Machine vision-based curtain wall door and window airtight performance evaluation method and system

Abstract

The invention relates to the field of machine vision, in particular to a curtain wall door and window airtight performance evaluation method and system based on machine vision, and the method comprises the steps: obtaining a door and window image through a thermal imaging dual-spectrum camera; determining a plurality of air leakage points based on the temperature of the pixel point and the distance between the pixel point and the door and window edge; for each adjacent area corresponding to each air leakage point, searching pixel points influenced by the air leakage points in the adjacent areas; determining a three-dimensional point corresponding to each found pixel point based on the position and the temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptical conical surface; for each air leakage point, an elliptical conical surface corresponding to each adjacent area of the air leakage point is obtained, and the air leakage degree of the air leakage point is calculated according to the distance between the air leakage point and each elliptical conical surface; and evaluating the air tightness of the curtain wall door and window according to the air leakage degree of each air leakage point. The obtained door and window air tightness evaluation result is accurate, and the evaluation result is not influenced by a complex door and window structure.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a method and system for evaluating the airtight performance of curtain wall doors and windows based on machine vision. Background technique [0002] If the curtain wall doors and windows are not properly installed, it will lead to cold air leakage and hot air backflow in summer, and cold air backflow and heating leakage in winter, which will increase the system load of heating or cooling system and increase operating costs. This problem is referred to as a "building airtightness" defect. [0003] The existing method for evaluating the air tightness of doors and windows is to process the thermal imaging of curtain wall doors and windows based on a deep neural network, determine the cold area, and evaluate the air tightness of the doors and windows according to the area ratio of the cold area; this method is subjected to thermal imaging. The resolution of the equipment and other stru...

AI Technical Summary

Problems solved by technology

[0002] If the doors and windows of the curtain wall are not installed correctly, it will cause cold air leakage and hot air backflow in summer, and cold air backflow and heating air leakage in winter, which will increase the system load of heating or cooling systems and increase operating costs. This problem is called "building air tightness" defect

[0003] The existing method for evaluating the airtightness of doors and windows is to process the thermal imaging of curtain wall doors and windows based on a deep neural network, determine the cold area, and evaluate the airtightness of doors and windows according to the area ratio of the cold area; this method is thermally imaged The resolution of the equipment and other structures of the doors and windows are greatly affected, so the evaluation results of the airtightness of the doors and windows are inaccurate

Images