CN114187524B - Household air conditioner identification method, device, equipment, storage medium and product - Google Patents

Abstract

The present disclosure provides a method, apparatus, device, storage medium and product for identifying a home air conditioner, the method comprising: acquiring an identification request; acquiring a remote sensing image corresponding to the area identifier according to the identification request, and determining the outline and height of each building in the area to be identified according to the remote sensing image; according to the identification request, obtaining a street view picture corresponding to the area identification, and determining the number of household air conditioners corresponding to each street building in the street view picture; determining the outline and the height of the buildings along the street in the remote sensing image according to the position information of the buildings along the street; determining the mapping relation between the number of the household air conditioners and the outline and the height; calculating the number of target household air conditioners corresponding to each building according to the outline and the height corresponding to each building; and determining the sum of the target household air conditioner quantity corresponding to each building as the total quantity of the household air conditioners in the area to be identified. The accurate extraction of the using amount and the spatial distribution condition of the urban household air conditioner is emphatically solved, and the using and surveying efficiency of the household air conditioner is effectively improved.

Description

Household air conditioner identification method, device, equipment, storage medium and product

technical field

The present disclosure relates to the field of image processing, and in particular, to a method, device, device, storage medium and product for identifying a household air conditioner.

Background technique

Climate change has exacerbated the risk and threat of extreme high temperature disasters to human life safety. Household air conditioners are an effective means for residents to cope with extreme temperature events, and also an important way to consume electricity and energy during high temperature in summer. Accurately grasping the number of household air conditioners and their spatial distribution is of great significance for scientifically dispatching energy, saving energy and reducing emissions, and improving residents' response to extreme temperature disasters. However, at present, the data on the usage quantity and spatial distribution of air conditioners are very lacking, and how to determine the usage data and spatial distribution of household air conditioners has become an urgent problem to be solved.

The existing household air conditioner identification methods are generally based on traditional human sample surveys and user surveys. There are few sample points, and the survey results have greater uncertainty. The survey is time-consuming and labor-intensive, and traditional identification methods are difficult to achieve. Accurately grasp the spatial distribution law of the number of air conditioners.

SUMMARY OF THE INVENTION

The present disclosure provides a method, device, equipment, storage medium and product for identifying household air conditioners, which are used to solve the problems that the existing methods for determining the use data and spatial distribution of household air conditioners are not accurate, consume human resources and have low efficiency. question.

A first aspect of the present disclosure is to provide a method for identifying a household air conditioner, including:

Obtaining an identification request, wherein the identification request includes an area identifier of the area to be identified;

According to the identification request, obtain a remote sensing image corresponding to the area identifier, determine the outline of each building in the to-be-identified area according to the remote sensing image, and determine the height of each building according to the remote sensing image;

Acquire at least one street view picture corresponding to the area identifier according to the identification request, and determine the number of household air conditioners corresponding to buildings along the street in the street view picture according to the at least one street view picture;

For each building along the street, determine the outline and height of the building along the street in the remote sensing image according to the location information of the building along the street;

Determine the mapping relationship between the number of household air conditioners and the contour and height according to the corresponding contour, height and the number of household air conditioners of the buildings along the street;

For each building in the to-be-identified area, calculate the number of target household air conditioners corresponding to each building according to the contour and height corresponding to each building;

The sum of the number of target household air conditioners corresponding to each building is determined as the total amount of household air conditioners in the to-be-identified area.

A second aspect of the present disclosure is to provide a household air conditioner identification device, comprising:

an acquisition module, configured to acquire an identification request, wherein the identification request includes an area identifier of the area to be identified;

The remote sensing image processing module is configured to obtain a remote sensing image corresponding to the area identifier according to the identification request, determine the outline of each building in the to-be-identified area according to the remote sensing image, and determine each building according to the remote sensing image. the height of the building;

A street view picture processing module, configured to obtain at least one street view picture corresponding to the area identifier according to the identification request, and determine the number of household air conditioners corresponding to each street building in the street view picture according to the at least one street view picture ;

a matching module for determining, for each building along the street, the outline and height of the building along the street in the remote sensing image according to the location information of the building along the street;

A determination module, configured to determine the mapping relationship between the number of household air conditioners and the outline and height according to the corresponding contours, heights and the number of household air conditioners of buildings along the street;

a calculation module, configured to calculate the number of target household air conditioners corresponding to each building according to the contour and height corresponding to each building for each building in the to-be-identified area;

The processing module is configured to determine the sum of the number of target household air conditioners corresponding to each building as the total amount of household air conditioners in the to-be-identified area.

A third aspect of the present disclosure is to provide an electronic device, including: a memory, and a processor;

memory; memory for storing instructions executable by the processor;

Wherein, the processor is configured to invoke the program instructions in the memory to execute the method for identifying a household air conditioner according to the first aspect.

A fourth aspect of the present disclosure is to provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, are used to implement the first aspect Home air conditioner identification method.

A fifth aspect of the present disclosure is to provide a computer program product, including a computer program that, when executed by a processor, implements the method for identifying a household air conditioner according to the first aspect.

The household air conditioner identification method, device, equipment, storage medium and product provided by the present disclosure, by using high-resolution satellite remote sensing images and Internet map street view picture information, an efficient and accurate household air conditioner spatial statistical survey method based on deep learning and spatial statistical methods , focusing on the accurate extraction of urban household air-conditioning usage and its spatial distribution, effectively improving the efficiency of household air-conditioning use investigations, and further improving the management and control level of urban residents and management departments in responding to extreme high temperature events and rationally dispatching electric energy.

Description of drawings

In order to explain the embodiments of the present disclosure or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are For some embodiments of the present disclosure, those of ordinary skill in the art can also obtain other drawings according to these drawings.

1 is a schematic diagram of a system architecture on which the present disclosure is based;

2 is a schematic flowchart of a method for identifying a household air conditioner according to Embodiment 1 of the present disclosure;

3 is a schematic outline diagram of a building in a to-be-identified area provided by an embodiment of the present disclosure;

4 is a schematic flowchart of a method for identifying a household air conditioner according to Embodiment 2 of the present disclosure;

5 is a schematic flowchart of a method for identifying a household air conditioner according to Embodiment 3 of the present disclosure;

6A is a schematic structural diagram of a satellite and the sun on different sides according to an embodiment of the present disclosure;

6B is a schematic structural diagram of the sun and the satellite being on the same side according to an embodiment of the present disclosure;

7 is a schematic flowchart of a method for identifying a household air conditioner according to Embodiment 4 of the present disclosure;

8 is a schematic structural diagram of a household air conditioner identification device provided in Embodiment 5 of the present disclosure;

FIG. 9 is a schematic structural diagram of an electronic device according to Embodiment 6 of the present disclosure.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments These are some, but not all, embodiments of the present disclosure. All other embodiments obtained based on the embodiments in the present disclosure fall within the protection scope of the present disclosure.

In view of the above-mentioned existing test methods, since a large amount of repeated information is stored in the data list used for testing, the test case has a low utilization rate of the data information of the data list to the data list during the test process. To solve the problem of inconvenient maintenance and management of the data list, the present disclosure provides a household air conditioner identification method, device, device, storage medium and product.

It should be noted that the present disclosure provides a household air conditioner identification method, device, device, storage medium, and product that can be used in scenarios where application software is tested.

The use of air conditioners is the main measure for urban residents to cope with extreme high temperatures, but the current data on the number and spatial distribution of air conditioners is very lacking. The survey on air conditioner use still uses traditional manual methods and statistical data estimated through sampling surveys. The survey methods are backward and the survey data The uncertainty is large, and the spatial distribution of household air conditioners is unclear.

In the process of solving the above technical problems, the inventor found through research that high-resolution remote sensing images contain rich shape structure and texture information of surface targets, making them an important data source for urban research, such as high-resolution aerial remote sensing images, Satellite remote sensing images, UAV remote sensing images, radar images, etc. are widely used to extract the outline of urban buildings. Urban street view images also contain more detailed information, and in recent years, they have been gradually applied to urban information extraction, such as traffic lights, roadside buildings, street lights, and the number of streets. It can use high-resolution satellite remote sensing images and Internet map street view image information, efficient and accurate household air-conditioning spatial statistical survey methods based on deep learning and spatial statistical methods, focusing on solving the accurate extraction of urban household air-conditioning usage and its spatial distribution, effectively improving The efficiency of surveys on the use of household air conditioners has also further improved the management and control level of urban residents and management departments in responding to extreme high temperature events and rationally dispatching power and energy.

FIG. 1 is a schematic diagram of the system architecture on which the present disclosure is based. As shown in FIG. 1 , the system architecture on which the present disclosure is based at least includes: a terminal device 11 , a server 12 , a remote sensing image data server 13 and a street view image data server 14 . The server 12 is provided with a household air conditioner identification device, which can be written in languages such as C/C++, Java, Shell, or Python; the terminal device 11 can be, for example, a desktop computer, a tablet computer, or the like. The remote sensing image data server 13 may be a cloud server or a server cluster, which stores remote sensing images of multiple regions. The street view image data server 14 may be a cloud server or a server cluster, which stores street view images of multiple regions.

FIG. 2 is a schematic flowchart of a method for identifying a household air conditioner provided in Embodiment 1 of the present disclosure. As shown in FIG. 2 , the method includes:

Step 201: Obtain an identification request, wherein the identification request includes an area identifier of the area to be identified.

The executive body of this embodiment is a household air conditioner identification device. The household air conditioner identification device can be coupled to a server, and the server can be communicatively connected with a terminal device, so as to be able to identify households in the identified area according to an identification request triggered by the user on the terminal device. Identify the number of air conditioners.

In this embodiment, in order to achieve accurate extraction of the usage of urban household air conditioners and their spatial distribution, the management and control level of urban residents and management departments in dealing with extreme high temperature events and rationally dispatching electric energy is further improved. The household air conditioner identification device may acquire an identification request, where the identification request may be triggered by a user on a terminal device. The identification request may specifically include the area identifier of the area to be identified. For example, it may be a cell identity, a community identity, or the like.

Step 202: Acquire a remote sensing image corresponding to the area identifier according to the identification request, determine the outline of each building in the to-be-identified area according to the remote sensing image, and determine the height of each building according to the remote sensing image .

In this embodiment, household air conditioners are generally provided with air conditioner plug-in units outside the building, and the number of air conditioners in the area to be identified can be counted by identifying the air conditioner plug-in units outside the building. Since high-resolution remote sensing images contain rich shape structure and texture information of surface targets, information such as the contours of buildings in the area to be identified can be realized through remote sensing images.

Specifically, after the identification request is obtained, the remote sensing image corresponding to the area identifier may be obtained according to the identification request. Wherein, the remote sensing image also includes content such as position information corresponding to each building. An image recognition operation is performed on the remote sensing image to determine the outline of each building in the area to be recognized and the height of each building.

Step 203: Acquire at least one street view picture corresponding to the area identifier according to the identification request, and determine the number of home air conditioners corresponding to each street building in the street view picture according to the at least one street view picture.

In this embodiment, the city street view picture also includes more detailed information, for example, it may include traffic lights, street lights, buildings along the street, and the like. Combined with deep learning methods and street view pictures, it is possible to identify the air conditioners installed on buildings along the street.

Specifically, after the identification request is obtained, at least one street view picture corresponding to the area identifier may be obtained according to the identification request. The street view image is recognized by means of deep learning to determine the number of household air conditioners on the side of the building along the street in the street view image. Further, the number of external air conditioners on the other three sides of the building along the street can be manually identified and counted. The sum of the number identified by deep learning and the number identified manually is determined as the number of household air conditioners corresponding to each building along the street.

Step 204: For each building along the street, determine the outline and height of the building along the street in the remote sensing image according to the location information of the building along the street.

In this embodiment, the buildings along the street in the street view picture have location information, and the location information can be compared with the location information of the buildings in the remote sensing image to determine the outline and height of each street view building in the remote sensing image.

Step 205: Determine the mapping relationship between the number of household air conditioners, the outline, and the height according to the corresponding outline and height of each building along the street, and the number of household air conditioners.

After respectively determining the contour, height and quantity of household air conditioners corresponding to each building along the street, a mapping relationship between the quantity of household air conditioners and the contour and height can be established. The contour corresponding to the building along the street includes its length and width in the remote sensing image.

Step 206: For each building in the to-be-identified area, calculate the number of target household air conditioners corresponding to each building according to the contour and height corresponding to each building.

In this embodiment, after obtaining the contour and height of each building in the area to be identified and the mapping relationship between the number of household air conditioners and the contour and height, for each building in the area to be identified, the building can be calculated separately The corresponding target number of household air conditioners. The mapping relationship may specifically be an algorithmic relationship between the mapping relationship between the number of household air conditioners and the contour and height.

Step 207: Determine the sum of the target household air conditioners corresponding to each building as the total amount of household air conditioners in the to-be-identified area.

In this embodiment, after calculating and obtaining the target number of household air conditioners corresponding to each building, the sum of the target number of household air conditioners corresponding to each building can be determined as the total number of household air conditioners in the area to be identified.

Optionally, by performing a recognition operation on a high-resolution satellite remote sensing image and a street view picture, the distribution of the household air conditioners in each building can be recognized.

The household air conditioner identification method provided in this embodiment focuses on solving the problem of urban household air conditioner usage and consumption by using high-resolution satellite remote sensing images and Internet map street view picture information, and an efficient and accurate household air conditioner space identification method based on deep learning and spatial statistics methods. The accurate extraction of its spatial distribution can effectively improve the efficiency of household air-conditioning use investigations, and further improve the management and control level of urban residents and management departments in responding to extreme high temperature events and rationally dispatching electric energy.

Further, on the basis of Embodiment 1, the buildings along the street include a first building along the street and a second building along the street, the number of household air conditioners corresponding to the first building along the street is the number of first household air conditioners, and the The number of household air conditioners corresponding to the second building along the street is the number of second household air conditioners; wherein, the shape of the first building along the street and the building along the second street are different; Step 205 includes:

For the contour, height, and quantity of household air conditioners corresponding to the first building along the street, a mapping relationship between the quantity of the first household air conditioner corresponding to the first building along the street and the contour and height is determined.

For the contour, height and quantity of household air conditioners corresponding to the second building along the street, a mapping relationship between the quantity of the second household air conditioner corresponding to the second building along the street and the contour and height is determined.

In this embodiment, the buildings along the street in the to-be-identified area can be divided into the first building along the street and the second building along the street according to their different shapes, wherein the first building along the street and the second building along the street have different shapes. Correspondingly, the buildings in the to-be-identified area can be divided into a first building and a second building according to their different shapes. Wherein, the first building/the first building along the street may specifically be a tower building, and the second building/the second building along the street may specifically be a slab building.

Since towers and slabs have different shapes, the corresponding number of household air conditioners are also different. Therefore, different mapping relationships between the number of air conditioners, contours and heights can be constructed for different types of buildings.

Specifically, with respect to the contour, height, and quantity of household air conditioners corresponding to the first building along the street, a mapping relationship between the quantity of the first household air conditioner corresponding to the first building along the street, the contour, and the height is determined. Wherein, the mapping relationship between the number of the first household air conditioner and the contour and height can be specifically shown in formula 1.

Number of air conditioners for the first household = f Buildings along the first street (floor height, building outline length and width) (1)

For the contour, height, and quantity of household air conditioners corresponding to the second building along the street, a mapping relationship between the quantity of the second household air conditioner corresponding to the second building along the street and the contour and height is determined. Wherein, the mapping relationship between the number of the second household air conditioner and the contour and height may be specifically as shown in formula 2.

Number of second household air conditioners = f second buildings along the street (floor height, building outline length and width) (2)

FIG. 3 is a schematic outline diagram of a building in a to-be-identified area provided by an embodiment of the present disclosure. As shown in FIG. 3 , the to-be-identified area may specifically include a tower building 31 and a slab building 32 , wherein the tower building 31 and the slab building 32 have Different outline shapes.

Further, on the basis of Embodiment 1, step 206 includes:

For each building in the to-be-identified area, the first similarity between the building and the first building along the street and the second similarity between the building and the second building along the street are calculated respectively.

The buildings are classified into a first building and a second building according to the first similarity and the second similarity.

For each first building, the number of household air conditioners corresponding to the first building is calculated according to the outline and height corresponding to the first building, and the mapping relationship between the number of first household air conditioners and the outline and height.

For each second building, the number of household air conditioners corresponding to the second building is calculated according to the contour and height corresponding to the second building, and the mapping relationship between the number of second household air conditioners and the contour and height.

In this embodiment, the buildings in the to-be-identified area may be divided into a first building and a second building according to their different shapes. The buildings can be classified according to the similarity between each building and the first and second buildings along the street. It can be understood that, if the similarity between the building and the first building along the street is higher than the similarity between the second building along the street, the building can be characterized as the first building. vice versa.

Specifically, for each building in the area to be identified, the first similarity between the building and the first building along the street, and the second similarity between the building and the second building along the street are calculated respectively. Specifically, the fractal dimension can be used to calculate the similarity. Fractal dimension is a good method to measure shape similarity. It has rotation, translation and scale invariance, which is more consistent with human visual perception. According to the characteristics of fractal dimension, it takes into account the local structure and overall structure of elements. self-similarity.

After the classification is completed, for each type of building, the number of household air conditioners corresponding to the building can be calculated according to the above-mentioned mapping relationship. Specifically, for each first building, the number of home air conditioners corresponding to the first building is calculated according to the contour and height corresponding to the first building, and the mapping relationship between the number of first home air conditioners and the contour and height. For each second building, the number of home air conditioners corresponding to the second building is calculated according to the contour and height corresponding to the second building, and the mapping relationship between the number of second home air conditioners and the contour and height.

Further, on the basis of Embodiment 1, step 207 includes:

Calculate the first sum of the number of target household air conditioners corresponding to the first building and the second sum of the number of target household air conditioners corresponding to the second building, respectively.

The sum of the first sum and the second sum is determined as the total amount of household air conditioners in the area to be identified.

In this embodiment, for each building in the area to be identified, after the classification is completed, the first sum of the number of target household air conditioners corresponding to the first building and the target household air conditioner corresponding to the second building can be calculated respectively. The second number and the number of air conditioners. The sum of the first sum and the second sum is determined as the total amount of household air conditioners in the area to be identified.

Optionally, in order to improve the efficiency of household air conditioner identification, after the classification of buildings is completed, the number of various types of buildings can be simply counted, and the average value of the household air conditioners corresponding to various types of buildings can be determined, and the average value can be determined. For the number of household air conditioners corresponding to the building, according to the number of various types of buildings and the corresponding number of air conditioners, the calculation of the total amount of household air conditioners in the area to be identified is realized.

Specifically, formula 3 can be used to calculate the number of all household air conditioners in the area to be identified:

The number of air conditioners in the area to be identified =

The method for identifying a household air conditioner provided in this embodiment can further improve the household air conditioner by classifying the building according to the shape of the building, and setting different mapping relationships between the number of air conditioners and the outline and height of the building for different categories. recognition accuracy.

4 is a schematic flowchart of a method for identifying a household air conditioner provided in Embodiment 2 of the present disclosure. On the basis of Embodiment 1, as shown in FIG. 4 , step 202 includes:

Step 401: Perform an image processing operation on the remote sensing image to obtain a processed remote sensing image, wherein the image processing operation includes a geometric correction operation and/or an image fusion operation.

Step 402: Input the processed remote sensing image into a preset contour extraction model to obtain the contours of the buildings.

In this embodiment, after the remote sensing image is acquired, an image processing operation may be performed on the remote sensing image first to obtain the processed remote sensing image. Specifically, image processing operations include geometric correction operations and/or image fusion operations. The combination, size, scale and direction of the ground object image information obtained from the remote sensing images are inconsistent with the real ground objects, and geometric correction is required. There are many orthorectification models for remote sensing images, such as the general polynomial correction model. High-resolution remote sensing image fusion mainly transforms and fuses multi-spectral imagery and higher-resolution panchromatic imagery data to improve the information and availability of images. Wherein, any remote sensing image fusion method can be used to realize the fusion operation of the remote sensing images, which is not limited in the present disclosure.

Further, after obtaining the processed remote sensing image, the processed remote sensing image can be input into a preset contour extraction model. The contour extraction model can extract the contours of buildings in the remote sensing images, so that the contours of each building can be obtained after the processed remote sensing images are input into the preset contour extraction model.

Further, on the basis of any of the above-mentioned embodiments, before step 402, it also includes:

Obtain a first training data set, wherein the first training data set includes a plurality of marked remote sensing images and first marking information corresponding to the marked remote sensing images, and the first marking information is a building in the remote sensing image contour.

An iterative training operation is performed on the preset first model to be trained by using the first training data set until the first model to be trained converges, and the contour extraction model is obtained.

In this embodiment, before the contour extraction of the building is performed by using the contour extraction model, the training operation of the contour extraction model may be performed in advance. Specifically, a first training data set may be obtained, wherein the first training data set includes a plurality of marked remote sensing images and first marking information corresponding to the marked remote sensing images, where the first marking information is buildings in the remote sensing images contour. An iterative training operation is performed on the preset first model to be trained through the first training data set, and the parameters of the first model to be trained are continuously adjusted according to the loss value of the first model to be trained until the first model to be trained converges , to obtain the contour extraction model.

In the method for identifying a home air conditioner provided in this embodiment, by performing image processing operations on remote sensing images, the processed remote sensing images are input into a preset contour extraction model to extract building contours, so that building contours in remote sensing images can be accurately extracted. The acquisition of the object contour provides a basis for the subsequent identification of the number of household air conditioners.

FIG. 5 is a schematic flowchart of a method for identifying a household air conditioner provided in Embodiment 3 of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 5 , step 202 includes:

Step 501: Determine shadow size information corresponding to the buildings according to the outlines of the buildings.

Step 502: Determine the positional relationship between the satellite and the sun when the remote sensing image is captured.

Step 503: Calculate the height of the building according to the positional relationship and the shadow size information.

In this embodiment, the number of household air conditioners corresponding to buildings of different heights is different. It can be understood that a taller building should theoretically have a larger number of household air conditioners. Therefore, in order to accurately identify the number of household air conditioners, it is also necessary to calculate the height corresponding to each building.

Specifically, the shadow length calculation is the key to inverting the building height using shadows. For the outlines of the buildings, shadow size information corresponding to the buildings can be determined. Specifically, the shadow size information may be extracted from remote sensing images. In the present disclosure, the shadow length is measured according to the direction of the sun azimuth angle, the influence of the sun azimuth angle has been considered, and the influence of the satellite azimuth angle on the test results is not considered.

FIG. 6A is a schematic structural diagram of the satellite and the sun on different sides according to an embodiment of the present disclosure. As shown in FIG. 6A , the sun 61 is on the left side of the building 62 , and the satellite 63 is on the right side of the building 62 . FIG. 6B is a schematic structural diagram of the sun and the satellite on the same side according to an embodiment of the present disclosure. As shown in FIG. 6B , the sun 64 and the satellite 65 are both located on the left side of the building 66 . As shown in Figures 6A-6B, since the positional relationship between the satellite and the sun is different, the shadow size is also different. Therefore, in order to improve the accuracy of the calculated building height, it is also necessary to determine the distance between the satellite and the sun when the remote sensing image is taken. Positional relationship. Calculate the height of the building based on the positional relationship and shadow size information.

Further, the positional relationship includes that the satellite and the sun are on the same side when the remote sensing image is taken, and the shadow size information includes the length of the shadow of the building in the remote sensing image, and the length of the shadow of the building along the direction of sun irradiation. , the sun elevation angle and the satellite elevation angle; on the basis of any of the above embodiments, step 503 includes:

The building is calculated according to the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, the sun elevation angle and the satellite elevation angle, and a preset first building height algorithm the height of.

In this embodiment, the positional relationship may specifically include that the satellite is on the same side as the sun when the remote sensing image is taken, and the shadow size information may specifically include the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, and the height of the sun. angle and satellite altitude. The height of the building may be calculated according to the position information, shadow size information and a preset first building height algorithm.

Among them, the first building height algorithm can be as shown in formula 4-5:

A = S–B = H/tanθ–H/tanω (4)

H = A tanθtanω/ (tanω–tanθ) (5)

Among them, H is the height of the building; S is the length of the shadow of the building along the direction of the sun on the high-resolution remote sensing image; A is the length of the shadow on the image; θ is the sun elevation angle; ω is the satellite elevation angle.

Further, the positional relationship includes that the satellite and the sun are on different sides when the remote sensing image is taken, and the shadow size information includes the length of the shadow of the building in the remote sensing image, and the length of the shadow of the building along the direction of sun irradiation. , the sun elevation angle and the satellite elevation angle; on the basis of any of the above embodiments, step 503 includes:

The building is calculated according to the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, the sun elevation angle and the satellite elevation angle, and a preset second building height algorithm. the height of.

In this embodiment, the positional relationship may specifically include that the satellite is on the same side as the sun when the remote sensing image is taken, and the shadow size information may specifically include the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, and the height of the sun. angle and satellite altitude. The height of the building may be calculated according to the position information, shadow size information and a preset second building height algorithm.

Wherein, the second building height algorithm can be as shown in formula 6-7:

A = S–B = H/tanθ–H/tanω (6)

H = A tanθ (7)

Among them, H is the height of the building; S is the length of the shadow of the building along the direction of the sun on the high-resolution remote sensing image; A is the length of the shadow on the image; θ is the sun elevation angle; ω is the satellite elevation angle.

The method for identifying a home air conditioner provided in this embodiment uses different algorithms to calculate the height of the building according to the different positional relationships between the satellite and the sun, so that the accuracy of the calculated height of the building can be improved, and the identification of the height of the building can be improved. The accuracy of the number of domestic air conditioners in the building.

FIG. 7 is a schematic flowchart of a method for identifying a household air conditioner according to Embodiment 4 of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 7 , step 203 includes:

Step 701: For each street view picture, input the street view picture into a preset household air conditioner identification model, and obtain the number of household air conditioners corresponding to the buildings along the street in the street view picture.

Step 702: Calculate the average value of the number of household air conditioners corresponding to the buildings along the street in the at least one street view picture, and determine the average value as the number of household air conditioners corresponding to the buildings along the street in the area to be identified.

In this embodiment, the Baidu Street View pictures of the research and investigation area can be captured by a web crawler. For each street view picture, the street view picture is input into a preset household air conditioner identification model, and the number of household air conditioners corresponding to the buildings along the street in the street view picture is obtained. Specifically, any network model capable of image recognition can be used as the household air conditioner recognition model to perform the recognition operation of the household air conditioner, which is not limited in the present disclosure. The number of air conditioners in the building at the sample point can be used as the sample point for the air conditioner survey sampling of the buildings in the community or area. Therefore, the average value of the number of household air conditioners corresponding to the buildings along the street in the at least one street view picture can be calculated, and the average value is determined as the number of household air conditioners corresponding to the buildings along the street in the area to be identified.

By using the household air conditioner recognition model to identify the household air conditioners in the street view pictures, on the basis of identifying the number of household air conditioners, the spatial distribution of the household air conditioners in the building can also be accurately identified. For example, the spatial distribution positions of household air conditioners in each building can be identified.

Further, on the basis of any of the above embodiments, before step 602, the method further includes:

Acquiring a second training data set, the second training data set includes a plurality of labeled pictures of buildings along the street and second label information corresponding to the pictures of buildings along the street after labeling, and the second label information is the pictures of buildings along the street Home air conditioner information inside.

An iterative training operation is performed on a preset second model to be trained by using the second training data set until the second model to be trained converges, and the household air conditioner identification model is obtained.

In this embodiment, before identifying the number of home air conditioners by using the home air conditioner identification model, a training operation of the home air conditioner identification model needs to be performed first. Specifically, a second training data set may be obtained, and the second training data set includes a plurality of labeled pictures of buildings along the street and second label information corresponding to the labeled pictures of buildings along the street, where the second label information is: Home air conditioner information in pictures of buildings along the street. Use the second training data set to perform an iterative training operation on the preset second model to be trained, and continuously adjust the parameters of the second model to be trained according to the loss value of the second model to be trained, until the second model to be trained Convergence to obtain the household air conditioner identification model.

The method for recognizing household air conditioners provided in this embodiment can accurately recognize the number of household air conditioners corresponding to buildings along the street by combining street view pictures with deep learning.

FIG. 8 is a schematic structural diagram of a household air conditioner identification device provided in Embodiment 5 of the present disclosure. As shown in FIG. 8 , the device includes: an acquisition module 81 , a remote sensing image processing module 82 , a street view image processing module 83 , a matching module 84 , and a determination module 85 , a computing module 86 and a processing module 88 . The obtaining module 81 is configured to obtain an identification request, wherein the identification request includes an area identifier of the area to be identified. The remote sensing image processing module 82 is configured to obtain a remote sensing image corresponding to the area identification according to the identification request, determine the outline of each building in the to-be-identified area according to the remote sensing image, and determine according to the remote sensing image height of each building. The street view picture processing module 83 is configured to obtain at least one street view picture corresponding to the area identifier according to the identification request, and determine the home air conditioner corresponding to each street building in the street view picture according to the at least one street view picture quantity. The matching module 84 is configured to, for each building along the street, determine the outline and height of the building along the street in the remote sensing image according to the position information of the building along the street. The determination module 85 is configured to determine the mapping relationship between the number of household air conditioners and the outline and height according to the corresponding outline and height of each building along the street and the number of household air conditioners. The calculation module 86 is configured to, for each building in the to-be-identified area, calculate the number of target household air conditioners corresponding to each building according to the contour and height corresponding to each building. The processing module 87 is configured to determine the sum of the number of target household air conditioners corresponding to each building as the total amount of household air conditioners in the area to be identified.

Further, on the basis of Embodiment 5, the buildings along the street include a first building along the street and a second building along the street, the number of household air conditioners corresponding to the first building along the street is the number of first household air conditioners, and the The number of household air conditioners corresponding to the second building along the street is the number of second household air conditioners; wherein, the shape of the first building along the street and the building along the second street are different. The determining module is used for: determining the mapping relationship between the number of the first household air conditioners corresponding to the first building along the street, the contour and the height, with respect to the contour, height and the number of household air conditioners corresponding to the first building along the street;

For the contour, height and quantity of household air conditioners corresponding to the second building along the street, a mapping relationship between the quantity of the second household air conditioner corresponding to the second building along the street and the contour and height is determined.

Further, on the basis of Embodiment 5, the determining module is configured to: for each building in the to-be-identified area, respectively calculate the first similarity between the building and the first building along the street, and The second similarity between the building and the second building along the street. The buildings are classified into a first building and a second building according to the first similarity and the second similarity. For each first building, the number of household air conditioners corresponding to the first building is calculated according to the outline and height corresponding to the first building, and the mapping relationship between the number of first household air conditioners and the outline and height. For each second building, the number of household air conditioners corresponding to the second building is calculated according to the contour and height corresponding to the second building, and the mapping relationship between the number of second household air conditioners and the contour and height.

Further, on the basis of Embodiment 5, the determining module is used to calculate the first sum of the target number of household air conditioners corresponding to the first building, and the second sum of the target number of household air conditioners corresponding to the second building. quantity and.

The sum of the first sum and the second sum is determined as the total amount of household air conditioners in the area to be identified.

Further, on the basis of any of the above embodiments, the remote sensing image processing module is configured to: perform an image processing operation on the remote sensing image to obtain a processed remote sensing image, wherein the image processing operation includes a geometric correction operation and/or or image fusion operation;

The processed remote sensing images are input into a preset contour extraction model to obtain the contours of the buildings.

Further, on the basis of any of the above-mentioned embodiments, the remote sensing image processing module is used to: obtain a first training data set, wherein the first training data set includes a plurality of marked remote sensing images and marked remote sensing images. First labeling information corresponding to the remote sensing image, the first labeling information is the outline of the building in the remote sensing image; using the first training data set to perform an iterative training operation on the preset first model to be trained until the first model to be trained The training model converges, and the contour extraction model is obtained.

Further, on the basis of any of the above-mentioned embodiments, the remote sensing image processing module is configured to: determine the shadow size information corresponding to the buildings according to the outlines of the buildings. Determine the positional relationship between the satellite and the sun when the remote sensing image is captured. The height of the building is calculated according to the positional relationship and the shadow size information.

Further, on the basis of any of the above-mentioned embodiments, the positional relationship includes that the satellite and the sun are on the same side when the remote sensing image is taken, and the shadow size information includes the length of the shadow of the building in the remote sensing image, the length of the shadow along the sun The length of the shadow of the building in the direction of illumination, the sun elevation angle and the satellite elevation angle. The remote sensing image processing module is configured to: according to the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, the sun elevation angle and the satellite elevation angle, and a preset first A building height algorithm calculates the height of the building.

Further, on the basis of any of the above-mentioned embodiments, the positional relationship includes that the satellite and the sun are on different sides when the remote sensing image is taken, and the shadow size information includes the length of the shadow of the building in the remote sensing image, the distance along the sun The length of the shadow of the building in the direction of illumination, the sun elevation angle and the satellite elevation angle. The remote sensing image processing module is used for: according to the length of the shadow of the building in the remote sensing image, the length of the shadow of the building along the direction of sun irradiation, the sun elevation angle and the satellite elevation angle, and a preset second A building height algorithm calculates the height of the building.

Further, on the basis of any of the above-mentioned embodiments, the street view picture processing module is used to: for each street view picture, input the street view picture into a preset household air conditioner identification model, and obtain the street view pictures in the street along the street. The number of home air conditioners corresponding to the building. Calculate the average value of the number of household air conditioners corresponding to the buildings along the street in the at least one street view picture, and determine the average value as the number of household air conditioners corresponding to the buildings along the street in the area to be identified.

Further, on the basis of any of the above-mentioned embodiments, the street view image processing module is used to: obtain a second training data set, and the second training data set includes a plurality of marked pictures of buildings along the street and marked pictures of buildings. second labeling information corresponding to the pictures of buildings along the street, where the second labeling information is household air conditioner information in the pictures of buildings along the street;

An iterative training operation is performed on a preset second model to be trained by using the second training data set until the second model to be trained converges, and the household air conditioner identification model is obtained.

Yet another embodiment of the present disclosure also provides an electronic device, including: a processor and a memory;

the memory stores computer-executable instructions;

The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for identifying a household air conditioner according to any one of the foregoing embodiments.

FIG. 9 is a schematic structural diagram of an electronic device according to Embodiment 6 of the present disclosure. As shown in FIG. 9 , the electronic device 900 may be a terminal device or a server. The terminal device may include, but is not limited to, such as a mobile phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (Personal Digital Assistant, PDA for short), a tablet computer (Portable Android Device, PAD for short), a portable multimedia player (Portable Media Player, PMP for short), mobile terminals such as in-vehicle terminals (eg, in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in FIG. 9 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 9 , the electronic device 900 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 901 , which may be stored in a read-only memory (Read Only Memory, ROM for short) 902 according to a program or from a storage device 908 is a program loaded into a random access memory (Random Access Memory, RAM for short) 903 to execute various appropriate actions and processes. In the RAM 903, various programs and data necessary for the operation of the electronic device 900 are also stored. The processing device 901 , the ROM 902 , and the RAM 903 are connected to each other through a bus 904 . An input/output (I/O) interface 905 is also connected to bus 904 .

Generally, the following devices can be connected to the I/O interface 905: input devices 906 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a Liquid Crystal Display (LCD) Output device 907 , speaker, vibrator, etc.; storage device 908 including, for example, magnetic tape, hard disk, etc.; and communication device 909 . The communication means 909 may allow the electronic device 900 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 9 shows an electronic device 900 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication device 909 , or from the storage device 908 , or from the ROM 902 . When the computer program is executed by the processing device 901, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

Yet another embodiment of the present disclosure further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the implementation of any of the foregoing embodiments is implemented. The method for identifying household air conditioners.

It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

Yet another embodiment of the present disclosure further provides a computer program product, including a computer program that, when executed by a processor, implements the method for recognizing a household air conditioner according to any of the foregoing embodiments.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, causes the electronic device to execute the methods shown in the above-mentioned embodiments.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional Procedural programming language - such as the "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (eg using an internet service provider to connect via the internet).

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, but not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present disclosure. scope.

Claims (10)

1. A household air conditioner identification method is characterized by comprising the following steps:

acquiring an identification request, wherein the identification request comprises an area identifier of an area to be identified;

acquiring a remote sensing image corresponding to the area identifier according to the identification request, determining the outline of each building in the area to be identified according to the remote sensing image, and determining the height of each building according to the remote sensing image;

acquiring at least one street view picture corresponding to the area identifier according to the identification request, and determining the number of household air conditioners corresponding to each street building in the street view picture according to the at least one street view picture;

determining the outline and the height of each buildings along the street in the remote sensing image according to the position information of the buildings along the street;

determining the mapping relation between the number of the household air conditioners and the profile and the height according to the profile and the height corresponding to each buildings along the street and the number of the household air conditioners;

aiming at each building in the area to be identified, calculating the number of target household air conditioners corresponding to each building according to the outline and height corresponding to each building;

and determining the sum of the target household air conditioner quantity corresponding to each building as the total quantity of the household air conditioners in the area to be identified.

2. The method of claim 1, wherein the buildings along the street comprise a first building along the street and a second building along the street, the first building along the street corresponding to the number of the household air conditioners being a first number of the household air conditioners, and the second building along the street corresponding to the number of the household air conditioners being a second number of the household air conditioners; the first buildings and the second buildings are different in shape;

the determining the mapping relation between the number of the household air conditioners and the profile and the height according to the profile and the height corresponding to each buildings along the street and the number of the household air conditioners comprises the following steps:

determining the mapping relation between the number of first household air conditioners corresponding to a first buildings along the street and the profile and the height of the first household air conditioners according to the profile and the height of the first buildings along the street and the number of the household air conditioners;

and determining the mapping relation between the second household air conditioner quantity corresponding to the second buildings along the street and the profile and the height of the second household air conditioner quantity corresponding to the second buildings along the street.

3. The method according to claim 2, wherein the calculating, for each building in the area to be identified, the target number of home air conditioners corresponding to each building according to the outline and the height corresponding to each building comprises:

respectively calculating a first similarity between the building and a first street building and a second similarity between the building and a second street building aiming at each building in the area to be identified;

classifying the buildings into a first building and a second building according to the first similarity and the second similarity;

aiming at each first building, calculating the number of the household air conditioners corresponding to the first building according to the corresponding outline and height of the first building and the mapping relation between the number of the first household air conditioners and the outline and height;

and aiming at each second building, calculating the number of the household air conditioners corresponding to the second building according to the corresponding outline and height of the second building and the mapping relation between the number of the second household air conditioners and the outline and height.

4. The method according to claim 2 or 3, wherein the determining the sum of the target number of the household air conditioners corresponding to each building as the total number of the household air conditioners in the area to be identified comprises:

respectively calculating a first quantity sum of target household air-conditioners corresponding to the first building and a second quantity sum of target household air-conditioners corresponding to the second building;

determining the sum of the first number sum and the second number sum as the total amount of the household air conditioners in the area to be identified.

5. The method according to any one of claims 1-3, wherein determining the outline of each building in the area to be identified from the remotely sensed image comprises:

carrying out image processing operation on the remote sensing image to obtain a processed remote sensing image, wherein the image processing operation comprises geometric correction operation and/or image fusion operation;

and inputting the processed remote sensing image into a preset contour extraction model to obtain the contour of each building.

6. A method according to any one of claims 1-3, wherein said determining the height of each building from said remote sensing images comprises:

determining shadow size information corresponding to the buildings aiming at the outlines of the buildings;

determining the position relation between a satellite and the sun when the remote sensing image is shot;

and calculating the height of the building according to the position relation and the shadow size information.

7. The method according to any one of claims 1 to 3, wherein the determining the number of the household air conditioners corresponding to each buildings along the street in the street view picture according to the at least one street view picture comprises:

inputting the street view picture into a preset household air conditioner identification model aiming at each street view picture to obtain the number of household air conditioners corresponding to buildings along the street in the street view picture;

and calculating the average value of the number of the household air conditioners corresponding to the buildings along the street in at least one street view picture, and determining the average value as the number of the household air conditioners corresponding to the buildings along the street in the area to be identified.

8. An identification device for a household air conditioner, comprising:

the device comprises an acquisition module, a recognition module and a processing module, wherein the acquisition module is used for acquiring a recognition request, and the recognition request comprises an area identifier of an area to be recognized;

the remote sensing image processing module is used for acquiring a remote sensing image corresponding to the area identifier according to the identification request, determining the outline of each building in the area to be identified according to the remote sensing image, and determining the height of each building according to the remote sensing image;

the street view picture processing module is used for acquiring at least one street view picture corresponding to the area identifier according to the identification request and determining the number of household air conditioners corresponding to each street building in the street view picture according to the at least one street view picture;

the matching module is used for determining the outline and the height of each buildings along the street in the remote sensing image according to the position information of the buildings along the street;

the determining module is used for determining the mapping relation between the number of the household air conditioners and the profile and the height according to the profile and the height corresponding to each buildings along the street and the number of the household air conditioners;

the calculation module is used for calculating the number of target household air conditioners corresponding to each building according to the outline and the height corresponding to each building aiming at each building in the area to be identified;

and the processing module is used for determining the sum of the target household air conditioner quantity corresponding to each building as the total quantity of the household air conditioners in the area to be identified.

9. An electronic device, comprising: a memory, a processor;

a memory; a memory for storing the processor-executable instructions;

wherein the processor is configured to call the program instructions in the memory to perform the home air conditioner identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored therein computer-executable instructions for implementing the home air conditioner identification method according to any one of claims 1 to 7 when executed by a processor.

Images