公开(公告)号：US11663832B2

公开(公告)日：2023-05-30

申请号：US17551621

申请日：2021-12-15

Applicant: MICROMAX INTERNATIONAL CORP. ,  NATIONAL TAIWAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Kai-Lung Hua ,  Yung-Yao Chen ,  Sin-Ye Jhong ,  Yo-Cheng Chen ,  Ba-Lin Lin ,  Tzyy-Yzong Lin ,  Cheng-Shu Wen ,  Yen-Po Wang ,  Chun-Jung Chen ,  Tung-Hsin Yang ,  Wen-Hsiang Lu ,  Chyi-Jia Huang

IPC: G06V20/58 ,  G06T5/00 ,  G06V10/80 ,  G06V10/75 ,  G06V10/74 ,  G01S13/90 ,  H04N23/55

CPC classification number: G06V20/58 ,  G01S13/9027 ,  G01S13/9029 ,  G06T5/003 ,  G06V10/757 ,  G06V10/761 ,  G06V10/803 ,  H04N23/55 ,  G06T2207/10024 ,  G06T2207/10044 ,  G06T2207/30252 ,  G06T2210/12 ,  G06V2201/07

Abstract: A method for detecting objects and labeling the objects with distances in an image includes steps of: obtaining a thermal image from a thermal camera, an RGB image from an RGB camera, and radar information from an mmWave radar; adjusting the thermal image based on the RGB image to generate an adjusted thermal image, and generating a fused image based on the RGB image and the adjusted thermal image; generating a second fused image based on the fused image and the radar information; detecting objects in the images, and generating, based on the fused image, another fused image including bounding boxes marking the objects; and determining motion parameters of the objects.

公开(公告)号：US20220230443A1

公开(公告)日：2022-07-21

申请号：US17551621

申请日：2021-12-15

Applicant: MICROMAX INTERNATIONAL CORP. ,  NATIONAL TAIWAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： KAI-LUNG HUA ,  YUNG-YAO CHEN ,  SIN-YE JHONG ,  YO-CHENG CHEN ,  BA-LIN LIN ,  TZYY-YZONG LIN ,  CHENG-SHU WEN ,  YEN-PO WANG ,  CHUN-JUNG CHEN ,  TUNG-HSIN YANG ,  WEN-HSIANG LU ,  CHYI-JIA HUANG

IPC: G06V20/58 ,  G06T5/00 ,  G06V10/80 ,  G06V10/75 ,  G06V10/74 ,  G01S13/90 ,  H04N5/225

Abstract: A method for detecting objects and labeling the objects with distances in an image includes steps of: obtaining a thermal image from a thermal camera, an RGB image from an RGB camera, and radar information from an mmWave radar; adjusting the thermal image based on the RGB image to generate an adjusted thermal image, and generating a fused image based on the RGB image and the adjusted thermal image; generating a second fused image based on the fused image and the radar information; detecting objects in the images, and generating, based on the fused image, another fused image including bounding boxes marking the objects; and determining motion parameters of the objects.