According the present invention, there is provided a control system (10) that includes an image acquisition unit (11) that acquires an image generated by a camera, a controlled object determination unit (12) that analyzes the image and determines at least one of a vehicle that satisfies a predetermined condition and a vehicle in which a predetermined person is riding included in the image, as a vehicle to be controlled, a control content decision unit (13) that decides a control content for the vehicle to be controlled, and an output unit (14) that outputs a control command including the control content to the vehicle to be controlled.

An apparatus for recording license plates of vehicles travelling on a road having several adjacent lanes comprises a vehicle classification sensor configured to detect a predetermined shape characteristic of a vehicle or group of vehicles. The apparatus further comprises at least one camera mounted at an elevated point beside one of the lanes and having an angle of aperture covering at least one of said lanes, each lane covered by at least one camera. The vehicle classification sensor is configured to, upon detecting the predetermined shape characteristic on a lane, trigger the camera that covers the lane the predetermined shape characteristic is detected on to record an image of a license plate on the back of the vehicle or group's leading vehicle, respectively, for which the predetermined shape characteristic is detected. The triggered camera is of a lane either adjacent to or at least one lane apart from the lane.

A mobile object control device according to an embodiment includes a recognizer configured to recognize a surroundings situation of a mobile object, a trajectory predictor configured to predict future trajectories of the mobile object and an object likely to come into contact with the mobile object when there is the object around the mobile object, and an unavoidable contact determiner configured to determine whether contact between the mobile object and the object is unavoidable on the basis of the predicted trajectories of the mobile object and the object predicted by the trajectory predictor, and the trajectory predictor predicts the future trajectory of the object on the basis of a recognition state of a travel wheel of the object in the recognizer.

In one embodiment, a video analysis service receives video data captured by one or more cameras at a particular location. The service applies a neural network-based model to portions of the video data, to identify objects within the video data. The service maps outputs of the neural network-based model to symbols using a conceptual space. The outputs of the model comprise the identified objects. The service applies a symbolic reasoning engine to the symbols, to generate an alert. The service sends the alert to a user interface in conjunction with the video data.

The solution proposed by the invention consists of a method for monitoring the tyres of vehicles transporting excavations in mines, using tyre handling equipment, said tyres being equipped with radio frequency identification tags and physical parameter sensors; said method also using a database comprising the identifiers of the vehicles, the identifiers of the tyres, the identifiers of the sensors and of the positions of the tyres on the axles.

A method and an apparatus for pushing vehicle information, a user account server, and user equipment are provided. The method includes: receiving an entry event that is of a vehicle and that is sent by a parking management server, and obtaining geo-fence information of a parking lot managed by the parking management server; obtaining, by a user account server, a user account bound to the license plate number of the vehicle; obtaining a location determining result of user equipment corresponding to the user account; and pushing the entry event of the vehicle to the user equipment when the current location of the user equipment is within a geo-fence range.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a generative adversarial network (GAN) to reconstruct a missing portion of an image by determining a reconstructed portion of the image based on data from portions of the image surrounding the missing portion and compare an acquired image with the reconstructed portion of the image to determine a damaged portion. The instructions further include instructions to determine estimated damage based on the damaged portion.

In some embodiments, apparatuses and methods are provided herein useful to determine text on an object. In some embodiments, there is provided a system to determine text of interest on an object of interest including at least one camera and a control circuit configured to execute a machine learning model trained to identify the text of interest, group into a cluster each node point that is located substantially in the same location in the text of interest, determine a score value of each particular character in the cluster, identify the particular character that has a determined score value corresponding to at least a threshold score value relative to all characters in the cluster, assign the particular character having the determined score value corresponding to at least the threshold score value as a recognized character in the cluster, and transmit to a display monitor overlay data.

An object detection method and apparatus are disclosed. The object detection method may include acquiring identification information of an object detected from each of N (N being a preset integer of 3 or more) images continuous in order of capture from the output of a classification layer of an object detection deep learning network and correcting, based on the identification information of the object detected from each of at least two images that have been captured early in order of time, among the N images, the identification information of the object detected from an image that has been captured later in order of time than the at least two images that have been captured early in order of time, among the N images.

A parking assist system for a vehicle includes an environment information obtainer, a storage, a parked vehicle detector, a space determiner, and a parking possibility determiner. The storage stores a reference parking width to be used for parking the vehicle. The parked vehicle detector detects a parked vehicle. The space determiner compares a width of a space next to the parked vehicle with the reference parking width and determines whether the width of the space is greater than or equal to the reference parking width. If the width of the space is found to be greater than or equal to the reference parking width, the parking possibility determiner determines whether a target object is detected at a back side of the space. If the target object is not detected, the parking possibility determiner determines that parking in the space is prohibited.