Title:
EMBEDDED IMAGE RECOGNITION AND INTEGRATED SAFETY MANAGEMENT PLATFORM COMPRISING ARTIFICIAL INTELLIGENCE-BASED IMAGE RECOGNITION SYSTEM
Document Type and Number:
WIPO Patent Application WO/2024/101726
Kind Code:
A1
Abstract:
The present invention relates to an embedded image recognition and integrated safety management platform comprising an artificial intelligence-based image recognition system. More specifically, the platform comprises: an image data reception unit that receives captured image data of the surroundings of a construction or industrial site from a camera module; an image recognition system including a CNN-based object recognition unit that recognizes a human object from the captured image data received from the image data reception unit and detects the recognized human object by boxing same in correspondence to data of the recognized human object, and an event information generation unit that generates a warning light or a warning alarm when the human object detected by the CNN-based object recognition unit is exposed to a dangerous situation and a preset danger radius including the surroundings of heavy equipment; and an AI image recognition platform including a false detection/missed detection classification unit that receives the event information detected by the CNN-based object recognition unit and classifies the event information into correct detection, false detection, or missed detection, a retraining unit for retraining the false detection or missed detection classification, received from the false detection/missed detection classification unit, in real time through You Only Look Once (YOLO), which is a deep learning-based object recognition training algorithm, a training model update unit that uploads a retraining data set, generated by the retraining unit, to the CNN-based object recognition unit online in real time, and an LTE communication unit for communication between the image recognition system and an external device including an external server or a manager terminal.
Inventors:
KANG IL HYOUNG (KR)
CHOI PYUNG HO (KR)
KIM DO KEUN (KR)
ROH DONG WON (KR)
RYU JAE GON (KR)
CHANG YONG JUN (KR)
LEE JOUNG WOOK (KR)
CHOI PYUNG HO (KR)
KIM DO KEUN (KR)
ROH DONG WON (KR)
RYU JAE GON (KR)
CHANG YONG JUN (KR)
LEE JOUNG WOOK (KR)
Application Number:
PCT/KR2023/016700
Publication Date:
May 16, 2024
Filing Date:
October 26, 2023
Export Citation:
Assignee:
YOUNGSHINE CO LTD (KR)
KYUNGWOO SYSTECH INC (KR)
KYUNGWOO SYSTECH INC (KR)
International Classes:
G06Q50/10; G06Q50/08; G06T3/40; G06T7/292; G06V20/52; G08B13/196; G08B21/02; H04N7/18
Attorney, Agent or Firm:
LEE, Sun Kuk (KR)
Download PDF: