Abstract

This application relates to a method of training a machine learning model. The method comprises the steps of generating a training data set by: receiving two-dimensional (2D) image data captured by a 2D camera; receiving three-dimensional (3D) image data captured a 3D camera, said 3D image data being synchronized with the 2D image data captured by the 2D camera; applying a first object detection model to the 2D image data to identify a first object in the 2D image data and output parameters defining a bounding box for the first object in the 2D image data; applying a second object detection model to the 3D image data to identify the same first object in the 3D image data and output a 3D coordinate corresponding to the location of the first object in the 3D image data, said 3D coordinate including either a z coordinate or a radial coordinate indicative of a distance to the first object from the 3D camera; storing the bounding box parameters and the coordinate indicative of the distance to the first object from the 3D camera in the training data set as a data pair; and repeating the above steps a plurality of times with the first object located at different locations in the 2D image data and 3D image data. The method further comprises training, using the generated training data set, a machine learning model for predicting a coordinate indicative of a distance to a target object from the 3D camera based on input data relating to additional image data captured by the 2D camera, said input data including bounding box parameters for the target object in the additional image data captured by the 2D camera.

IPC Classes  ?

• G06V 10/70 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning
• G06T 7/70 - Determining position or orientation of objects or cameras
• G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
• G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands

Abstract

There is provided an image processing system and method for identifying associations between detected entities. The system comprises a processor configured to detect a number of entities within an observable environment, determine the behaviour of the detected entities including identifying predetermined behaviour with a first machine learning model and/or identifying anomalous behaviour with a second machine learning model, and determining an association between a first entity and another entity based on the identified behaviour(s).

IPC Classes  ?

• G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
• G06N 20/00 - Machine learning
• G06T 7/70 - Determining position or orientation of objects or cameras
• G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
• G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces

Abstract

A method of managing aircraft information is provided The method comprises receiving scheduling information, the scheduling information comprising flight and turnaround information relating to a plurality of aircraft; extracting the flight and turnaround information for each of the plurality of aircraft from the scheduling information; assigning the extracted flight and turnaround information for each of the plurality of aircraft to a channel, wherein each channel corresponds to one of the plurality of aircraft; and providing access to the channels to a user. A corresponding computer system and non-transitory memory are also provided.

IPC Classes  ?

• G08G 5/00 - Traffic control systems for aircraft

Abstract

There is provided a freestanding kiosk 100 having a front side and a rear side, the kiosk comprising: a body 110 for housing one or more internal components of the kiosk 100; a first display 111 on the front side of a top portion of the kiosk 100; a second display 112 on the rear side of a top portion of the kiosk 100; wherein the second display 112 is movable between a first position in which it is proximate the kiosk body 110 and a second position in which it is spaced away from kiosk body 110; and wherein the kiosk 100 is provided with at least two wheels 122 for transporting the kiosk 100.

IPC Classes  ?

• G09F 19/02 - Advertising or display means not otherwise provided for incorporating moving display members
• A47F 10/02 - Furniture or installations specially adapted to particular types of service systems, not otherwise provided for for self-service type systems, e.g. supermarkets
• G06Q 50/26 - Government or public services
• G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
• G07F 17/42 - Coin-freed apparatus for hiring articlesCoin-freed facilities or services for ticket printing or like apparatus
• G09F 19/00 - Advertising or display means not otherwise provided for

Abstract

A system for generating a labelled dataset is provided. The system comprises processor configured to: receive first data wherein the first data comprises one or more frames and wherein the first data comprises data defining an object of interest within a predetermined area; receive second data wherein the second data is associated with the object of interest within the predetermined area; analyse the one or more frames of the first data to identify, based on the second data, the object of interest present in the first data; label the one or more frames of the first data based on the analysis to generate a labelled dataset; and output the labelled dataset. Also provided is a method for generating a labelled dataset, a system for training a machine learning model, and a detection system for detecting one or more objects of interest.

IPC Classes  ?

• G06V 20/54 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
• G06V 20/40 - ScenesScene-specific elements in video content
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
• G06T 7/70 - Determining position or orientation of objects or cameras

Abstract

A system for generating a labelled dataset is provided. The system comprises processing means configured to: receive first data wherein the first data comprises one or more frames and wherein the first data comprises data defining an object of interest (203) within a predetermined area (202); receive second data wherein the second data is associated with the object of interest within the predetermined area; analyse the one or more frames of the first data to identify, based on the second data, the object of interest present in the first data; label the one or more frames of the first data based on the analysis to generate a labelled dataset; and output the labelled dataset. Also provided is a method for generating a labelled dataset, a system for training a machine learning model, and a detection system for detecting one or more objects of interest.

IPC Classes  ?

• G06K 9/00 - Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
• B64F 1/36 - Other airport installations
• G01D 21/02 - Measuring two or more variables by means not covered by a single other subclass
• G06N 20/00 - Machine learning
• G01B 21/02 - Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G08G 9/02 - Anti-collision systems

Abstract

An interactive kiosk for reading a document, the kiosk comprising: a transparent platform for supporting a document; a first camera disposed below the transparent platform; a mirror assembly comprising at least one mirror disposed below the transparent platform, the mirror assembly being arranged to reflect light from the underside of the transparent platform to the lens of the first camera; and a control unit connected to the first camera, the control unit being configured to receive content from the first camera and extract data from a document disposed on the transparent platform.

IPC Classes  ?

• G06V 30/40 - Document-oriented image-based pattern recognition
• G06K 7/14 - Methods or arrangements for sensing record carriers by electromagnetic radiation, e.g. optical sensingMethods or arrangements for sensing record carriers by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
• H04N 23/51 - Housings

Abstract

An interactive kiosk for reading a document, the kiosk comprising: a transparent platform for supporting a document; a first camera disposed below the transparent platform; a mirror assembly comprising at least one mirror disposed below the transparent platform, the mirror assembly being arranged to reflect light from the underside of the transparent platform to the lens of the first camera; and a control unit connected to the first camera, the control unit being configured to receive content from the first camera and extract data from a document disposed on the transparent platform.

IPC Classes  ?

• H04N 1/23 - Reproducing arrangements
• G03B 15/00 - Special procedures for taking photographsApparatus therefor
• G06K 9/20 - Image acquisition
• G06K 9/78 - Combination of image acquisition and recognition functions

Abstract

A system for generating a labelled dataset is provided. The system comprises processing means configured to: receive first data wherein the first data comprises one or more frames and wherein the first data comprises data defining an object of interest (203) within a predetermined area (202); receive second data wherein the second data is associated with the object of interest within the predetermined area; analyse the one or more frames of the first data to identify, based on the second data, the object of interest present in the first data; label the one or more frames of the first data based on the analysis to generate a labelled dataset; and output the labelled dataset. Also provided is a method for generating a labelled dataset, a system for training a machine learning model, and a detection system for detecting one or more objects of interest.

IPC Classes  ?

• B64F 1/36 - Other airport installations
• G01B 21/02 - Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
• G01D 21/02 - Measuring two or more variables by means not covered by a single other subclass
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G06N 20/00 - Machine learning
• G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
• G08G 9/02 - Anti-collision systems