A control device for automated valet parking lot includes: a travel route determining unit configured to determine a travel route to a parking space; a travel route transmission unit configured to transmit the travel route to a vehicle; a position acquiring unit configured to acquire, from the vehicle, a position of the vehicle that is estimated by the vehicle while traveling; and a positional accuracy calculation unit configured to calculate a dynamic estimation accuracy, which is an accuracy of the position of the vehicle acquired by the position acquiring unit from the vehicle while the vehicle is travelling, prior to performing automated driving of the vehicle in accordance with the travel route.

Apparatuses, systems, and techniques to train neural networks to perform classification. In at least one embodiment, one or more neural networks are trained to perform classification based, at least in part, on grouping one or more sets of neural network training data according to behaviors of one or more objects within one or more images represented by the training data.

A parking management system identifies vehicles in entrance lanes, exit lanes, or both, of a parking facility and provides a real-time vehicle inventory count. One or more beacons locate point of sale (POS) devices assigned to parking attendants to determine which of them are performing vehicle transactions. Vehicles can be associated with specific transactions, as well as the transaction-authorizing attendant and the barrier gate and vehicle travel lane to which the attendant is assigned. To reduce fraud, this transaction information can be monitored in real time by a web or mobile dashboard and analyzed in real time or upon attendant end-of-shift checkout. The parking management system also implements permit parking invitation techniques that provide registration, payment in advance or on demand, or both, for parking of an invitee's vehicle. These tasks are accomplished without an inviter's knowledge about the invitee, the invitee's vehicle, or both.

A parking management system identifies vehicles in entrance lanes, exit lanes, or both, of a parking facility and provides a real-time vehicle inventory count. One or more beacons locate point of sale (POS) devices assigned to parking attendants to determine which of them are performing vehicle transactions. Vehicles can be associated with specific transactions, as well as the transaction-authorizing attendant and the barrier gate and vehicle travel lane to which the attendant is assigned. To reduce fraud, this transaction information can be monitored in real time by a web or mobile dashboard and analyzed in real time or upon attendant end-of-shift checkout. The parking management system also implements permit parking invitation techniques that provide registration, payment in advance or on demand, or both, for parking of an invitee's vehicle. These tasks are accomplished without an inviter's knowledge about the invitee, the invitee's vehicle, or both.

A method of training a model, an electronic device, and a readable storage medium are provided, which relate to a field of artificial intelligence, in particular to computer vision and deep learning technologies, and specifically used in smart city and intelligent transportation scenarios. The method includes: determining a target pre-trained model; and performing an unsupervised training and/or a semi-supervised training on the target pre-trained model based on an image acquired by the target terminal, so as to obtain a first target trained model.

A lane information management method for managing lane information using a processor is provided. This method includes acquiring road map information and information on a travel history that is represented by a travel trajectory on a road map, determining, using a plurality of the travel histories, whether or not a lane connected to an intersection is in a multiple lane form in which two or more lines of vehicles are formed on a single lane, and managing the lane information, including a result of determination of the multiple lane form in the lane information.

A mobile terminal to be carried by a user of a vehicle acquires a captured image of the vehicle, acquires distance information on a distance to the vehicle based on the captured image, determines whether the distance to the vehicle is within a predetermined allowable distance based on the distance information, and transmits an operation signal corresponding to an operation content input by a user to the vehicle when the distance to the vehicle is determined to be within the allowable distance.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to detect a moving object in video stream data based on determining an eccentricity map. The instructions can further include instructions to determine a magnitude and direction of motion of the moving object, transform the magnitude and direction to global coordinates and operate a vehicle based on the transformed magnitude and direction.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to detect a moving object in video stream data based on determining an eccentricity map. The instructions can further include instructions to determine a magnitude and direction of motion of the moving object, transform the magnitude and direction to global coordinates and operate a vehicle based on the transformed magnitude and direction.

Disclosed is a method for short-term traffic risk prediction of road sections by using roadside observation data. The method includes the following steps: 1) vehicle trajectory data in the detection area is obtained by using roadside observation data; 2) according to the continuous driving trajectories in the detection area, the traffic flow indicators are counted, and the surrogate safety indicators between vehicles are calculated; 3) time to collision and deceleration are selected as identification indicators to identify conflict events with collision risk in the detection area; 4) traffic flow indicators and surrogate safety indicators within the set time before the occurrence of conflict events are extracted, and the feature screening of various extracted indicators is performed by using classification algorithms; 5) based on the selected feature indicators, the indicators with the highest importance ranking are selected as the input to build a short-term traffic risk prediction model, and the model training and testing are completed by using the identified conflict events; 6) the short-term traffic risk prediction model is used to predict the risk of road sections. The proposed method can improve the prediction accuracy rate of road sections.