知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

116 records (took 0.029 seconds)

    Detecting Vehicles In Low Light Conditions
    61.
    发明申请
    Detecting Vehicles In Low Light Conditions 审中-公开

    公开(公告)号：US20180211121A1

    公开(公告)日：2018-07-26

    申请号：US15415733

    申请日：2017-01-25

    Applicant: Ford Global Technologies, LLC

    Inventor： Maryam Moosaei ,  Guy Hotson ,  Vidya Nariyambut Murali ,  Madeline J. Goh

    IPC: G06K9/00 ,  G06T5/20 ,  G06K9/46 ,  H04N9/77 ,  H04N7/18 ,  G01S17/93 ,  B60R1/00 ,  G05D1/00 ,  G05D1/02

    CPC classification number: G06K9/00825 ,  G01S17/023 ,  G01S17/936 ,  G06K9/6273 ,  H04N7/183

    Abstract: The present invention extends to methods, systems, and computer program products for detecting vehicles in low light conditions. Cameras are used to obtain RGB images of the environment around a vehicle. RGB images are converted to LAB images. The “A” channel is filtered to extract contours from LAB images. The contours are filtered based on their shapes/sizes to reduce false positives from contours unlikely to correspond to vehicles. A neural network classifies an object as a vehicle or non-vehicle based the contours. Accordingly, aspects provide reliable autonomous driving with lower cost sensors and improved aesthetics. Vehicles can be detected at night as well as in other low light conditions using their head lights and tail lights, enabling autonomous vehicles to better detect other vehicles in their environment. Vehicle detections can be facilitated using a combination of virtual data, deep learning, and computer vision.

    DE-BIASING DATASETS FOR MACHINE LEARNING
    66.
    发明公开
    DE-BIASING DATASETS FOR MACHINE LEARNING 审中-公开

    公开(公告)号：US20240046625A1

    公开(公告)日：2024-02-08

    申请号：US17817235

    申请日：2022-08-03

    Applicant: Ford Global Technologies, LLC

    Inventor： Nikita Jaipuria ,  Xianling Zhang ,  Katherine Stevo ,  Jinesh Jain ,  Vidya Nariyambut Murali ,  Meghana Laxmidhar Gaopande

    IPC: G06V10/778 ,  G06V10/77

    CPC classification number: G06V10/778 ,  G06V10/7715

    Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a dataset of images; extract feature data from the images; optimize a number of clusters into which the images are classified based on the feature data; for each cluster, optimize a number of subclusters into which the images in that cluster are classified; determine a metric indicating a bias of the dataset toward at least one of the clusters or subclusters based on the number of clusters, the numbers of subclusters, distances between the respective clusters, and distances between the respective subclusters; and after determining the metric, train a machine-learning program using a training set constructed from the clusters and the subclusters.

    Systems And Methods For Improved Training Data Acquisition
    67.
    发明公开
    Systems And Methods For Improved Training Data Acquisition 审中-公开

    公开(公告)号：US20230196740A1

    公开(公告)日：2023-06-22

    申请号：US17552913

    申请日：2021-12-16

    Applicant: Ford Global Technologies, LLC

    Inventor： Vidya Nariyambut Murali ,  Nikita Jaipuria ,  Xianling Zhang

    IPC: G06V10/774 ,  G06V20/70 ,  G06T7/00 ,  G06T7/11

    CPC classification number: G06V10/7747 ,  G06V20/70 ,  G06T7/0002 ,  G06T7/11 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: This disclosure describes systems and methods for improved training data acquisition. An example method may include sending, by a processor, an indication for a user to capture data relating to a first area of interest using a first mobile device. The example method may also include determining, by the processor, that first data captured by the first mobile device would fail to satisfy a quality requirement. The example method may also include causing, by the processor, to present an indication through the first mobile device to the user to adjust the first mobile device. The example method may also include determining, by the processor, that second data captured by the first mobile device after being adjusted would satisfy the quality requirement. The example method may also include receiving, by the processor, the second data from the first mobile device. The example method may also include receiving, by the processor, third data from a second mobile device, wherein the second data and third data are used to train a neural network associated with a vehicle.

    Fixation generation for machine learning
    69.
    发明授权
    Fixation generation for machine learning 有权

    公开(公告)号：US11087186B2

    公开(公告)日：2021-08-10

    申请号：US16657327

    申请日：2019-10-18

    Applicant: Ford Global Technologies, LLC

    Inventor： Madeline Jane Schrier ,  Vidya Nariyambut Murali

    IPC: G06K9/66 ,  G06K9/00 ,  G06T7/70 ,  G06K9/46 ,  G06T5/00 ,  G05D1/02 ,  G08G1/16

    Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

    Vehicle image generation
    70.
    发明授权
    Vehicle image generation 有权

    公开(公告)号：US11042758B2

    公开(公告)日：2021-06-22

    申请号：US16460066

    申请日：2019-07-02

    Applicant: Ford Global Technologies, LLC

    Inventor： Nikita Jaipuria ,  Gautham Sholingar ,  Vidya Nariyambut Murali ,  Rohan Bhasin ,  Akhil Perincherry

    IPC: G06K9/62 ,  G06K9/00 ,  G06N3/08 ,  G06T15/06 ,  G06T7/70

    Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate a synthetic image and corresponding ground truth and generate a plurality of domain adapted synthetic images by processing the synthetic image with a variational auto encoder-generative adversarial network (VAE-GAN), wherein the VAE-GAN is trained to adapt the synthetic image from a first domain to a second domain. The instructions can include further instructions to train a deep neural network (DNN) based on the domain adapted synthetic images and the corresponding ground truth and process images with the trained deep neural network to determine objects.

Patent Agency Ranking