一种用于液位图像标定的相机自检方法  

A Camera Self-check Method for Liquid Level Image Calibration

作　　者：陈科地 赵翠莲[1] CHEN Kedi;ZHAO Cuilian

机构地区：[1]上海大学机电工程与自动化学院

出　　处：《计量与测试技术》2024年第9期53-56,共4页Metrology & Measurement Technique

摘　　要：本文探讨了一种用于液位图像标定的相机自检方法。实验表明:该方法基于YOLOv4目标检测的SIFT特征点提取和FLANN匹配的位移测量算法,可实现更精确的目标位移测量,不仅能应对日常使用中相机可能出现的轻微扰动问题,而且能有效地发现相机扰动,确保液位检测的准确性和稳定性。This paper discusses a camera self-test method for liquid level image calibration.Experiments show that the proposed method,based on SIFT feature point extraction of YOLOv4 target detection and FLANN matching dis-placement measurement algorithm,can achieve more accurate target displacement measurement,which can not only deal with the slight disturbance that may occur in daily use of the camera,but also effectively detect the camera dis-turbance to ensure the accuracy and stability of liquid level detection.

关 键 词：液位图像 位移测量 相机自检 YOLO SIFT特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TH70[自动化与计算机技术—计算机科学与技术]