Fire door opening method of cable tunnel patrol robot based on YOLOv4 image recognition algorithm

This paper first introduces the position signal method, RFID tag identification method, mechanical arm door opening method of three kinds of robot fire door, compared and analyzed the applicable environment and shortcomings of these methods. In order to overcome the above shortcomings, YOLOv4 image...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) pp. 233 - 236
Main Authors Li, Chong, Li, Xueliang, Sun, Zongwei, Wang, Kenan, Yang, Yuechen, Guo, Rui, Liu, Piyu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2021
Subjects
Artificial intelligence
Automation
Cable tunnel patrol robot
Image recognition
Manipulators
Method of opening fire door
RFID tags
YOlOv4 image recognition algorithm
Online AccessGet full text

Cover

More Information
Summary:This paper first introduces the position signal method, RFID tag identification method, mechanical arm door opening method of three kinds of robot fire door, compared and analyzed the applicable environment and shortcomings of these methods. In order to overcome the above shortcomings, YOLOv4 image recognition algorithm technology was innovatively applied to the door opening method, and a method of robot opening fire door based on YOLOv4 image recognition algorithm was proposed, referred to as image recognition method for short. The test results show that the detection accuracy reaches 98%, which verifies the advantages of this method in the door opening method and can better meet the application requirements of the patrol robot in opening the fire door in the cable tunnel.
DOI:10.1109/AIEA53260.2021.00056