Urban area building energy-saving reconstruction evaluation method based on thermal imaging technology

Abstract

The invention discloses an urban area building energy-saving reconstruction evaluation method based on a thermal imaging technology, and belongs to the field of building energy management, and the method comprises the steps: determining a target research region in a city, obtaining a high-altitude top-view image of the target research region, carrying out the building contour recognition of the high-altitude top-view image, and obtaining a building contour recognition result; positioning the buildings in the target research area; a high-altitude infrared image of the target research area is obtained through infrared imaging of the unmanned aerial vehicle, the activeness of energy consumption of the buildings in the target research area is analyzed based on the recognized building contours and the positioning coordinates of the corresponding buildings, and the target buildings subjected to energy-saving transformation are screened; and acquiring a building infrared image of the target building, acquiring pixel temperature data on the building infrared image, calculating a current heat loss defect coefficient of the target building, and evaluating whether the target building needs to be subjected to energy-saving transformation or not. According to the invention, heat loss evaluation of buildings in a large area in a city can be realized, and a complete evaluation system is established for the early stage and later stage of building energy-saving reconstruction.

Description

Technical Field

[0001] The present invention relates to the field of building energy management, and in particular to an urban area building energy-saving reconstruction assessment method based on thermal imaging technology. Background Art

[0002] As society pays increasing attention to energy conservation, emission reduction, and sustainable development, the assessment and optimization of building energy efficiency has become an important issue in the construction industry. As a non-contact, real-time, and intuitive detection tool, online infrared thermal imagers play an indispensable role in building energy efficiency assessment and energy-saving renovation. In existing technologies, infrared thermal imagers can only be used to evaluate the energy consumption of a single building. They are unable to cope with and implement energy-saving renovation assessments for building complexes in large areas. At the same time, they are unable to scientifically screen target buildings within a building complex. Generally, they are selected subjectively by humans, which results in a waste of energy-saving renovation resources for some buildings with inactive energy consumption. In addition, the assessment of heat loss in buildings is easily affected by weather and ambient temperature, resulting in inaccurate heat loss assessments. Summary of the Invention

[0003] In response to the above-mentioned deficiencies in the prior art, the present invention provides an urban area building energy-saving renovation assessment method based on thermal imaging technology, which accurately identifies and locates target buildings in a large area, thereby achieving accurate energy-saving renovation assessment of buildings in the target study area.

[0004] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0005] A method for evaluating energy-saving renovation of urban buildings based on thermal imaging technology is provided, which comprises the following steps:

[0006] S1: Identify the target study area in the city, use drones to obtain aerial aerial images of the target study area, identify building outlines from the aerial aerial images, and locate buildings within the target study area;

[0007] S2: Use UAV infrared imaging to obtain high-altitude infrared images of the target study area. Based on the identified building outlines and the corresponding building location coordinates, analyze the energy consumption activity of buildings in the target study area and select target buildings for energy-saving renovation assessment;

[0008] S3: Collect infrared images of the target building, obtain pixel temperature data on the infrared images, calculate the current heat loss defect coefficient of the target building, and evaluate whether the target building needs energy-saving renovation.

[0009] Furthermore, it also includes:

[0010] After the target building has undergone energy-saving renovation, the renovation benefit coefficient is calculated. The size of the renovation benefit coefficient is used to evaluate the effect of the energy-saving renovation. The larger the renovation benefit coefficient, the better the effect of the energy-saving renovation. Otherwise, the effect of the energy-saving renovation is worse, and the energy-saving renovation method needs to be modified.

[0011]

[0012] Among them, s is the area number of energy-saving transformation, S is the number of areas of energy-saving transformation, are the thermal resistance values of the areas before and after energy-saving transformation, A s is the area of the region, ΔHDD is the difference in heating degree days, P′ is the energy price coefficient, ω s It is the regional weight coefficient, which is determined by the ratio of the area of the region to the total building area.

[0013] Furthermore, the method of identifying building outlines in the high-altitude bird's-eye view image and locating buildings in the target research area in step S1 specifically includes:

[0014] S11: grayscale processing is performed on the high-altitude bird's-eye view image, and a difference threshold Δh0 of the pixel grayscale values between the roof part and the non-roof part of the building in the target area is set. Based on the difference threshold Δh0, an objective function for screening building boundary points is constructed to screen out a set A of building boundary points;

[0015]

[0016] Among them, a n is the nth building boundary point, n is the number of building boundary points, (x n ,y n ) is the pixel coordinate of the building boundary point, i and v are any two pixels, (x i ,y i ) is the pixel coordinate of pixel i, (x v ,y v ) is the pixel coordinate of pixel v, h i 、h n are the grayscale values of two pixels respectively, and d0 is the building boundary width threshold based on the image;

[0017] S12: Split the building boundary points in the building boundary point set A to form several sub-building boundary point sets. The objective function of the building boundary point splitting is:

[0018]

[0019] Among them, a m ,a eare the boundary point sets of any two sub-buildings split out, m and e are the numbers of the boundary point sets of any two sub-buildings, are the sub-building boundary point sets a m The coordinates of two adjacent pixels in the image, c and d are the boundary points of the sub-building set a m The numbers of two adjacent pixels in , are the grayscale values of pixels c and d respectively, are the sub-building boundary point sets a e The coordinates of two adjacent pixels in the image, f and g are the sub-building boundary point set a e The numbers of two adjacent pixels in , are the grayscale values of pixels f and g, respectively, and a c 、a f are the sub-building boundary point sets a m , sub-building boundary point set a e The two pixels with the closest distance between them, α is the boundary segmentation coefficient;

[0020] S13: based on the number of building boundary points in the split sub-building boundary point sets, delete the sub-building boundary point sets whose number of building boundary points is less than a set threshold, and connect the number of building boundary points in the remaining sub-building boundary point sets to form the building outline within the target research area;

[0021] S14: Calculate the location coordinates of buildings in the target study area based on the coordinates of the building boundary points on the building outline

[0022]

[0023] Where j is the number of the building boundary point on the building outline, J is the number of building boundary points on the building outline, (x j ,y j ) is the pixel coordinate of building boundary point j.

[0024] Furthermore, step S2 specifically includes:

[0025] S21: Selecting a period of time at night when the ambient temperature is stable as an image acquisition period, using drone infrared imaging to acquire high-altitude infrared images of the target research area during the image acquisition period, and processing the high-altitude infrared images to align the high-altitude infrared images with the high-altitude overhead images;

[0026] S22: grayscale the aligned high-altitude infrared images to obtain a grayscale image set, and move the building outlines in the high-altitude overhead image to the grayscale image;

[0027] S23: Calculate the activity coefficient F of building energy consumption based on the change of pixel grayscale values within the building outline in the grayscale image during the image acquisition cycle k ;

[0028]

[0029] Where k is the number of the building outline in the target study area, F k is the activity coefficient of the building corresponding to the k-th building outline in the target study area, q is the number of times high-altitude infrared images are collected during the image acquisition cycle, is the average grayscale value of the pixels within the building outline in the high-altitude infrared image collected for the qth time, h0′ is the threshold value representing the excessive heat loss of the building corresponding to the building outline, Q is the number of high-altitude infrared images collected during the image acquisition cycle, p is the number of times the excessive heat loss of the building is represented during the image acquisition cycle, β1 and β2 are the weights of the influence of the frequency and degree of excessive heat loss of the building on the activity coefficient during the image acquisition cycle, respectively.

[0030] S24: Setting a threshold F0 of the activity coefficient, evaluating the activity of building energy consumption, and determining target buildings for energy-saving renovation assessment;

[0031] If F k >F0, it means that the energy consumption activity of the building corresponding to the building profile k in the target study area is high, and the building corresponding to the building profile k is taken as the target building for energy-saving renovation assessment;

[0032] If F k ≤F0, it means that the activity of building energy consumption corresponding to building profile k in the target study area is low.

[0033] Furthermore, step S3 specifically includes:

[0034] S31: After screening all target buildings for energy-saving renovation assessment in the target study area, locate the target buildings according to the positioning coordinates of the corresponding buildings in the high-altitude bird's-eye view, and arrive at the location of the target buildings to obtain infrared images of the buildings;

[0035] S32: Calculate the current heat loss defect coefficient of the target building based on the pixel temperature data on the building infrared image;

[0036]

[0037] Among them, r is the pixel number of the building infrared image, R is the number of pixels of the building infrared image, T r is the pixel temperature value, is the average pixel temperature, σ T is the standard deviation of pixel temperature values, is the gradient modulus of the pixel temperature value, σ g is the Gaussian threshold.

[0038] The beneficial effects of the present invention are as follows: the present invention utilizes high-altitude infrared recognition technology and image recognition technology to scientifically and accurately identify and locate buildings and buildings with active energy consumption, accurately obtain target buildings that need to be evaluated for energy-saving renovations, and collect close-up infrared images of the target buildings, accurately identify the heat loss defects of the target buildings, and calculate the heat loss coefficient of the target buildings based on the loss defects, thereby determining whether the target buildings need to be energy-saving renovations. At the same time, it can also realize the benefit evaluation before and after the energy-saving renovation to ensure the effect of the energy-saving renovation. The present invention can realize the heat loss assessment of buildings in large areas within the city, provide reliable data support for subsequent energy-saving renovations of buildings, link building energy savings with economic benefits, and establish a complete evaluation system for the early and late stages of building energy-saving renovations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Flowchart of the urban area building energy-saving renovation assessment method based on thermal imaging technology.

[0040] Figure 2 Schematic diagram for screening building boundary points.

[0041] Figure 3 Schematic diagram of the false boundary. DETAILED DESCRIPTION

[0042] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0043] like Figure 1 As shown, a method for evaluating energy-saving renovation of urban area buildings based on thermal imaging technology includes the following steps:

[0044] S1: Identify the target study area in the city, use drones to obtain high-altitude bird's-eye view images of the target study area, identify building outlines from the high-altitude bird's-eye view images, and locate buildings within the target study area.

[0045] The method of identifying building outlines in the high-altitude bird's-eye view image and locating buildings in the target research area in step S1 specifically includes:

[0046] S11: Grayscale the aerial image and set a threshold Δh0 for the difference in pixel grayscale values between the roof and non-roof parts of the target area. The threshold Δh0 represents the minimum difference in pixel grayscale values on both sides of the roof boundary. Only when the difference threshold Δh0 is exceeded are two pixels considered to be on the roof boundary. Based on the difference threshold Δh0, an objective function for filtering building boundary points is constructed to filter out a set A of building boundary points.

[0047]

[0048] Among them, a n is the nth building boundary point, n is the number of building boundary points, (x n ,y n ) is the pixel coordinate of the building boundary point, i and v are any two pixels, (x i ,y i ) is the pixel coordinate of pixel i, (x v ,y v ) is the pixel coordinate of pixel v, h i 、h n are the grayscale values of two pixels respectively, and d0 is the building boundary width threshold based on the image;

[0049] like Figure 2 As shown in the figure, the principle diagram of filtering building boundary points after grayscale processing of high-altitude bird's-eye view images is given. Figure 2 The pixels in the medium grayscale image are magnified, and each square represents a pixel. The difference and distance between the grayscale values of two pixels are used to filter out the two pixels on both sides of the building boundary, and the midpoint of the two pixels is used as the building boundary point.

[0050] S12: Split the building boundary points in the building boundary point set A to form several sub-building boundary point sets. The objective function of the building boundary point splitting is:

[0051]

[0052] Among them, a m ,a e are the boundary point sets of any two sub-buildings split out, m and e are the numbers of the boundary point sets of any two sub-buildings, are the sub-building boundary point sets a m The coordinates of the two adjacent building boundary points in , c and d are the sub-building boundary point set a m The numbers of the two adjacent building boundary points, are the grayscale values of building boundary points c and d respectively, are the sub-building boundary point sets a eThe coordinates of the two adjacent building boundary points in , f and g are the sub-building boundary point set a e The numbers of the two adjacent building boundary points, are the grayscale values of the building boundary points f and g, respectively, c 、a f are the sub-building boundary point sets a m , sub-building boundary point set a e The two building boundary points with the closest distance, α is the boundary division coefficient, which is generally set to 1.5-3;

[0053] The boundary segmentation coefficient is used as the judgment standard for segmenting the boundaries of two adjacent sub-buildings. Its role is to: during the identification of building boundary points, non-real building outline boundaries will also be identified, or false boundaries inside the building will be identified, such as Figure 3 As shown in the figure, by reasonably setting the size of the boundary segmentation coefficient α, these false boundaries can be effectively isolated, and the boundaries of two adjacent real buildings can be segmented with high precision to avoid overlap and fusion;

[0054] S13: based on the number of building boundary points in the split sub-building boundary point sets, delete the sub-building boundary point sets whose number of building boundary points is less than a set threshold, and connect the building boundary points in the remaining sub-building boundary point sets to form the building outline within the target research area;

[0055] S14: Calculate the location coordinates of buildings in the target study area based on the coordinates of the building boundary points on the building outline

[0056]

[0057] Where j is the number of the building boundary point on the building outline, J is the number of building boundary points on the building outline, (x j ,y j ) is the pixel coordinate of building boundary point j.

[0058] S2: Use drone infrared imaging to obtain high-altitude infrared images of the target study area. Based on the identified building outlines and the corresponding building positioning coordinates, analyze the energy consumption activity of buildings in the target study area and select target buildings for energy-saving renovation assessment. Step S2 specifically includes:

[0059] S21: Select a period of time at night when the ambient temperature is stable as the image acquisition period, such as 1-3 am as the image acquisition period. Use drone infrared imaging to obtain high-altitude infrared images of the target research area during the image acquisition period, and continuously and evenly acquire multiple high-altitude infrared images. Process the high-altitude infrared images, including rotating, cropping, zooming in or out, to align the high-altitude infrared images with the high-altitude bird's-eye view images.

[0060] S22: grayscale the aligned high-altitude infrared images to obtain a grayscale image set, and move the building outlines in the high-altitude overhead image to the grayscale image;

[0061] In step S1, the pixel coordinates of each boundary pixel on the building outline in the high-altitude overhead image have been calculated. After the high-altitude infrared image and the high-altitude overhead image are aligned, the pixel positions on the two images correspond. Therefore, the pixel coordinates of the building outline in the grayscale image can be determined based on the coordinates of the boundary pixels in the high-altitude overhead image, and then the building outline in the grayscale image can be determined.

[0062] S23: Calculate the activity coefficient F of building energy consumption based on the change of pixel grayscale values within the building outline in the grayscale image during the image acquisition cycle k ;

[0063]

[0064] Where k is the number of the building outline in the target study area, F k is the activity coefficient of the building corresponding to the k-th building outline in the target study area, q is the number of times high-altitude infrared images are collected during the image acquisition cycle, is the average grayscale value of the pixels within the building outline in the qth high-altitude infrared image collected, h0′ is the grayscale value threshold of the pixels that characterize the excessive heat loss of the building corresponding to the building outline, Q is the number of high-altitude infrared images collected during the image acquisition cycle, p is the number of times the excessive heat loss of the building is characterized during the image acquisition cycle, β1 and β2 are the weights of the influence of the frequency and degree of excessive heat loss of the building on the activity coefficient during the image acquisition cycle, respectively, β1 = 0.4 and β2 = 0.6;

[0065] S24: Setting a threshold F0 of the activity coefficient, evaluating the activity of building energy consumption, and determining target buildings for energy-saving renovation assessment;

[0066] If F k >F0, it means that the energy consumption activity of the building corresponding to the building profile k in the target study area is high, and the building corresponding to the building profile k is taken as the target building for energy-saving renovation assessment;

[0067] If F k≤F0, it means that the activity of building energy consumption corresponding to building profile k in the target study area is low.

[0068] S3: Collect infrared images of the target building, obtain pixel temperature data on the infrared images, calculate the current heat loss defect coefficient of the target building, and evaluate whether the target building needs energy-saving renovation.

[0069] Step S3 specifically includes:

[0070] S31: After screening all target buildings in the target study area, locate the target building according to the positioning coordinates of the corresponding building in the high-altitude bird's-eye view, and arrive at the location of the target building to obtain an infrared image of the building;

[0071] S32: Calculate the current heat loss defect coefficient of the target building based on the pixel temperature data on the building infrared image;

[0072]

[0073] Among them, r is the pixel number of the building infrared image, R is the number of pixels of the building infrared image, T r is the pixel temperature value, is the average pixel temperature, σ T is the standard deviation of pixel temperature values, is the gradient modulus of the pixel temperature value, σ g is the Gaussian threshold;

[0074] In the present invention, the thermal insulation defects of the target building surface are quantitatively evaluated by the heat loss defect coefficient, and the heat loss defect coefficient is calculated by fusing the statistical characteristics of the temperature field with the spatial gradient information; the deviation term of the pixel temperature value can measure the degree of deviation between the pixel point temperature and the regional average temperature, reflecting the local abnormal thermal characteristics, and the cubic operation significantly amplifies the contribution of the abnormal temperature point, enhancing the sensitivity to small heat loss defects; the temperature gradient suppression term can effectively suppress the misjudgment of the natural temperature gradient area, focusing on the sudden temperature anomaly caused by the heat loss defect. Exceeding the Gaussian threshold σ g When , the exponential term approaches 0, filtering out normal temperature changes caused by building structures (such as window frames, beams and columns). By adjusting the Gaussian threshold σ g , which can calculate the sensitivity for different building types (such as glass curtain walls or concrete walls).

[0075] S33: Based on the set heat loss defect coefficient threshold D0, evaluate whether the target building currently needs energy-saving renovation; if D>D0, it is determined that the target building needs energy-saving renovation; if D≤D0, it is determined that the target building does not need energy-saving renovation.

[0076] After the target building has undergone energy-saving renovation, the renovation benefit coefficient is calculated. The size of the renovation benefit coefficient is used to evaluate the effect of the energy-saving renovation. The larger the renovation benefit coefficient, the better the effect of the energy-saving renovation. Otherwise, the effect of the energy-saving renovation is worse, and the energy-saving renovation method needs to be modified.

[0077]

[0078] Among them, s is the area number of energy-saving transformation, S is the number of areas of energy-saving transformation, are the thermal resistance values of the areas before and after energy-saving transformation, A s is the area of the region, ΔHDD is the difference in heating degree days, P′ is the energy price coefficient, ω s It is the regional weight coefficient, which is determined by the ratio of the area of the region to the total building area.

[0079] Heating degree days (HDDs) is a quantitative indicator of the need for supplemental heat during the heating season. When the outdoor temperature falls below a certain baseline, buildings require heating to maintain a comfortable indoor temperature. Energy savings potential is determined by improving the thermal resistance and area of the target building's heat loss zones and translating this into economic benefits under actual climate conditions. If a wall renovation results in a 30% increase in thermal resistance, but the number of winter heating degree days decreases by 50 compared to the baseline year, the ΔHDD value will be negative, objectively reflecting a downward revision of energy savings due to global warming.

[0080] The present invention uses high-altitude infrared recognition technology and image recognition technology to scientifically and accurately identify and locate buildings and buildings with active energy consumption, accurately obtain target buildings that need to be evaluated for energy-saving renovations, and collect close-up infrared images of the target buildings, accurately identify the heat loss defects of the target buildings, and calculate the heat loss coefficient of the target buildings based on the loss defects, thereby judging whether the target buildings need to be energy-saving renovations. At the same time, it can also realize the benefit evaluation before and after the energy-saving renovation to ensure the effect of the energy-saving renovation. The present invention can realize the heat loss assessment of buildings in large areas within the city, provide reliable data support for the subsequent energy-saving renovation of buildings, link the energy saving of buildings with economic benefits, and establish a complete evaluation system for the early and late stages of building energy-saving renovations.

Claims

1. A method for evaluating energy-saving renovation of urban buildings based on thermal imaging technology, characterized in that: The following steps are involved: S1: Identify the target study area in the city, use drones to obtain aerial aerial images of the target study area, identify building outlines from the aerial aerial images, and locate buildings within the target study area; S2: Use UAV infrared imaging to obtain high-altitude infrared images of the target study area. Based on the identified building outlines and the corresponding building location coordinates, analyze the energy consumption activity of buildings in the target study area and select target buildings for energy-saving renovation assessment; S3: Collect infrared images of the target building, obtain pixel temperature data on the infrared images, calculate the current heat loss defect coefficient of the target building, and evaluate whether the target building needs energy-saving renovation.

2. The urban area building energy-saving renovation assessment method based on thermal imaging technology according to claim 1 is characterized in that: Also includes: After the target building has undergone energy-saving renovation, the renovation benefit coefficient is calculated. The size of the renovation benefit coefficient is used to evaluate the effect of the energy-saving renovation. The larger the renovation benefit coefficient, the better the effect of the energy-saving renovation. Otherwise, the effect of the energy-saving renovation is worse, and the energy-saving renovation method needs to be modified. Among them, s is the area number of energy-saving transformation, S is the number of areas of energy-saving transformation, are the thermal resistance values of the areas before and after energy-saving transformation, A s is the area of the region, ΔHDD is the difference in heating degree days, P′ is the energy price coefficient, ω s It is the regional weight coefficient, which is determined by the ratio of the area of the region to the total building area.

3. The urban area building energy-saving renovation assessment method based on thermal imaging technology according to claim 1 is characterized in that: The method for identifying building outlines in the high-altitude bird's-eye view image and locating buildings in the target research area in step S1 specifically includes: S11: grayscale processing is performed on the high-altitude bird's-eye view image, and a difference threshold Δh0 of the pixel grayscale values between the roof part and the non-roof part of the building in the target area is set. Based on the difference threshold Δh0, an objective function for screening building boundary points is constructed to screen out a set A of building boundary points; <h2 style=";text-align:left;direction:ltr">A = {a1,a2,…,a<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr">} Among them, a n is the nth building boundary point, n is the number of building boundary points, (x n ,y n ) is the pixel coordinate of the building boundary point, i and v are any two pixels, (x i ,y i ) is the pixel coordinate of pixel i, (x v ,y v ) is the pixel coordinate of pixel v, h i 、h n are the grayscale values of two pixels respectively, and d0 is the building boundary width threshold based on the image; S12: Split the building boundary points in the building boundary point set A to form several sub-building boundary point sets. The objective function of the building boundary point splitting is: Among them, a m ,a e are the boundary point sets of any two sub-buildings split out, m and e are the numbers of the boundary point sets of any two sub-buildings, are the sub-building boundary point sets a m The coordinates of two adjacent pixels in the image, c and d are the boundary points of the sub-building set a m The numbers of two adjacent pixels in , are the grayscale values of pixels c and d respectively, are the sub-building boundary point sets a e The coordinates of two adjacent pixels in the image, f and g are the sub-building boundary point set a e The numbers of two adjacent pixels in , are the grayscale values of pixels f and g, respectively, and a c 、a f are the sub-building boundary point sets a m , sub-building boundary point set a e The two pixels with the closest distance between them, α is the boundary segmentation coefficient; S13: based on the number of building boundary points in the split sub-building boundary point sets, delete the sub-building boundary point sets whose number of building boundary points is less than a set threshold, and connect the number of building boundary points in the remaining sub-building boundary point sets to form the building outline within the target research area; S14: Calculate the location coordinates of buildings in the target study area based on the coordinates of the building boundary points on the building outline Where j is the number of the building boundary point on the building outline, J is the number of building boundary points on the building outline, (x j ,y j ) is the pixel coordinate of building boundary point j.

4. The urban area building energy-saving renovation assessment method based on thermal imaging technology according to claim 3 is characterized in that: The step S2 specifically includes: S21: Selecting a period of time at night when the ambient temperature is stable as an image acquisition period, using drone infrared imaging to acquire high-altitude infrared images of the target research area during the image acquisition period, and processing the high-altitude infrared images to align the high-altitude infrared images with the high-altitude overhead images; S22: grayscale the aligned high-altitude infrared images to obtain a grayscale image set, and move the building outlines in the high-altitude overhead image to the grayscale image; S23: Calculate the activity coefficient F of building energy consumption based on the change of pixel grayscale values within the building outline in the grayscale image during the image acquisition cycle k ; Where k is the number of the building outline in the target study area, F k is the activity coefficient of the building corresponding to the k-th building outline in the target study area, q is the number of times high-altitude infrared images are collected during the image acquisition cycle, is the average grayscale value of the pixels within the building outline in the high-altitude infrared image collected for the qth time, h0′ is the threshold value representing the excessive heat loss of the building corresponding to the building outline, Q is the number of high-altitude infrared images collected during the image acquisition cycle, p is the number of times the excessive heat loss of the building is represented during the image acquisition cycle, β1 and β2 are the weights of the influence of the frequency and degree of excessive heat loss of the building on the activity coefficient during the image acquisition cycle, respectively. S24: Setting a threshold F0 of the activity coefficient, evaluating the activity of building energy consumption, and determining target buildings for energy-saving renovation assessment; If F k >F0, it means that the energy consumption activity of the building corresponding to the building profile k in the target study area is high, and the building corresponding to the building profile k is taken as the target building for energy-saving renovation assessment; If F k ≤F0, it means that the activity of building energy consumption corresponding to building profile k in the target study area is low.

5. The urban area building energy-saving renovation assessment method based on thermal imaging technology according to claim 4 is characterized in that: The step S3 specifically includes: S31: After screening all target buildings for energy-saving renovation assessment in the target study area, locate the target buildings according to the positioning coordinates of the corresponding buildings in the high-altitude bird's-eye view, and arrive at the location of the target buildings to obtain infrared images of the buildings; S32: Calculate the current heat loss defect coefficient of the target building based on the pixel temperature data on the building infrared image; Among them, r is the pixel number of the building infrared image, R is the number of pixels of the building infrared image, T r is the pixel temperature value, is the average pixel temperature, σ T is the standard deviation of pixel temperature values, is the gradient modulus of the pixel temperature value, σ g is the Gaussian threshold.

Images