KR20220049746A - System for determining thermal abnormalities on exterior walls of building using thermal image and real image and method thereof - Google Patents

Abstract

Disclosed are a system for determining thermal abnormalities on an external wall of a building using a thermal image and a real image and a method thereof. According to the present invention, the system for determining thermal abnormalities on the external wall of the building using the thermal image and the real image comprises: a real image camera module photographing the external wall of the building and generating the real image; a thermal image camera module photographing the external wall of the building and generating the thermal image; an external wall temperature distribution identification module using the real image generated by the real image camera module and the thermal image generated by the thermal image camera module, and identifying the external wall temperature distribution of the external wall of the building; and a thermal abnormalities extraction module using the external wall temperature distribution identified by the external wall temperature distribution identification module, and extracting the thermal abnormalities. According to the present invention, the system for determining thermal abnormalities on the external wall of the building using the thermal image and the real image and the method thereof are able to be configured to classify areas of the external wall of the building and identify the temperature distribution by using the real image and the thermal image, and precisely find the thermal abnormalities despite the existence of various components on the external wall of the building, such as windows, doors, vehicles, and outdoor units.

Description

SYSTEM FOR DETERMINING THERMAL ABNORMALITIES ON EXTERIOR WALLS OF BUILDING USING THERMAL IMAGE AND REAL IMAGE AND METHOD THEREOF

The present invention relates to a system and method for determining a thermal anomaly of a building, and more particularly, to a system and a method for determining a thermal anomaly of an exterior wall of a building using a thermal image and a real image.

In the case of poor insulation or heat loss on the outer wall of the building, energy loss and deterioration of occupancy comfort are caused through the thermal abnormality.

Although thermal imaging cameras are mainly used to find such thermal anomalies, it is not easy to find an exact thermal anomaly because various components such as windows, doors, vehicles, and outdoor units are arranged on the exterior wall of the building.

Since these components have different temperature distributions even in the same environment, it is sometimes judged that a thermal abnormality occurs in a non-thermal abnormal region.

Accordingly, there is a need for a method capable of finding an accurate thermal anomaly through thermal imaging.

Laid-Open Patent Publication No. 10-2020-0101727 Registered Patent Publication No. 10-1238982

SUMMARY OF THE INVENTION It is an object of the present invention to provide a system for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image.

Another object of the present invention is to provide a method for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image.

According to an aspect of the present invention, a system for determining a portion of a thermal abnormality on an exterior wall of a building using a thermal image and a real image includes: a real image camera module for generating a real image by photographing the exterior wall of the building; a thermal imaging camera module for generating a thermal image by photographing the exterior wall of the building; It may be configured to include an exterior wall temperature distribution identification module configured to determine an exterior wall temperature distribution of the exterior wall of the building using a real image generated by the real image camera module and a thermal image generated by the thermal imaging camera module.

Here, it may be configured to further include a thermal abnormality region extraction module for extracting a thermal abnormality region using the external wall temperature distribution identified by the external wall temperature distribution identification module.

According to the above-described object of the present invention, a method for determining a portion of a thermal abnormality of an exterior wall of a building using a thermal image and a real image includes: generating a real image by a real image camera module photographing the exterior wall of the building; generating, by a thermal imaging camera module, a thermal image by photographing the exterior wall of the building; The external wall temperature distribution identification module may be configured to include the step of acquiring the external wall temperature distribution of the exterior wall of the building using the real image generated by the real image camera module and the thermal image generated by the thermal imaging camera module. .

Here, the thermal anomaly extraction module may be configured to further include the step of extracting the thermal anomaly by using the outer wall temperature distribution identified by the outer wall temperature distribution determining module.

According to the system and method for determining the thermal abnormality of the outer wall of a building using the above-described thermal image and real image, it is configured to identify the temperature distribution by dividing the area of the outer wall of the building using the real image and the thermal image, thereby In spite of the existence of various components such as , doors, vehicles, outdoor units, etc., there is an effect of accurately detecting thermal abnormalities.

1 is a schematic diagram of a thermal abnormality determination process of an exterior wall of a building according to the present invention.
2 is a block diagram of a system for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image according to an embodiment of the present invention.
3 is an exemplary diagram of a result of classification of a real image according to an embodiment of the present invention.
4 is a graph illustrating a temperature distribution of a thermal image and setting a critical temperature according to an embodiment of the present invention.
5 is an exemplary view of an image obtained by extracting a thermal abnormality portion of an exterior wall of a building according to an embodiment of the present invention.
6 is a flowchart of a method for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image according to an embodiment of the present invention.

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and will be described in detail in the detailed content for carrying out the invention. However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing each figure, like reference numerals have been used for like elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but it is understood that other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a schematic diagram of a thermal abnormality determination process of an exterior wall of a building according to the present invention.

Referring to FIG. 1 , first, a real image and a thermal image are acquired for the same outer wall of a building. In the real image, each area is divided by a wall, a window, other objects covering the exterior wall of the building, and the background. It is configured to grasp the temperature distribution by the thermal image for the area divided by the wall in the real image, and to extract the defective thermal abnormality from the temperature distribution of the wall area.

2 is a block diagram of a system for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image according to an embodiment of the present invention. And FIG. 3 is an exemplary diagram of a result of classification of a real image according to an embodiment of the present invention, FIG. 4 is a graph relating to a temperature distribution and a critical temperature setting of a thermal image according to an embodiment of the present invention, and FIG. 5 is a diagram of the present invention It is an exemplary view of an image obtained by extracting a thermal abnormality portion of an outer wall of a building according to an embodiment of the present invention.

Referring to FIG. 2 , the system 100 for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image according to an embodiment of the present invention includes a real image camera module 101, a thermal image camera module 102, and a real image. Image database 103, region classification module 104, region mask application module 105, scaling module 106, external wall temperature distribution identification module 107, critical temperature automatic setting module 108, thermal abnormality region extraction module (109).

Hereinafter, a detailed configuration will be described.

The real image camera module 101 may be configured to generate a real image by photographing an exterior wall of a building.

The thermal imaging camera module 102 may be configured to generate a thermal image by photographing an exterior wall of a building.

The real image database 103 may be configured such that a real image of the exterior wall of the building is stored in advance.

The region classification module 104 may be configured to separate the region of the real image generated by the real image camera module 101 into a wall, a window, other objects covering the exterior wall of the building, and a background, respectively.

Specifically, the region classification module 104 may be configured to first perform learning for region classification with reference to a real image previously stored in the real image database 103 using a convolutional neural network model.

And the area division module 104 separates the area of the building exterior from the real image generated by the real image camera module 102 into a wall, a window, other objects (vehicles, outdoor units, etc.) covering the exterior wall of the building, and the background, respectively. can be

The region mask assignment module 105 may be configured to assign and display a region mask including index information to each region divided by the region classification module 104 . The index information may be set to a wall, a window, other objects covering the exterior wall of a building, and a background, respectively. FIG. 3 shows an image semantically divided into such an exterior wall of a building, in which a green area is a wall, an orange area is a window, and a yellow area is other areas.

The scaling module 106 applies an area interpolation algorithm to adjust the size of the real image generated by the real image camera module 101 to be the same as the size of the thermal image generated by the thermal image camera module 102 to contrast each other can be

In general, since the size of the thermal image is generated smaller than that of the real image, the scaling module 106 applies an area interpolation algorithm to minimize the error when the real image is reduced to the size of the thermal image.

The external wall temperature distribution determining module 107 may be configured to grasp the temperature distribution of the area divided by the wall by the area mask in the contrast result thermal image of the scaling module 106 .

The external wall temperature distribution identification module 107 may be configured to remove the background temperature distribution from the thermal image and determine the temperature distribution of the exterior wall of the building.

The external wall temperature distribution identification module 107 may be configured to generate a temperature histogram from the thermal image, and apply a kernel density estimation algorithm to the generated temperature histogram to estimate the temperature distribution.

The automatic threshold temperature setting module 108 may be configured to automatically set a threshold temperature for classifying a normal region and an abnormal region by analyzing the temperature distribution detected by the external wall temperature distribution identification module 107 .

The threshold temperature automatic setting module 108 may be configured to include a maximum limit calculation unit 108a, a maximum point selection unit 108b and a defect threshold temperature selection unit 108c. Hereinafter, a detailed configuration will be described.

으로부터 극대값 한계

를 계산하도록 구성될 수 있다.First, the maximum value limit calculation unit 108a calculates the maximum value of the temperature distribution estimated by the outer wall temperature distribution determining module 107 according to Equation 1 below.

from the maximum limit

can be configured to calculate

는 0.05로 설정될 수 있다.here,

may be set to 0.05.

보다 큰 온도 분포의 극대값 중에서 온도 분포의 빈도가 가장 큰 두 개의 극대점

을 선정하도록 구성될 수 있다.And the maximum point selection unit 108b is the maximum value limit

The two local maxima with the highest frequency of the temperature distribution among the local maxima of the larger temperature distribution.

may be configured to select

로 선정하도록 구성될 수 있다.And, the defect critical temperature selection unit 108c is a defect critical temperature for determining a thermal abnormality at a temperature having the lowest frequency of temperature distribution between two maximum points according to Equation 2 below.

It can be configured to select

The thermal anomaly extraction module 109 may be configured to extract a thermal anomaly from the wall using the threshold temperature automatically set in the automatic threshold temperature setting module 109 .

보다 큰 극대점이 하나만 존재하는 경우 열화상에 열적 이상 부위가 존재하지 않는 것으로 판단하며, 극대값 한계

보다 큰 극대점이 둘 이상 존재하는 경우 하자 임계 온도

이상 극대점

이하의 온도 분포를 갖는 부위를 열적 이상 부위로 판단하도록 구성될 수 있다.Specifically, the thermal anomaly extraction module 109 has a maximum limit

If there is only one larger maximal point, it is judged that there is no thermal anomaly in the thermal image, and the limit of the maximal value is

Fault critical temperature when two or more larger maxima exist

ideal maximum

It may be configured to determine a region having the following temperature distribution as a thermal abnormal region.

FIG. 5 shows that a defect region is found by extracting two maximum points from each of the wall region 1 and the wall region 2 in the real image and the thermal image.

6 is a flowchart of a method for determining a thermal abnormality of an exterior wall of a building using a thermal image and a real image according to an embodiment of the present invention.

Referring to FIG. 6 , the real image camera module 101 creates a real image by photographing the exterior wall of the building ( S101 ).

Next, the thermal imaging camera module 102 generates a thermal image by photographing the exterior wall of the building ( S102 ).

Next, the external wall temperature distribution identification module 107 uses the real image generated by the real image camera module 101 and the thermal image generated by the thermal imaging camera module 102 to determine the external wall temperature distribution of the building exterior wall do (S103).

Next, the thermal anomaly extraction module 109 extracts a thermal anomaly using the outer wall temperature distribution identified by the outer wall temperature distribution determining module 107 ( S104 ).

Although described with reference to the above embodiments, those skilled in the art can understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the following claims. There will be.

101: visual camera module
102: thermal imaging camera module
103: real image database
104: zone division module
105: region mask grant module
106: scaling module
107: external wall temperature distribution identification module
108: threshold temperature automatic setting module
109: thermal anomaly extraction module

Claims (4)

a real image camera module for generating a real image by photographing an exterior wall of a building;
a thermal imaging camera module for generating a thermal image by photographing the exterior wall of the building;
Thermal images and real images comprising an exterior wall temperature distribution identification module that grasps the exterior wall temperature distribution of the exterior wall of the building using the real image generated by the real image camera module and the thermal image generated by the thermal imaging camera module A system for judging the thermal abnormality of the exterior wall of a building. According to claim 1,
Thermal anomaly part of the exterior wall of a building using a thermal image and a real image, characterized in that it further comprises a thermal abnormality region extraction module for extracting a thermal abnormality region using the external wall temperature distribution grasped by the external wall temperature distribution identification module judgment system. generating, by a real image camera module, a real image by photographing an exterior wall of the building;
generating, by a thermal imaging camera module, a thermal image by photographing the exterior wall of the building;
Thermal image and real, comprising the step of determining, by an external wall temperature distribution identification module, the external wall temperature distribution of the exterior wall of the building using the real image generated by the real image camera module and the thermal image generated by the thermal imaging camera module A method for determining thermal anomalies of exterior walls of buildings using burns. 4. The method of claim 3,
Thermal anomaly of a building exterior wall using a thermal image and a real image, characterized in that the thermal anomaly extraction module further comprises the step of extracting the thermal anomaly using the external wall temperature distribution identified by the external wall temperature distribution identification module How to determine an abnormal area.

Images