In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

Disclosed herein are systems and methods for alleviating traffic congestion within an enforcement zone. In some embodiments, a system for alleviating traffic congestion within an enforcement zone comprises a server and a plurality of edge devices coupled to carrier vehicles deployed within the enforcement zone. The edge devices can be configured to capture videos of vehicles that may be subject to the traffic congestion pricing policy and to determine their locations, license plate numbers, and certain vehicle attributes using certain sensors on the edge devices and deep learning models running on the edge devices. The edge devices can also be configured to transmit evidence packages to the server concerning such vehicles. The server can be configured to evaluate the evidence packages received from the edge devices and prepare final evidence packages concerning the vehicles for further review and processing.

A vehicle parking management method, comprising: on at least one of a vehicle and a mobile device, acquiring current parking place information and a plurality of additional information of a parking lot, the current parking place information at least comprising a location of an unoccupied parking place, each additional information in the plurality of additional information being configured for identifying associated data; on the basis of the current parking place information and the additional information, generating a parking place distribution image, the parking place distribution image at least indicating the unoccupied parking place and the additional information; presenting the parking place distribution image; and in response to that an operation targeting the unoccupied parking place or the additional information is detected, generating a navigation indication related to a target unoccupied parking place.

A parking assistance system for assisting parking of a vehicle includes: an autonomous driving vehicle configured to perform automatic driving from a drop off area in a parking lot to a parking position upon receiving a parking start instruction; a management device configured to manage entering and exiting of the autonomous driving vehicle; and a fixed terminal device installed in the drop off area, the fixed terminal device being operable by a user of the autonomous driving vehicle. The management device includes an intention acquiring unit configured to acquire a parking intention input by the user; an inspection executing unit configured to execute an inspection on the autonomous driving vehicle; an operation requesting unit configured to request the user to perform a predetermined operation through the fixed terminal device; and an instruction transmitting unit configured to transmit the parking start instruction to the autonomous driving vehicle.

A data acquisition system of a vehicle includes an image capture device, a communication interface, and a controller communicatively coupled to the image capture device and communicatively coupled to the communication interface. Processors of the controller are configured to calibrate an image-distance relationship value of an identified component of a first image captured by the image capture device corresponding to a known feature based on established metrics of the known feature. The processors are also configured to provide control of the vehicle or activation of an alert system of the vehicle via the communication interface based on the image-distance relationship value.

An information processing apparatus according to an embodiment of the present technology includes a first acquisition unit, a second acquisition unit, and a generation unit. The first acquisition unit acquires peripheral information regarding a periphery of a first mobile object. The second acquisition unit acquires, from an apparatus different from the first mobile object, attribute information regarding an attribute of a second mobile object present in the periphery of the first mobile object. The generation unit generates learning data for extracting an attribute of a target mobile object, on the basis of the acquired peripheral information and the acquired attribute information.

A system, method and program storage device are provided for automatically associating evidence recorded by a plurality of cameras with a discrete occurrence, including: receiving occurrence data pertaining to the discrete occurrence and storing at least a portion of the occurrence data in an occurrence record; receiving first evidence data comprising at least a video data portion and a metadata portion of the evidence recorded by a first camera of the plurality of cameras and storing it in an evidence record; receiving second evidence data comprising at least a video data portion and a metadata portion of the evidence recorded by a second camera of the plurality of cameras and storing it in the evidence record; automatically associating information stored in the evidence record with information stored in the occurrence record based on a correspondence of at least two criteria including a first criterion of time; identifying, based on the automatic association, a first image data portion of the evidence recorded by the first camera that is related to the discrete occurrence while excluding a second image data portion of the evidence recorded by the first camera that is unrelated to the discrete occurrence; and identifying, based on the automatic association, a third image data portion of the evidence recorded by the second camera that is related to the discrete occurrence while excluding a fourth image data portion of the evidence recorded by the second camera that is unrelated to the discrete occurrence.

A method for generating learning data for the neural network may comprise generating a license plate image by combining a background image, a frame image and a text image, generating a transformed image by performing at least one of a geometry transformation and a filter transformation on the license plate image, setting a text corresponding to the text image as target data for the transformed image, and generating the learning data including the transformed image and the target data.

A method performed by a computing system includes receiving from a first detection system, a plurality of identity tokens, the plurality of identity tokens including different types of identity tokens, the first detection system having a plurality of different types of detection instruments. The method further includes using information from the first detection system, creating correlation information that correlates different types of identity tokens. The method further includes receiving from a second detection system, a number of identity tokens, the second detection system having a plurality of different types of detection instruments that is fewer than the first detection system. The method further includes using the number of identity tokens received from the first and second detection systems, identifying a vehicle passing through the second detection system.

Systems and methods for generating targeted media content capture an image from an image capture device. The system may analyze the image to recognize a visual identifier for each entity in the image, each of which may have one or more group identifiers. The system may aggregate the group identifiers to identify the number of each group in the audience area and select media content to display to the audience based on the aggregate numbers of each group identified in the audience area. The system may also derive time restrictions for groups identified in the audience area to help optimize how groups traverse through one or more areas.