Provided is a method and apparatus for identifying a vehicle cross-line. The method may include: determining, in each road condition image of a plurality of road condition images, position information of a target lane line and position information of a target vehicle; determining, based on the position information of the target lane line and the position information of the target vehicle, a relative positional relationship between the target vehicle and the target lane line corresponding to the each road condition image; and determining that the target vehicle crosses the line, if the relative positional relationships corresponding to the plurality of road condition images meet a preset condition.

Provided is a method and apparatus for identifying a vehicle cross-line. The method may include: determining, in each road condition image of a plurality of road condition images, position information of a target lane line and position information of a target vehicle; determining, based on the position information of the target lane line and the position information of the target vehicle, a relative positional relationship between the target vehicle and the target lane line corresponding to the each road condition image; and determining that the target vehicle crosses the line, if the relative positional relationships corresponding to the plurality of road condition images meet a preset condition.

Embodiments of this disclosure provide an object recognition method and apparatus and a single step object recognition neural network, in which by replacing a part of convolutional layers in a conventional single shot multibox detector (SSD) network with dilate convolution, limitation on a size of an input image may be reduced; by increasing connection paths, accuracy of object recognition may be improved; and by connecting the convolutional layers by using residual structures, a convergence effect may be ensured, and accuracy of object recognition may be improved.

A computer-implemented method comprising: providing data of at least one of distance, time, and velocity as at least one trajectory feature, the data defining a plurality of vehicle trajectories; computing for each vehicle trajectory a plurality of meta-features by computing, based on the data, at least one of a maximum value, a mean value, and a standard deviation of at least one of the at least one trajectory feature of each vehicle trajectory, so that each vehicle trajectory is represented by a point in a meta-feature space, the point defined by the plurality of meta-features; implementing a clustering algorithm on the points and selecting, based on a result of the clustering algorithm, at least one point as an anomaly; and selecting the at least one vehicle trajectory corresponding to the at least one point as at least one anomalous vehicle trajectory.

This disclosure discloses a vehicle scheduling method, apparatus and system, and relates to the field of scheduling. The method includes acquiring image information of each area; determining vehicle density information in each area according to the image information; configuring a first path cost corresponding to the path of each area according to the vehicle density information in each area; calculating a path value corresponding to each planning path among a plurality of planning paths from the starting position to at least one target position for a target vehicle, according to the first path cost configured for the path of each area; and determining an optimal planning path of the target vehicle by taking a minimum path value as a target.

This disclosure discloses a vehicle scheduling method, apparatus and system, and relates to the field of scheduling. The method includes acquiring image information of each area; determining vehicle density information in each area according to the image information; configuring a first path cost corresponding to the path of each area according to the vehicle density information in each area; calculating a path value corresponding to each planning path among a plurality of planning paths from the starting position to at least one target position for a target vehicle, according to the first path cost configured for the path of each area; and determining an optimal planning path of the target vehicle by taking a minimum path value as a target.

A 3D bounding box reconstruction method includes obtaining masks corresponding to a target object in images, obtaining a trajectory direction of the target object according to the masks, generating a target contour according to one of the masks, transforming the target contour into a transformed contour using a transformation matrix, obtaining a first bounding box according to the transformed contour and the trajectory direction, transforming the first bounding box into a second bounding box corresponding to the target contour using the transformation matrix, obtaining first reference points according to the target contour and the second bounding box, transforming the first reference points into second reference points using the transformation matrix, obtaining a third bounding box using the second reference points, transforming the third bounding box into a fourth bounding box using the transformation matrix, and obtaining a 3D bounding box using the second bounding box and the fourth bounding box.

The present invention provides a robust and effective solution to an entity or an organization for creating and standardizing an Automotive Data Quality Marker (ADQM) to determine/evaluate/predict the quality of automotive data such as Telematics, Body Control, ADAS, Diagnostics, Dashcams, and In-Vehicle Infotainment but not limited to the like generated by the vehicle (i.e., data source) using a machine learning (ML) engine associated with a processing unit. The machine learning engine comprises an amalgamation of machine learning algorithms to determine ADQM for a particular dataset. Data pertaining to vehicles is huge and repetitive. Re-training of the model for improved accuracy is a requirement as automotive data can be augmented with additional signals and data received and stored as trip objects on a regular basis.

Various embodiments include systems and methods of calculating performance-based rent. Sensor(s) may capture object data associated with objects in an interior and/or exterior environment of a commercial real estate location. Computing device(s) may obtain sales data associated with sales transactions attributable to the commercial real estate location; determine, based at least in part on the object data captured by the sensor(s), object traffic value(s) indicative of an amount of traffic of at least one of the objects; and calculate, based at least in part on performance metric values indicative of actual sales performance and potential sales performance of the commercial real estate location over a particular period of time, a performance-based rent for the commercial real estate location. The performance metric values comprise the sales data and the object traffic value(s), and the performance-based rent is variable over different periods of time with different performance metric values.

There is provided an automated valet parking server that causes an autonomous driving vehicle in a parking place to perform automated valet parking by instructing the autonomous driving vehicle. The automated valet parking server includes an illuminance information acquisition unit configured to acquire illuminance information of front lighting devices of the autonomous driving vehicle, an illuminance suppression point setting unit configured to set an illuminance suppression point which is a position in the parking place at which illuminance of the front lighting devices of the autonomous driving vehicle is suppressed based on parking place map information of the parking place and the illuminance information of the front lighting devices of the autonomous driving vehicle, and an illuminance suppression instruction unit configured to instruct the autonomous driving vehicle to perform illuminance suppression at the illuminance suppression point.