METHOD AND APPARATUS WITH OBJECT TRACKING

    公开(公告)号:US20220383514A1

    公开(公告)日:2022-12-01

    申请号:US17528501

    申请日:2021-11-17

    Abstract: A processor-implemented method with object tracking includes: determining an initial template image based on an input bounding box and an input image; generating an initial feature map by extracting features from the initial template image; generating a transformed feature map by performing feature transformation adapted to objectness on the initial feature map; generating an objectness probability map and a bounding box map indicating bounding box information corresponding to each coordinate of the objectness probability map by performing objectness-based bounding box regression analysis on the transformed feature map; and determining a refined bounding box based on the objectness probability map and the bounding box map.

    METHOD AND APPARATUS WITH STATE ESTIMATION

    公开(公告)号:US20250166384A1

    公开(公告)日:2025-05-22

    申请号:US18939432

    申请日:2024-11-06

    Abstract: A method of estimating a state includes: predicting current state prediction data of a target object by using previous state estimation data of a previous image frame of an image sequence in which the target object is represented, the previous image frame previous to a current image frame; acquiring current target detection data of the target object for the current image frame of the image sequence; and determining current state estimation data of the target object of the current image frame by updating the current state prediction data by using the current target detection data and by using a detection reliability of the current target detection data.

    METHOD AND APPARATUS WITH AUTHENTICATION AND NEURAL NETWORK TRAINING

    公开(公告)号:US20210166071A1

    公开(公告)日:2021-06-03

    申请号:US16913205

    申请日:2020-06-26

    Abstract: A processor-implemented neural network method includes: determining, using a neural network, a feature vector based on a training image of a first class among a plurality of classes; determining, using the neural network, plural feature angles between the feature vector and class vectors of other classes among the plurality of classes; determining a margin based on a class angle between a first class vector of the first class and a second class vector of a second class, among the class vectors, and a feature angle between the feature vector and the first class vector; determining a loss value using a loss function including an angle with the margin applied to the feature angle and the plural feature angles; and training the neural network by updating, based on the loss value, either one or both of one or more parameters of the neural network and one or more of the class vectors.

Patent Agency Ranking