-
公开(公告)号:US11682218B2
公开(公告)日:2023-06-20
申请号:US17553264
申请日:2021-12-16
Applicant: Geotab Inc.
IPC: G06V20/59 , G06V20/70 , G06V10/74 , G06V10/22 , G06V10/70 , G06V10/75 , G06V10/774 , G06V10/94 , B60R25/30 , G07C5/00 , H04N7/18
CPC classification number: G06V20/59 , B60R25/305 , G06V10/235 , G06V10/759 , G06V10/761 , G06V10/774 , G06V10/87 , G06V10/945 , G06V20/70 , G07C5/008 , H04N7/188 , G06V2201/02
Abstract: Methods for vehicle data collection by image analysis are provided. An example method involves positioning a camera in a vehicle to be pointed toward a field of interest in the vehicle, capturing an image of the field of interest with the camera, identifying a region of interest in the image that is expected to convey vehicle information, and running an image processing model over the region of interest to extract vehicle information from the image.
-
公开(公告)号:US12088964B2
公开(公告)日:2024-09-10
申请号:US17890560
申请日:2022-08-18
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
IPC: H04N7/18 , G01C21/36 , G06F3/04847 , G06V20/52 , G06V20/56 , G06F3/04842
CPC classification number: H04N7/181 , G01C21/3614 , G01C21/3667 , G06V20/52 , G06V20/56 , G06F3/04842 , G06F3/04847
Abstract: Detection models are distributed as needed to a select subset of image capture devices, based on geographic location and time of the image capture devices. Each image capture device which receives a model processes image data according to the model, and provides a notification of any detected instances of an event the model is trained to detect. Distribution and detection can be based on historical data or live data.
-
3.
公开(公告)号:US20230143809A1
公开(公告)日:2023-05-11
申请号:US17714570
申请日:2022-04-06
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
CPC classification number: G06K9/6256 , G05B13/0265
Abstract: Systems and methods by a telematics server are provided. The method includes receiving, over a network, training data including model input data and a known output label corresponding to the model input data from a first device, training a centralized machine-learning model using the training data, determining, by the centralized machine-learning model, an output label prediction certainty based on the model input data, determining an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model, and sending, over the network, a machine-learning model update to a second device in response to determining that the increase in the output label prediction certainty is greater than an output label prediction increase threshold.
-
公开(公告)号:US20240275917A1
公开(公告)日:2024-08-15
申请号:US18420976
申请日:2024-01-24
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique , Willem Petersen
IPC: H04N7/01
CPC classification number: H04N7/0127 , H04N7/0135
Abstract: A synchronized data set is generated from multiple asynchronous data sets. An interpolated data set is generated for each asynchronous data set, at a higher data rate than recorded data rates for the asynchronous data sets. The interpolated data for each data set is then sampled at a lower data rate which is common to all the interpolated data sets. The sampled data points are synchronized between the different data sets, such that the sampled data points represent a synchronized data set. Input telematic data can be reduced to inflection points in the telematic data, and interpolation and sampling of asynchronous data sets can be limited to threshold time periods around the inflection points.
-
公开(公告)号:US11693920B2
公开(公告)日:2023-07-04
申请号:US17714570
申请日:2022-04-06
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
CPC classification number: G05B13/0265 , G06N3/08
Abstract: Systems and methods by a telematics server are provided. The method includes receiving, over a network, training data including model input data and a known output label corresponding to the model input data from a first device, training a centralized machine-learning model using the training data, determining, by the centralized machine-learning model, an output label prediction certainty based on the model input data, determining an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model, and sending, over the network, a machine-learning model update to a second device in response to determining that the increase in the output label prediction certainty is greater than an output label prediction increase threshold.
-
公开(公告)号:US11669593B2
公开(公告)日:2023-06-06
申请号:US17205961
申请日:2021-03-18
Applicant: Geotab Inc.
CPC classification number: G06F18/40 , G06F18/2148 , G06F18/24 , G06V10/235 , G06V20/59 , G06V2201/02
Abstract: Systems and methods for training image processing models for vehicle data collection by image analysis are provided. An example method involves accessing an image of a field of interest in a vehicle captured by a camera in the vehicle, providing a user interface to, display the image, receive input that defines a region of interest in the image that is expected to convey vehicle information, and receive input that assigns a label to the region of interest that associates the region of interest with an image processing model that is to be trained to extract a type of vehicle information from the region of interest, and contributing the image, labelled with the region of interest and the label associating the region of interest to the image processing model, to a training data library to train the image processing model.
-
公开(公告)号:US20230144289A1
公开(公告)日:2023-05-11
申请号:US17971960
申请日:2022-10-24
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
CPC classification number: G07C5/008 , G06K9/6265 , G06K9/6257 , G06F13/28 , G06F2213/28
Abstract: An input/output (I/O) expansion adapter and a method by an I/O expansion adapter are provided. The method includes receiving raw I/O expansion data from an I/O expander coupled thereto, processing the raw I/O expansion into processed I/O expansion data, and sending the processed I/O expansion data to the telematics device.
-
公开(公告)号:US12284461B2
公开(公告)日:2025-04-22
申请号:US18420976
申请日:2024-01-24
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique , Willem Petersen
Abstract: A synchronized data set is generated from multiple asynchronous data sets. An interpolated data set is generated for each asynchronous data set, at a higher data rate than recorded data rates for the asynchronous data sets. The interpolated data for each data set is then sampled at a lower data rate which is common to all the interpolated data sets. The sampled data points are synchronized between the different data sets, such that the sampled data points represent a synchronized data set. Input telematic data can be reduced to inflection points in the telematic data, and interpolation and sampling of asynchronous data sets can be limited to threshold time periods around the inflection points.
-
公开(公告)号:US20240015265A1
公开(公告)日:2024-01-11
申请号:US18370050
申请日:2023-09-19
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
CPC classification number: H04N7/181 , G06V20/52 , G06V20/56 , G01C21/3614 , G01C21/3667 , G06F3/04842
Abstract: Detection models are distributed as needed to a select subset of image capture devices, based on geographic location and time of the image capture devices. Each image capture device which receives a model processes image data according to the model, and provides a notification of any detected instances of an event the model is trained to detect. Distribution and detection can be based on historical data or live data.
-
公开(公告)号:US20230057652A1
公开(公告)日:2023-02-23
申请号:US17890560
申请日:2022-08-18
Applicant: Geotab Inc.
Inventor: William John Ballantyne , Javed Siddique
Abstract: Detection models are distributed as needed to a select subset of image capture devices, based on geographic location and time of the image capture devices. Each image capture device which receives a model processes image data according to the model, and provides a notification of any detected instances of an event the model is trained to detect. Distribution and detection can be based on historical data or live data.
-
-
-
-
-
-
-
-
-