利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

292 records (took 0.015 seconds)

    FEATURE EXTRACTION FOR OBJECT RE-IDENTIFICATION OR OBJECT CLASSIFICATION USING A COMPOSITE IMAGE
    2.
    发明公开
    FEATURE EXTRACTION FOR OBJECT RE-IDENTIFICATION OR OBJECT CLASSIFICATION USING A COMPOSITE IMAGE 审中-公开

    公开(公告)号：EP4485378A1

    公开(公告)日：2025-01-01

    申请号：EP23181628.1

    申请日：2023-06-27

    Applicant: Axis AB

    Inventor： Danielsson, Niclas ,  Nilsson, Amanda ,  Colliander, Christian ,  Laross, Sarah

    IPC: G06V10/82 ,  G06V10/80

    Abstract: A method for feature extraction of detected objects, comprising the steps of: receiving a plurality of images, each depicting an object detected by the object detecting application; concatenating the plurality of images into a composite image according to a grid pattern; feeding the composite image through a convolutional neural network (CNN) trained for feature extraction, wherein each convolutional layer of the CNN is configured to, while convolving input data to the convolutional layer using a convolutional filter: determine a currently convolved image of the plurality of images by determining a centre coordinate of a subset of the input data currently covered by the convolutional filter, and mapping the centre coordinate to the grid pattern; and selectively nullifying all weights of the convolutional filter that cover input data derived from any of the plurality of images not being the currently convolved image.

    FACE POSE ESTIMATION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
    3.
    发明公开
    FACE POSE ESTIMATION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：EP4471737A1

    公开(公告)日：2024-12-04

    申请号：EP22925596.3

    申请日：2022-07-26

    Applicant: Shenzhen Xumi Yuntu Space Technology Co., Ltd.

    Inventor： YANG, Zhanbo ,  HUANG, Zeyuan ,  QI, Xiaoting ,  JIANG, Zhao

    IPC: G06V40/16 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06F18/40 ,  G06T3/40 ,  G06T7/73

    Abstract: The present disclosure provides a face pose estimation method and apparatus, an electronic device, and a storage medium. The method includes: obtaining a target image containing face information, and inputting the target image into a pre-constructed pose estimation model; performing feature extraction on the target image by using a shallow densely connected layer to obtain a plurality of first feature maps containing shallow feature information; performing an information fusion operation on the plurality of first feature maps by using a deep feature multiplexing layer to obtain a second feature map, such that deep feature information is fused into the shallow feature information; and extracting face pose information in the second feature map by using an attention layer to obtain a third feature map containing the face pose information, performing prediction on the third feature map by using a classifier to obtain a face pose prediction result corresponding to the third feature map, and determining a face pose in the target image according to the prediction result. According to the present disclosure, key information of the face pose can be fully obtained, and accuracy of a face pose estimation result is improved.

    SEMANTIC SEGMENTATION OF AIRBORNE LIDAR DATA BY ARTIFICIAL INTELLIGENCE
    4.
    发明公开
    SEMANTIC SEGMENTATION OF AIRBORNE LIDAR DATA BY ARTIFICIAL INTELLIGENCE 审中-公开

    公开(公告)号：EP4471728A1

    公开(公告)日：2024-12-04

    申请号：EP24178352.1

    申请日：2024-05-28

    Applicant: Xeos Imaging Inc.

    Inventor： NGUYEN, Van Tho ,  ST-PIERRE, Tony ,  CLABAUT, Etienne

    IPC: G06V10/26 ,  G06V10/764 ,  G06V10/82 ,  G06V20/17 ,  G06V20/56 ,  G06V20/64 ,  G06V20/70 ,  G06V10/774 ,  G06V10/80

    Abstract: Systems and methods for performing semantic segmentation of LiDAR point clouds are provided. LiDAR point data are generated using aerial vehicles equipped with LiDAR transceivers. Tiles representing sampled areas of the point cloud are augmented by rotation or division, allowing for multiple semantic segmentation by a neural network, resulting in a smoother segmentation with an increased quality. To increase the quality further, buffers can be used around tiles, the scan angle of each LiDAR point can be used as input to the neural network, and points of an object can be segmented into different classes. The resulting segmentations are then aggregated to provide a final semantic segmentation, which can be used to create a digital terrain map, a building footprint or a vegetation map.

    LAWN MOWER CONTROL METHOD AND DEVICE, LAWN MOWER, AND STORAGE MEDIUM
    9.
    发明公开
    LAWN MOWER CONTROL METHOD AND DEVICE, LAWN MOWER, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：EP4462083A1

    公开(公告)日：2024-11-13

    申请号：EP23791184.7

    申请日：2023-04-17

    Applicant: Shenzhen Mammotion Innovation Co., Limited

    Inventor： YUAN, Li

    IPC: G01D18/00 ,  G01D21/02 ,  G06V10/80 ,  G06V20/10

    Abstract: A lawn mower control method and device, a lawn mower, and a storage medium. The method comprises: detecting operating data and sensing data of a plurality of operating sensors provided on a lawn mower, wherein the plurality of operating sensors comprise at least two different types of sensors (S 101); fusing the sensing data of the plurality of operating sensors to obtain environment data around the lawn mower (S102); determining, when it is detected that a fault occurs in any of the operating sensors, a fault type of a faulty sensor according to the operating data of the faulty sensor and the environment data around the lawn mower, wherein the faulty sensor is an operating sensor in which a fault occurs (S103); and controlling, if the fault type of the faulty sensor is a first fault type, the faulty sensor to stop operating, and a backup sensor corresponding to the faulty sensor to start operating (S104). A redundant and accurate sensing function can be provided to enable accurate recognition of the fault type and effective handling of a fault.

Patent Agency Ranking