METHOD AND SYSTEM FOR DETECTING COMPLEX IMAGE-BASED ANOMALY EVENT

A method for detecting a complex image-based anomaly behavior is provided. The method includes the steps of: acquiring an RGB image and a depth image through a 2D camera and a depth camera, respectively; inputting the RGB image and depth image into a deep learning model to calculate a probability va...

Full description

Saved in:
Bibliographic Details
Main Authors YANG CHANG MO, KIM DONG CHIL
Format Patent
LanguageEnglish
Korean
Published 01.06.2023
Subjects
ALARM SYSTEMS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ORDER TELEGRAPHS
PHYSICS
SIGNALLING
SIGNALLING OR CALLING SYSTEMS
Online AccessGet full text

Cover

More Information
Summary:A method for detecting a complex image-based anomaly behavior is provided. The method includes the steps of: acquiring an RGB image and a depth image through a 2D camera and a depth camera, respectively; inputting the RGB image and depth image into a deep learning model to calculate a probability value for each abnormal behavior class; and outputting an abnormal behavior event based on the probability value for each abnormal behavior class. 복합 영상 기반 이상행위 탐지 방법이 제공된다. 상기 방법은 2D 카메라 및 깊이 카메라를 통해 각각 RGB 영상 및 깊이 영상을 획득하는 단계; 상기 RGB 영상 및 깊이 영상을 딥러닝 모델에 입력하여 이상행위 클래스별 확률값을 산출하는 단계; 및 상기 이상행위 클래스별 확률값을 기반으로 이상행위 이벤트를 출력하는 단계를 포함한다.
Bibliography:Application Number: KR20210164961