MODELLING METHOD AND SYSTEM, AND STORAGE CONTAINER COMPRISING THE SYSTEM

    公开(公告)号:US20240346766A1

    公开(公告)日:2024-10-17

    申请号:US18633582

    申请日:2024-04-12

    申请人: TOBII AB

    发明人: ANDREW RATCLIFF

    IPC分类号: G06T17/20 G06T7/20

    CPC分类号: G06T17/20 G06T7/20

    摘要: A modelling method comprising receiving a plurality of images from an image sensor attached to a side of a hinged door facing an interior of a storage container, wherein each of the plurality of images is captured when the hinged door is at a corresponding one of a plurality of angular positions (θ) relative to the storage container, constructing a three-dimensional, 3D, model of contents within the storage container from the plurality of images and the corresponding plurality of angular positions.

    Method and system for alignment of data

    公开(公告)号:US11943420B2

    公开(公告)日:2024-03-26

    申请号:US17810092

    申请日:2022-06-30

    申请人: TOBII AB

    摘要: A user monitoring system receives a first data stream from a first recording device and a second data stream from a second recording device. Each of the first data stream and the second data stream include data relating to an eye of the user. The first data stream and the second data stream overlap temporally. The system processes the first data stream to determine a first blink sequence of the user, processes the second data stream to determine a second blink sequence of the user, and compares the first blink sequence and the second blink sequence to detect a blink pattern present in both the first blink sequence and the second blink sequence. The system determines a temporal offset of the first data stream and the second data stream by comparing respective positions of the blink pattern in the first data stream and the second data stream.

    Method and system for glint classification

    公开(公告)号:US11854213B2

    公开(公告)日:2023-12-26

    申请号:US17544881

    申请日:2021-12-07

    申请人: Tobii AB

    摘要: An eye tracking system comprises at least one illuminator and at least one image sensor configured to produce an image of an eye of a user, the image including illuminator light reflected from the eye of a user. A Fresnel lens is positioned between the image sensor and the eye of the user, through which the image sensor views the eye. Processing circuitry receives an image from the image sensor, identifies glints in the image, assigns an angular position to each glint based on an angular relationship between each glint and a centre of the Fresnel lens and determines how many glints have the same angular position. Glints are classified as false glints if more than a predetermined number of glints have the same angular position.

    METHOD OF ESTIMATING A THREE-DIMENSIONAL POSITION OF AN OBJECT

    公开(公告)号:US20230394699A1

    公开(公告)日:2023-12-07

    申请号:US18198313

    申请日:2023-05-17

    申请人: TOBII AB

    发明人: DAVID MOLIN

    IPC分类号: G06T7/70 G06T7/80

    摘要: The disclosure relates to a method of estimating a three-dimensional position of at least one target object performed by a computer, the method comprising obtaining a first image, detecting at least one target object, generating a set of images depicting subsets of a captured scene, and estimating a three-dimensional position of at least one target object using a probability distribution (P) indicative of a likelihood that the at least one target object is in a particular position (x, y, z) in the scene.

    Method computer program and driver unit for streaming gaze data packets

    公开(公告)号:US11716365B2

    公开(公告)日:2023-08-01

    申请号:US17007397

    申请日:2020-08-31

    申请人: Tobii AB

    摘要: Data packets containing gaze data are streamed from an eyetracker to a client via a driver unit by receiving, repeatedly, gaze data packets in a first interface; and, providing, repeatedly, via a second interface, gaze data packets. The client sends a request message to the driver unit. The request message defines a delivery point in time in a first time frame structure at which delivery point in time in each frame of the first time frame structure the gaze data packet shall be provided to the client via the second interface. An offset is calculated between a reception point in time and the delivery point in time. The reception point in time indicates when a gaze data packet is received from the eyetracker relative to the first time structure. An adjusted data acquisition instance is assigned based on the offset. The adjusted data acquisition instance represents a modified point in time in a second time frame structure when at least one future gaze data packet shall be produced by the eyetracker. The driver unit sends a control message to the eyetracker. The control message is adapted to cause the eyetracker to produce the at least one future gaze data packet at such an adjusted acquisition instance in the second time structure that the reception point in time for the at least one future gaze data packet is expected to lie within a margin prior to the delivery point in time.

    Multi line trace gaze to object mapping for determining gaze focus targets

    公开(公告)号:US11688128B2

    公开(公告)日:2023-06-27

    申请号:US17572883

    申请日:2022-01-11

    申请人: Tobii AB

    发明人: Fredrik Lindh

    摘要: A method for determining a focus target of a user's gaze in a three-dimensional (“3D”) scene is disclosed. The method may include determining a first gaze direction of a user into a 3D scene, where the 3D scene includes a plurality of components. The method may also include executing a first plurality of line traces in the 3D scene, where each of the first plurality of Line traces is in proximity to the first gaze direction. The method may further include determining a confidence value for each component intersected by at least one of the first plurality of line traces. The method may additionally include identifying as a focus target of the user the component having the highest confidence value of all components intersected by at least one of the first plurality of line traces.