comprises determining, with the edge-determining algorithm in response to the coefficient having the first value, at least one edge of at least one object in the first image. The method further comprises generating, in response to the determined at least one edge, a first edge map corresponding to the first image. The method further comprises determining at least one navigation parameter of the vehicle in response to the first and second edge maps.

A system includes one or more video capture devices and a processor coupled to each video capture device. Each processor is operable to direct its respective video capture device to obtain an image of a monitored area and process the image to identify objects of interest represented in the image. The processor is also operable to generate bounding perimeter virtual objects for the identified objects of interest, each bounding perimeter virtual object surrounding at least part of its respective object of interest. The processor is further operable to determine danger zones for the identified objects of interest based on the bounding perimeter virtual objects. The processor is further operable to determine at least one near-miss condition based at least in part on an actual or predicted overlap of danger zones for multiple objects of interest, and may optionally generate an alert at least partially in response to the near-miss condition.

A prediction device 100 of the present invention includes a detection means 121 for, on the basis of a river image that is an image obtained by capturing a river and associated with capturing position information representing a position where the river is captured, detecting river condition information representing a condition of the river at the position where the river image is captured; and a prediction means 122 for, on the basis of the capturing position information, the river condition information, and topography information representing the topography of the river, predicting a river condition representing a condition of the river at a given point of the river. The given point is different from the position represented by the capturing position information.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a driving scenario machine learning network and providing a simulated driving environment. One of the operations is performed by receiving video data that includes multiple video frames depicting an aerial view of vehicles moving about an area. The video data is processed and driving scenario data is generated which includes information about the dynamic objects identified in the video. A machine learning network is trained using the generated driving scenario data. A 3-dimensional simulated environment is provided which is configured to allow an autonomous vehicle to interact with one or more of the dynamic objects.

A method for constructing a three-dimensional road network map is disclosed. The method includes: extracting a two-dimensional road based on a satellite remote sensing image; skeletonizing the two-dimensional road to obtain a two-dimensional road network map; and determining a height of each point in the two-dimensional road network map based on an elevation of three-dimensional point cloud data, to obtain the three-dimensional road network map.

A method of generating a roadway map includes receiving an image of a roadway. The method further includes identifying features in the roadway. The method further includes assigning a feature identification (FID) number to each of the identified features. The method further includes generating a score for each of the identified features based on a comparison between the identified features and a corresponding feature having a same FID number from a previously generated roadway map. The method further includes determining whether each of the identified features have changed based on whether the corresponding score exceeds a predetermined threshold. The method further includes updating the roadway map by changing identified features determined to have changed and maintaining identified features determined to have remain unchanged.

A method of generating a roadway map includes receiving an image of a roadway. The method further includes performing a spectral analysis of the received image to determine reflectivity data for a plurality of wavelengths of light. The method further includes identifying a feature of the roadway in response to the determined reflectivity data exhibiting a reflection peak. The method further includes classifying the identified feature based on a size or a pitch of the exhibited reflection peak. The method further includes generating the roadway map based on the classification of the identified feature.