-
公开(公告)号：US12103530B2
公开(公告)日：2024-10-01
申请号：US16848957
申请日：2020-04-15
Applicant: Ford Global Technologies, LLC
Inventor： Gautham Sholingar , Sowndarya Sundar
IPC: B60W30/18 , B60W10/10 , B60W10/18 , B60W10/20 , G05D1/00 , G06F18/21 , G06F18/214 , G06N3/08 , G06V10/772 , G06V10/774 , G06V10/82 , G06V20/56 , G06V20/58
CPC classification number: B60W30/18036 , B60W10/10 , B60W10/18 , B60W10/20 , G05D1/0212 , G05D1/0231 , G06F18/214 , G06F18/217 , G06N3/08 , G06V10/772 , G06V10/7747 , G06V10/82 , G06V20/56 , G06V20/584 , B60W2420/403 , B60W2555/20
Abstract: A system, including a processor and a memory, the memory including instructions to be executed by the processor to receive one or more images from a vehicle, wherein a first deep neural network included in a computer in the vehicle has failed to determine an orientation of a first object in the one or more images. The instructions can include further instructions to generate a plurality of modified images with a few-shot image translator, wherein the modified images each include a modified object based on the first object. The instructions can include further instructions to re-train the deep neural network to determine the orientation of the first object based on the plurality of modified images and download the re-trained deep neural network to the vehicle.
-
公开(公告)号：US11772656B2
公开(公告)日：2023-10-03
申请号：US16923367
申请日：2020-07-08
Applicant: Ford Global Technologies, LLC
Inventor： Apurbaa Mallik , Kaushik Balakrishnan , Vijay Nagasamy , Praveen Narayanan , Sowndarya Sundar
CPC classification number: B60W40/02 , B60W60/005 , G06N20/00 , G06V10/751 , B60W2420/42 , B60W2555/20
Abstract: A system includes a computer including a processor and a memory, the memory storing instructions executable by the processor to generate a synthetic image by adjusting respective color values of one or more pixels of a reference image based on a specified meteorological optical range from a vehicle sensor to simulated fog, and input the synthetic image to a machine learning program to train the machine learning program to identify a meteorological optical range from the vehicle sensor to actual fog.
-
公开(公告)号：US20220234617A1
公开(公告)日：2022-07-28
申请号：US17158088
申请日：2021-01-26
Applicant: Ford Global Technologies, LLC
Inventor： Gautham Sholingar , Sowndarya Sundar , Jinesh Jain , Shreyasha Paudel
Abstract: A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to: process vehicle sensor data with a deep neural network to generate a prediction indicative of one or more objects based on the data and determine an object uncertainty corresponding to the prediction and when the object uncertainty is greater than an uncertainty threshold, segment the vehicle sensor data into a foreground portion and a background portion. Classify the foreground portion as including an unseen object class when a foreground uncertainty is greater than a foreground uncertainty threshold; classify the background portion as including unseen background when a background uncertainty is greater than a background uncertainty threshold; and transmit the data and a data classification to a server.
-
Patent Agency Ranking
公开(公告)号：US11745766B2
公开(公告)日：2023-09-05
申请号：US17158088
申请日：2021-01-26
Applicant: Ford Global Technologies, LLC
Inventor： Gautham Sholingar , Sowndarya Sundar , Jinesh Jain , Shreyasha Paudel
IPC: B60W40/00 , B60W60/00 , G06F16/28 , G06N3/04 , G06N3/08 , B60W30/095 , B60W30/09 , B60W40/06 , B60W50/00
CPC classification number: B60W60/0015 , B60W30/09 , B60W30/0956 , B60W40/06 , B60W50/0097 , G06F16/285 , G06N3/04 , G06N3/08 , B60W2420/42 , B60W2555/20
Abstract: A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to: process vehicle sensor data with a deep neural network to generate a prediction indicative of one or more objects based on the data and determine an object uncertainty corresponding to the prediction and when the object uncertainty is greater than an uncertainty threshold, segment the vehicle sensor data into a foreground portion and a background portion. Classify the foreground portion as including an unseen object class when a foreground uncertainty is greater than a foreground uncertainty threshold; classify the background portion as including unseen background when a background uncertainty is greater than a background uncertainty threshold; and transmit the data and a data classification to a server.
-
公开(公告)号：US20210323555A1
公开(公告)日：2021-10-21
申请号：US16848957
申请日：2020-04-15
Applicant: Ford Global Technologies, LLC
Inventor： Gautham Sholingar , Sowndarya Sundar
Abstract: A system, including a processor and a memory, the memory including instructions to be executed by the processor to receive one or more images from a vehicle, wherein a first deep neural network included in a computer in the vehicle has failed to determine an orientation of a first object in the one or more images. The instructions can include further instructions to generate a plurality of modified images with a few-shot image translator, wherein the modified images each include a modified object based on the first object. The instructions can include further instructions to re-train the deep neural network to determine the orientation of the first object based on the plurality of modified images and download the re-trained deep neural network to the vehicle.
-
公开(公告)号：US12054152B2
公开(公告)日：2024-08-06
申请号：US17146739
申请日：2021-01-12
Applicant: Ford Global Technologies, LLC
Inventor： Gurjeet Singh , Sowndarya Sundar
CPC classification number: B60W30/18036 , B60R1/002 , G06F18/214 , G06N3/08 , G06N20/20 , G06V20/56
Abstract: A computer is programmed to determine a training dataset that includes a plurality of images each including a first object and an object label, train a first machine learning program to identify first object parameters of the first objects in the plurality of images based on the object labels and a confidence level based on a standard deviation of a distribution of a plurality of identifications of the first object parameters, receive, from a second machine learning program, a plurality of second images each including a second object identified with a low confidence level, process the plurality of second images with the first machine learning program to identify the second object parameters with a corresponding second confidence level that is greater than a second confidence level, retrain the first machine learning program based on the identified second object parameters.
-
公开(公告)号：US20220219698A1
公开(公告)日：2022-07-14
申请号：US17146739
申请日：2021-01-12
Applicant: Ford Global Technologies, LLC
Inventor： Gurjeet Singh , Sowndarya Sundar
Abstract: A computer is programmed to determine a training dataset that includes a plurality of images each including a first object and an object label, train a first machine learning program to identify first object parameters of the first objects in the plurality of images based on the object labels and a confidence level based on a standard deviation of a distribution of a plurality of identifications of the first object parameters, receive, from a second machine learning program, a plurality of second images each including a second object identified with a low confidence level, process the plurality of second images with the first machine learning program to identify the second object parameters with a corresponding second confidence level that is greater than a second confidence level, retrain the first machine learning program based on the identified second object parameters.
-
公开(公告)号：US20220009498A1
公开(公告)日：2022-01-13
申请号：US16923367
申请日：2020-07-08
Applicant: Ford Global Technologies, LLC
Inventor： Apurbaa Mallik , Kaushik Balakrishnan , Vijay Nagasamy , Praveen Narayanan , Sowndarya Sundar
Abstract: A system includes a computer including a processor and a memory, the memory storing instructions executable by the processor to, generate a synthetic image by adjusting respective color values of one or more pixels of a reference image based on a specified meteorological optical range from a vehicle sensor to simulated fog, and input the synthetic image to a machine learning program to train the machine learning program to identify a meteorological optical range from the vehicle sensor to actual fog.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.023 seconds)
