公开(公告)号：US12223737B2

公开(公告)日：2025-02-11

申请号：US17315554

申请日：2021-05-10

Applicant: Korea University Research and Business Foundation

Inventor： Joongheon Kim ,  Won Joon Yun ,  SooHyun Park

IPC: G06V20/58 ,  B60W60/00 ,  G06N3/08

Abstract: An object recognition method using queue-based model selection and optical flow in an autonomous driving environment includes preprocessing data through a dense flow in a matrix form by calculating an optical flow of images captured consecutively in time by a sensor for an autonomous vehicle, generating a confidence mask by generating a vectorized confidence threshold representing a probability that there is a moving object for each cell of the preprocessed matrix, determining whether there is a moving object on the images by mapping the images captured consecutively in time to the confidence mask, and selecting an object recognition model using a tradeoff constant between object recognition accuracy and queue stability in each time unit. Accordingly, it is possible to improve the performance of object recognition in an autonomous driving environment by applying the optical flow to the confidence threshold of the object recognition system.

公开(公告)号：US12225327B2

公开(公告)日：2025-02-11

申请号：US18139683

申请日：2023-04-26

Applicant: KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION ,  AJOU UNIVERSITY INDUSTRY—ACADEMIC COOPERATION FOUNDATION

Inventor： Joongheon Kim ,  Soyi Jung ,  Jae-Hyun Kim ,  Won Joon Yun ,  SooHyun Park

IPC: H04N7/18 ,  B64U10/00 ,  B64U101/20 ,  B64U101/31 ,  H04N23/661

Abstract: Provided is a surveillance system employing a plurality of unmanned aerial vehicles (UAVs), the surveillance system showing improved surveillance performance while optimizing common energy consumption for computing of all the UAVs and also providing a stable visual monitoring service using autonomous mobility of the plurality of UAVs regardless of movement of an object to be monitored and action uncertainty of an adjacent UAV.

公开(公告)号：US11915477B2

公开(公告)日：2024-02-27

申请号：US17720735

申请日：2022-04-14

Applicant: Korea University Research and Business Foundation

Inventor： Joongheon Kim ,  Yoo Jeong Ha ,  Minjae Yoo ,  SooHyun Park

IPC: G06V20/17 ,  B64C39/02 ,  G06V20/52 ,  G06N3/045 ,  B64U101/30

CPC classification number: G06V20/17 ,  B64C39/024 ,  G06N3/045 ,  G06V20/52 ,  B64U2101/30 ,  B64U2201/20

Abstract: Disclosed is a video processing system including multiple unmanned aerial vehicles (UAVs) configured to capture a video of a fire site, wherein each UAV has a control unit including an input layer and a first hidden layer (hidden layer 1) and a central server connected to the multiple UAVs by wireless communication, wherein the central server includes multiple hidden layers and an output layer. The video processing system performs a learning process to determine whether a fire has occurred using a feature map in which an original video is difficult to recognize and personal information is protected. Thus, it is possible to fundamentally prevent the exposure and infringement of personal information.