中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1522 records (took 0.033 seconds)

    LOCALIZATION AND MAPPING
    441.
    发明申请
    LOCALIZATION AND MAPPING 有权

    公开(公告)号：US20230123671A1

    公开(公告)日：2023-04-20

    申请号：US18069856

    申请日：2022-12-21

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Xiaobo WAN ,  Yueqiang DONG ,  Kang WANG ,  Xianpeng MENG

    IPC: G06T7/73

    Abstract: A method for localization and mapping is provided. The method includes: determining a first estimated pose of a current frame based on a matching result of scan data of the current frame and a first submap and a pose of the first submap, where the first submap includes scan data of a common-viewing-angle frame; adding the scan data of the current frame into the first submap; determining a plurality of candidate poses around the first estimated pose; matching the scan data of the current frame with the second submap based on each candidate pose and a pose of each second submap to determine a score of each candidate pose, and determining a second estimated pose of the current frame corresponding to the second submap; determining a third estimated pose from the at least one second estimated pose; updating the scan data based on the third estimated pose.

    ACCESS CONTROL METHOD AND APPARATUS FOR SHARED MEMORY, ELECTRONIC DEVICE AND AUTONOMOUS VEHICLE
    443.
    发明申请
    ACCESS CONTROL METHOD AND APPARATUS FOR SHARED MEMORY, ELECTRONIC DEVICE AND AUTONOMOUS VEHICLE 有权

    公开(公告)号：US20230120580A1

    公开(公告)日：2023-04-20

    申请号：US18068179

    申请日：2022-12-19

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Lei Dong

    IPC: G06F3/06

    Abstract: An access control method for a shared memory includes: creating and initializing the shared memory, the shared memory initialized including a plurality of region configuration objects, a plurality of block configuration objects and a plurality of data buffers; determining at least one target block according to a volume of data to be written corresponding to a first process; and writing the data by the first process into a target data buffer corresponding to the at least one target block, storing configuration information of the at least one target block to a region configuration object corresponding to a target region, and storing configuration information of the target data buffer to a block configuration object corresponding to the at least one target block.

    KEY POINT DETECTION METHOD, MODEL TRAINING METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM
    444.
    发明申请
    KEY POINT DETECTION METHOD, MODEL TRAINING METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM 有权

    公开(公告)号：US20230120054A1

    公开(公告)日：2023-04-20

    申请号：US17884968

    申请日：2022-08-10

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Qiansheng YANG

    IPC: G06V10/44 ,  G06T7/73 ,  G06T7/50 ,  G06V10/80 ,  G06V40/10

    Abstract: There is provided a key point detection method, a model training method, an electronic device and a storage medium, which relates to the field of artificial intelligence, and particularly to computer vision technologies and deep learning technologies, and may be particularly used for scenarios, such as behavior recognition, human-body special effect generation, entertainment game interaction, or the like. The key point detection method includes: extracting features of an image to obtain image features of the image; acquiring graph information of key points of a target in the image based on the image features, the graph information including a location relationship graph of the key points and location information of a central point in the key points; and acquiring location information of non-central points in the key points based on the location relationship graph of the key points and the location information of the central point.

    Operator registration method and apparatus for deep learning framework, device and storage medium
    446.
    发明授权
    Operator registration method and apparatus for deep learning framework, device and storage medium 有权

    公开(公告)号：US11625248B2

    公开(公告)日：2023-04-11

    申请号：US17572140

    申请日：2022-01-10

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Weihang Chen ,  Jiabin Yang ,  Hongyu Liu ,  Xiang Lan

    IPC: G06F9/44 ,  G06F9/38 ,  G06F9/30 ,  G06F9/54 ,  G06F8/41 ,  G06F8/51

    Abstract: The present disclosure provides an operator registration method and apparatus for a deep learning framework, a device and a storage medium, relates to the field of computer technologies, and specifically to the field of artificial intelligence such as deep learning. The operator registration method for a deep learning framework includes: receiving registration information provided by a user for registering operators with the deep learning framework, the registration information including: a custom calculation function, the custom calculation function being written in a manner irrelevant to the deep learning framework; building operator meta-information in the deep learning framework based on the registration information; and constructing a to-be-registered operator within the deep learning framework based on the operator meta-information, and registering the to-be-registered operator in a global operator table within the deep learning framework. The present disclosure can simplify an operator registration process.

    METHOD OF RECTIFYING TEXT IMAGE, TRAINING METHOD, ELECTRONIC DEVICE, AND MEDIUM
    447.
    发明申请
    METHOD OF RECTIFYING TEXT IMAGE, TRAINING METHOD, ELECTRONIC DEVICE, AND MEDIUM 有权

    公开(公告)号：US20230102804A1

    公开(公告)日：2023-03-30

    申请号：US18077026

    申请日：2022-12-07

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Xiyan LIU ,  Junjie CAI ,  Kai ZHONG ,  Jianzhong YANG ,  Deguo XIA ,  Tongbin ZHANG ,  Zhen LU

    IPC: G06V10/24 ,  G06V30/16 ,  G06V10/774 ,  G06V10/77

    Abstract: A method of rectifying a text image, a training method, an electronic device, and a medium, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, deep learning technology, intelligent transportation and high-precision maps. An exemplary implementation includes: performing, based on a gating strategy, a plurality of first layer-wise processing on a text image to be rectified, so as to obtain respective feature maps of a plurality of layer levels, wherein each of the feature maps includes a text structural feature related to the text image to be rectified, and the gating strategy is configured to increase an attention to the text structural feature; and performing a plurality of second layer-wise processing on the respective feature maps of the plurality of layer levels, so as to obtain a rectified text image corresponding to the text image to be rectified.

    DETERMINATION OF DRIVING DIRECTION
    449.
    发明申请
    DETERMINATION OF DRIVING DIRECTION 有权

    公开(公告)号：US20230097364A1

    公开(公告)日：2023-03-30

    申请号：US18076220

    申请日：2022-12-06

    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

    Inventor： Mei LI

    IPC: B60W30/18 ,  B60W30/12 ,  B60W50/00 ,  G06V20/56

    Abstract: A method for determining a driving direction is disclosed. The method includes: obtaining a driving route for a vehicle; determining a target intersection in the driving route, and obtaining border information about intersection range borders defining a range of the target intersection; predicting, based on the driving route and the border information corresponding to the target intersection, a first direction for the vehicle to enter the target intersection, a second direction for the vehicle to travel within the target intersection, and a third direction for the vehicle to leave the target intersection; and determining, based on the first direction, the second direction, and the third direction, a target driving direction for the vehicle to pass the target intersection.

Patent Agency Ranking