Single-shot adaptive fusion method and apparatus for robust multispectral object detection

Disclosed are a single-shot-based adaptive fusion method for robust object detection and a device thereof. The single-shot-based adaptive fusion method for robust object detection includes the steps of: (a) obtaining a first feature map and a second feature map from a first image and a second image,...

Full description

Saved in:
Bibliographic Details
Main Authors NAM HYUNG HO, ROH CHI WON, HWANG SOON MIN, KIM NAM IL, JO WON, KIM JI WON, CHOI YU KYUNG
Format Patent
LanguageEnglish
Korean
Published 15.09.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Disclosed are a single-shot-based adaptive fusion method for robust object detection and a device thereof. The single-shot-based adaptive fusion method for robust object detection includes the steps of: (a) obtaining a first feature map and a second feature map from a first image and a second image, respectively; (b) generating a fusion parameter by using a correlation analysis result of the first feature map and the second feature map; and (c) fusing other feature maps using the fusion parameter. 강인한 객체 검출을 위한 싱글샷 기반 적응적 융합 방법 및 그 장치가 개시된다. 강인한 객체 검출을 위한 싱글샷 기반 적응적 융합 방법은, (a) 제1 영상과 제2 영상으로부터 제1 특징맵과 제2 특징맵을 각각 획득하는 단계; (b) 상기 제1 특징맵과 상기 제2 특징맵의 상관 분석 결과를 이용하여 융합 파라미터를 생성하는 단계; 및 (c) 상기 융합 파라미터를 이용하여 다른 특징맵을 융합하는 단계를 포함한다.
Bibliography:Application Number: KR20200028451