中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

82 records (took 0.022 seconds)

    MULTI-TASK PANOPTIC DRIVING PERCEPTION METHOD AND SYSTEM BASED ON IMPROVED YOU ONLY LOOK ONCE VERSION 5 (YOLOv5)
    31.
    发明申请
    MULTI-TASK PANOPTIC DRIVING PERCEPTION METHOD AND SYSTEM BASED ON IMPROVED YOU ONLY LOOK ONCE VERSION 5 (YOLOv5) 有权

    公开(公告)号：US20250005914A1

    公开(公告)日：2025-01-02

    申请号：US18711367

    申请日：2023-04-21

    Applicant: NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Yong QI ,  Xin ZENG

    IPC: G06V10/80 ,  G06V10/77 ,  G06V10/82 ,  G06V20/54 ,  G06V20/56

    Abstract: The present disclosure provides a multi-task panoptic driving perception method and system based on improved You Only Look Once version 5 (YOLOv5). The method in the present disclosure includes: performing image preprocessing on an image in a dataset to obtain an input image; extracting a feature of the input image by using a backbone network of improved YOLOv5, to obtain a feature map, where the backbone network is obtained by replacing a C3 module in a backbone network of YOLOv5 with an inverted residual bottleneck module; inputting the feature map into a neck network to obtain a feature map, and fusing the obtained feature map and the feature map obtained by the backbone network; inputting the fused feature map into a detection head to perform traffic target detection; and inputting the feature map of the neck network into a branch network to perform lane line detection and drivable area segmentation.

    DOMAIN ADAPTATION METHOD AND SYSTEM FOR GESTURE RECOGNITION
    32.
    发明公开
    DOMAIN ADAPTATION METHOD AND SYSTEM FOR GESTURE RECOGNITION 审中-公开

    公开(公告)号：US20240168554A1

    公开(公告)日：2024-05-23

    申请号：US18515592

    申请日：2023-11-21

    Applicant: Nanjing University of Science and Technology

    Inventor： Wentao WEI ,  Linyan REN ,  Bowen ZHOU

    IPC: G06F3/01 ,  G06N3/08

    CPC classification number: G06F3/015 ,  G06F3/017 ,  G06N3/08

    Abstract: An objective of the present disclosure is to provide a domain adaptation method and system for gesture recognition, which relates to the field of gesture recognition technologies. The domain adaptation method for gesture recognition includes: obtaining a to-be-recognized target domain surface electromyography signal of a user; separately inputting the to-be-recognized target domain surface electromyography signal into multiple target domain gesture recognition models, to obtain target domain gesture recognition results under multiple source-specific views, where source domains of training data used by different target domain gesture recognition models are different; and determining a gesture category of the to-be-recognized target domain surface electromyography signal according to the gesture recognition results under multiple source-specific views and a weight under each source-specific view.

    THREE-DIMENSIONAL TOWERED CHECKERBOARD FOR MULTI-SENSOR CALIBRATION
    34.
    发明公开
    THREE-DIMENSIONAL TOWERED CHECKERBOARD FOR MULTI-SENSOR CALIBRATION 审中-公开

    公开(公告)号：US20240134024A1

    公开(公告)日：2024-04-25

    申请号：US18403731

    申请日：2024-01-04

    Applicant: NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Mingwu REN ,  Dexin REN

    IPC: G01S7/497 ,  G01S17/86 ,  G06T7/33 ,  G06T7/80

    CPC classification number: G01S7/497 ,  G01S17/86 ,  G06T7/33 ,  G06T7/80 ,  G06T2207/10028 ,  G06T2207/20164 ,  G06T2207/30244

    Abstract: The disclosure is a three-dimensional towered checkerboard for multi-sensor calibration, and a LiDAR and camera joint calibration method based on the checkerboard. The joint calibration method includes: establishing a modeling coordinate system taking the three-dimensional towered checkerboard as a basis, and generating a point cloud of the three-dimensional towered checkerboard; denoising a three-dimensional point cloud obtained by LiDAR, and obtaining an actual point cloud of the three-dimensional towered checkerboard under a LiDAR coordinate system; determining a transformation relationship between the LiDAR coordinate system and the modeling coordinate system; generating a corner point set of two-dimensional checkerboards under the modeling coordinate system in sequence according to actual positions of corners of the two-dimensional checkerboards, and transforming into the LiDAR coordinate system; obtaining a corner point set of the two-dimensional checkerboards on a photo; and calculating a transformation relationship between the camera coordinate system and the LiDAR coordinate system.

    A THREE-DIMENSIONAL MEASUREMENT METHOD BASED ON END-TO-END DEEP LEARNING FOR SPECKLE PROJECTION
    37.
    发明公开
    A THREE-DIMENSIONAL MEASUREMENT METHOD BASED ON END-TO-END DEEP LEARNING FOR SPECKLE PROJECTION 审中-公开

    公开(公告)号：US20240020866A1

    公开(公告)日：2024-01-18

    申请号：US18025815

    申请日：2021-08-18

    Applicant: Nanjing University of Science and Technology

    Inventor： Chao Zuo ,  Qian Chen ,  Shijie Feng ,  Jiasong Sun ,  Yuzhen Zhang ,  Guohua Gu

    IPC: G06T7/593 ,  G06T3/40 ,  G06T7/194 ,  G06V10/44

    CPC classification number: G06T7/593 ,  G06T3/4007 ,  G06T7/194 ,  G06V10/44 ,  G06T2207/20228

    Abstract: The invention discloses a three-dimensional (3D) measurement method based on end-to-end deep learning for speckle projection. First, the speckle pattern was projected by the projector and collected simultaneously by the stereo camera. The speckle images after stereo rectification are fed into the stereo matching network. A feature extraction sub-network based on shared weights processes the speckle images to obtain a series of low-resolution 3D feature tensors, The feature tensor is fed into the saliency object detection sub-network to detect foreground information in the speckle images, producing a full-resolution valid mask map. A 4D matching cost volume is generated using the feature tensor of both views based on the candidate disparity range, filtered by a series of 3D convolutional layers to achieve cost aggregation, so that the initial disparity map is obtained by disparity regression. The final disparity map is obtained by combining the mask map and the initial disparity map to achieve a single-frame, robust, and absolute 3D shape measurement. The invention achieves a single-frame, robust, and absolute 3D shape measurement by projecting a single speckle pattern.

    Weakly supervised video activity detection method and system based on iterative learning
    38.
    发明授权
    Weakly supervised video activity detection method and system based on iterative learning 有权

    公开(公告)号：US11721130B2

    公开(公告)日：2023-08-08

    申请号：US17425653

    申请日：2020-09-16

    Applicant: Nanjing University of Science and Technology

    Inventor： Yan Song ,  Rong Zou ,  Xiangbo Shu

    IPC: G06V40/20 ,  G06V10/82 ,  G06V10/40

    CPC classification number: G06V40/23 ,  G06V10/40 ,  G06V10/82

    Abstract: The present disclosure relates to a weakly supervised video activity detection method and system based on iterative learning. The method includes: extracting spatial-temporal features of a video that contains actions; constructing a neural network model group; training a first neural network model according to the class label of the video, a class activation sequence output by the first neural network model, and a video feature output by the first neural network model; training the next neural network model according to the class label of the video, a pseudo temporal label output by the current neural network model, a class activation sequence output by the next neural network model, and a video feature output by the next neural network model; and performing action detection on the test video according to the neural network model corresponding to the highest detection accuracy value.

Patent Agency Ranking