KR20240014806A - System and Method for estimating electric power demand through land cover information based on image recognition - Google Patents

Abstract

A power demand prediction system that can selectively apply standard load density according to object recognition feature information for infrastructure built within the complex through land cover information based on image recognition of satellite and aerial images of a new development complex is disclosed. The power capacity prediction system generates land cover information based on image recognition for the image information through an image information providing server that generates image information, and a communication network, and provides information on infrastructure to be built within a specific complex through the land cover information. It is characterized by including a power prediction server that generates power demand prediction information by selectively applying a standard load density according to object recognition feature information.

Description

{System and Method for estimating electric power demand through land cover information based on image recognition}

The present invention relates to power demand prediction technology, and more specifically, to a power demand prediction system and method for a new development complex through image recognition-based land cover information.

Recently, development complexes are being actively created in accordance with the government's national balanced development and economic revitalization policy, and the designation and development of new development complexes is continuously progressing nationwide. In addition, the number of industrial complexes is continuously increasing, and the designation of residential land districts is also steadily maintained. In order to plan power facilities for newly developed complexes and respond to changes in power demand input for development, highly reliable power for new development complexes is provided. Demand forecasting is necessary.

The existing power demand forecasting method establishes and applies standards for determining the appropriate scale of new electricity supply facilities in areas where new housing complexes and industrial complexes are being built, and mathematical formulas are applied to housing complexes by dividing them into residential land and non-residential land.

For residential land, standard load density and inequality rate are applied according to housing classification (single-family, communal) and regional classification (metropolitan area, metropolitan city, etc.), and for non-residential land, standard load density and inequality rate are applied by land use and specific building use. Apply.

In addition, since electricity demand in industrial complexes varies depending on each company's site use plan and level of technology, it is difficult to accurately predict, so standard load density standards for each industry are established and reflected in demand forecasts.

However, the existing power demand forecasting method that uses indicators such as standard load density and inequality ratio is unclear in its selection criteria, scope, and definition of base data, and the results are different every time a research study on the standards is conducted. This may lead to a decrease in the reliability of demand forecasting.

In particular, the industry-specific standard load density applied to industrial complexes is defined only for about 20 industries, making it difficult to accurately predict demand for special complexes based on new industries such as the knowledge industry and high-tech industry.

In addition, regional investment due to changes in urban composition plans, new construction, and infrastructure construction projects increases population inflow and birth rate. Therefore, demand forecasting based on urban power generation factors and power usage is necessary because economic revitalization can lead to an increase in sales, which can lead to an increase in electricity demand.

In particular, when planning infrastructure facilities where a large demand for electricity is expected in a large-scale new development complex, it is common for the construction period of the development complex to take more than 5 to 10 years, and accordingly, power facilities and demand forecasts are also planned and responded to in consideration of the mid- to long-term. It has to be.

However, in reality, existing demand forecasts can only be estimated based on publicly announced information based on the time of completion of construction, such as application area, purpose of use, and period for the entire complex size at the time of development complex construction. Therefore, it is difficult to establish sequential demand forecasts and detailed power facility plans by construction period for large-scale new development complexes.

Figure 1 is a diagram showing the concept of the power demand forecasting process for a new development complex. Referring to Figure 1, electricity demand is predicted by applying the standard load density and inequality ratio for the relevant infrastructure based on publicly announced information (construction scale, use, period) containing construction plan information.

Based on this, it is possible to establish and proceed with a plan to build power facilities, but this is a plan established only based on planning information about the early stage of development complex construction. Therefore, in the case of a development complex with a construction period of 5 to 10 years or more, like an actual large-scale complex, it is impossible to sequentially establish and proceed with mid- to long-term plans until the completion of construction.

Therefore, for adaptive power demand planning and response to new development complexes, a power demand forecasting method that is different from the power demand forecasting method based on publicly announced information according to the construction plan at the beginning of the development complex is required.

1. Republic of Korea Patent No. 10-2022-0011506

The present invention was proposed to solve the problems caused by the above background technology, and uses land cover information based on image recognition for satellite and aerial images of new development complexes to establish a standard according to object recognition feature information for infrastructure built within the complex. The purpose is to provide a power demand prediction system and method that can selectively apply load density.

In addition, the present invention provides a power demand prediction system and method that enables efficient power facility construction planning and power demand response by deriving power demand forecasts based on situational information through image recognition results for the development complex periodically during the construction period, for another purpose. There is.

In order to achieve the task presented above, the present invention selectively applies standard load density according to object recognition feature information for infrastructure built within the complex through land cover information based on image recognition of satellite and aerial images of a new development complex. Provides a power demand prediction system that can

The power acceptance prediction system is,

A video information provision server that generates video information; and

Land cover information based on image recognition of the image information is generated through a communication network, and standard load density is selectively applied according to object recognition feature information for infrastructure built in a specific complex through the land cover information to predict power demand. It is characterized in that it includes a power prediction server that generates.

Additionally, the power prediction server includes a collection module that collects the image information; a classification module for extracting image information according to location information of a new development complex from the image information and generating land cover information from the extracted image information; an object recognition module that generates object recognition feature information through the object recognition and generates power demand prediction information for each object according to the object recognition feature information; and a prediction module that generates total power demand prediction information for the new development complex by adding up the power demand prediction information for each object.

Additionally, the object recognition feature information includes the area and height of the object.

In addition, the land cover information is characterized in that it is generated by classifying a parcel in a bare land state at the initial stage of construction of the new development complex into a bare land area.

In addition, the image information is periodically collected and compared, and according to the comparison result, power demand prediction information for each object is generated based on changes in the land cover state of the object in the land cover information.

In addition, the change is characterized in that it is calculated by estimating the added area or height of the object through comparison with past image information at the beginning of the construction of the new development complex.

In addition, the power demand prediction information for each object is characterized in that it is calculated by applying a standard load density predetermined according to public information to the object recognition feature information.

In addition, the power demand prediction information for each object is the product of the area of the object and the standard load density divided by the inequality rate, or the product of the height of the object and the standard load density divided by the inequality rate. Do it as

At this time, the inequality ratio is a predetermined value that represents the relationship of received power between two or more loads.

Additionally, the image information may be satellite image information or aerial image information.

On the other hand, another embodiment of the present invention includes the steps of: (a) an image information providing server generating image information; and (b) a power prediction server generates land cover information based on image recognition for the image information through a communication network, and determines a standard load density according to object recognition feature information for infrastructure constructed within a specific complex through the land cover information. Provides a power demand prediction method through image recognition-based land cover information, comprising the step of selectively applying power demand prediction information.

At this time, step (b) includes collecting the image information by a collection module; A classification module extracting image information according to the location information of a new development complex from the image information and generating land cover information from the extracted image information; An object recognition module generating object recognition feature information through object recognition within the bare land area, and generating power demand prediction information for each object according to the object recognition feature information; And a step where the prediction module generates total power demand prediction information for the new development complex by adding up the power demand prediction information for each object.

According to the present invention, it is possible to establish an efficient plan for facility investment and period through adaptive response to the construction of power facilities required for a new development complex by referring to periodic power demand forecasts according to the development process.

In addition, another effect of the present invention is that it is possible to efficiently and quickly predict power demand even for large-scale complexes through satellite images of new development complexes, and when using the image recognition-based power demand prediction system, periodic and rapid prediction of development complexes being built nationwide is possible. One example is that it is possible to estimate comprehensive power demand forecasts.

Figure 1 is an example of the existing power demand forecasting process for a general new development complex.
Figure 2 is a block diagram of a power demand prediction system using image recognition-based land cover information according to an embodiment of the present invention.
FIG. 3 is a detailed block diagram of the power prediction server shown in FIG. 2.
Figure 4 is a flowchart showing the power demand prediction process through image recognition-based land cover information according to an embodiment of the present invention.
Figure 5 is a flowchart showing a process for predicting power demand for an object according to an embodiment of the present invention.
Figure 6 is a flowchart showing a periodic power demand prediction process through image information according to an embodiment of the present invention.
Figure 7 is a conceptual diagram of extracting object features based on image recognition according to an embodiment of the present invention.

The present invention can make various changes and have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention.

When describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

For example, a first component may be referred to as a second component, and similarly, the second component may be referred to as a first component without departing from the scope of the present invention. The term “and/or” includes any of a plurality of related stated items or a combination of a plurality of related stated items.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains.

Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application. It shouldn't be.

Hereinafter, a power demand prediction system and method using image recognition-based land cover information according to an embodiment of the present invention will be described in detail with reference to the attached drawings.

Figure 2 is a block diagram of a power demand prediction system 200 using image recognition-based land cover information according to an embodiment of the present invention. Referring to FIG. 2, the power demand prediction system 200 provides satellite image information and aerial image information through an image information providing server 210, a communication network 220, and a communication network 220 that generate satellite image information and aerial image information. A power prediction server (power prediction server) that generates land cover information based on image recognition of information and generates power demand prediction information by selectively applying standard load density according to object recognition feature information for infrastructure built within the complex through land cover information ( 230), and a terminal 240 that receives and outputs power demand prediction information from the power prediction server 230 through the communication network 220.

The image information providing server 210 performs a function of generating satellite image information and/or aerial image information. Provides a service API (Application Programming Interface) that can acquire satellite and/or aerial images. Accordingly, the power prediction server 230 can collect satellite images of the new development complex according to the location information of the new development complex in connection with this service API. Of course, the phase image server 210 may provide both location information and map information, or may provide only image information. Additionally, the image information providing server 210 may be linked to a server operated by the National Geographic Information Institute.

The communication network 220 may connect the phase image server 210, the power prediction server 230, and the terminal 240 through communication. For this purpose, the communication network 220 refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers, such as the public switched telephone network (PSTN), public switched data network (PSDN), and comprehensive information and communication network. (ISDN: Integrated Services Digital Networks), Broadband ISDN (BISDN), Local Area Network (LAN), Metropolitan Area Network (MAN), Wide LAN (WLAN), etc. This can be.

However, the present invention is not limited thereto, and includes wireless communication networks such as CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), Wibro (Wireless Broadband), WiFi (Wireless Fidelity), and DLNA (Digital Living Network Alliance). , Zigbee, Z-wave, HSDPA (High Speed Downlink Packet Access) network, Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra-wide Band, It may be a Wireless USB (Wireless Universal Serial Bus), NFC (Near Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. Alternatively, it may be a combination of these wired communication networks and wireless communication networks.

The power prediction server 230 generates land cover information based on image recognition of satellite image information and aerial image information through the communication network 220, and uses the land cover information according to object recognition feature information for infrastructure constructed within the complex. It performs the function of generating power demand prediction information by selectively applying standard load density.

The terminal 240 connects to the power prediction server 230 and performs a function of receiving and outputting power acceptance prediction information. Therefore, the terminal 240 may be a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation device, a note pad, etc. This can be. Accordingly, the terminal 240 may be configured to include a communication circuit, a display, a microprocessor, memory, etc.

FIG. 3 is a detailed block diagram of the power prediction server 230 shown in FIG. 2. Referring to FIG. 3, the power prediction server 230 includes a collection module 310 that collects image information including satellite image information and aerial image information, and extracts corresponding image information according to the location information of the new development complex from the image information. and a classification module 320 that generates land cover information by classifying the bare land area, which is a parcel in the bare land state at the beginning of the construction of a new development complex, and generates object recognition feature information through object recognition in the bare land area, and predetermined according to the land cover information. An object recognition module 330 that generates power demand prediction information for each object by applying standard load density to object recognition feature information, and a prediction that generates overall power demand prediction information for a new development complex based on the power demand prediction information for each object. It may be configured to include a module 340 and a display unit 350 that outputs total power demand prediction information.

The collection module 310 functions to collect image information including satellite image information and aerial image information. To this end, the collection module 310 may be configured to include a communication modem, microprocessor, microcomputer, memory, etc. for communication connection with the communication network 220.

The memory may be a memory provided within a microprocessor or microcomputer, or may be a separate memory. Therefore, flash memory disk (SSD: Solid State Disk), hard disk drive, flash memory, EEPROM (Electrically erasable programmable read-only memory), SRAM (Static RAM), FRAM (Ferro-electric RAM), PRAM (Phase-change RAM) ), composed of a combination of non-volatile memory such as MRAM (Magnetic RAM) and/or volatile memory such as DRAM (Dynamic Random Access Memory), SDRAM (Synchronous Dynamic Random Access Memory), DDR-SDRAM (Double Data Rate-SDRAM), etc. It can be.

The classification module 320 performs a function of generating land cover information by extracting image information according to the location information of the new development complex from the image information and classifying the bare land area, which is a section in the bare land state at the initial stage of construction of the new development complex. Images captured by satellites or aircraft can be used to create a map expressing the state of the land surface, which is called a land cover map. Depending on the classification item, there are major categories that classify urbanized dry areas, agricultural areas, etc.; depending on the major categories, for example, urbanized dry areas are classified into residential areas, industrial areas, commercial areas, etc.; middle categories, such as residential areas, etc. It is divided into subcategories that subdivide it into single-family residential areas, public residential areas, etc. Subcategories can be composed of detailed items, classification codes, and color codes.

Land cover classification is one of the most representative and typical application methods of remote sensing data, classifying the physical conditions of the land surface such as forests, grasslands, and concrete pavement. Such land cover maps best reflect the current situation of the land surface and are used as basic data for various modeling reflecting reality, contributing greatly to increasing the efficiency and scientificity of policy establishment.

The object recognition module 330 generates object recognition feature information through object recognition within the bare land area, and applies a predetermined standard load density according to land cover information to the object recognition feature information to generate power demand prediction information for each object. Perform. Object recognition feature information can be area and height.

Once object recognition is achieved, the area and height of the object (for example, a building) in the area can be estimated through a pre-machine-learned object recognition model, or the area and height of the added object can be estimated through comparison with past image information at the beginning of construction. It can be estimated. The object recognition model is an object detection algorithm that detects predetermined main objects and distinguishes them by displaying a bounding box around the objects.

The area can be calculated using the number of pixels (for example, 5 cm per pixel) within the bounding box. For example, it can be calculated as the product of the number of pixels on the x-axis and the number of pixels on the y-axis. Of course, it is also possible to do it in proportions.

Additionally, machine learning is performed using a neural network, and the neural network has a structure with several hidden layers between the input layer and the output layer. This is a method in which machines learn processing rules through data on their own and process them without humans providing procedures or rules for data processing. Neural networks may include Deep Neural Network (DNN), Convolution Neural Network (CNN), and Recurrent Neural Network (RNN).

In addition, the height characteristics of objects (e.g., buildings) can also be estimated through 3D satellite images, and power demand forecasts based on the entire development complex can be derived by reflecting the power demand characteristics of each object.

The prediction module 340 performs a function of generating overall power demand prediction information for the new development complex based on power demand prediction information for each object. In more detail, the power demand prediction information for each object generated by the object recognition module 330 is added to generate comprehensive overall power demand prediction information for the new development complex.

The display unit 350 performs a function of outputting total power demand prediction information. Additionally, an information processing screen, settings screen, information guidance screen, etc. are output. To this end, the display unit 350 may be configured to include a display and a sound system. Displays include LCD (Liquid Crystal Display), LED (Light Emitting Diode) display, PDP (Plasma Display Panel), OLED (Organic LED) display, touch screen, CRT (Cathode Ray Tube), flexible display, micro LED, and mini LED. It can be etc. In the case of a touch screen, it can also be used as an input method.

The classification module 320, object recognition module 330, prediction module 340, etc. shown in FIG. 3 refers to a unit that processes at least one function or operation, and can be implemented in software and/or hardware. there is. In hardware implementation, an application specific integrated circuit (ASIC), digital signal processing (DSP), programmable logic device (PLD), field programmable gate array (FPGA), processor, microprocessor, and other devices designed to perform the above-described functions. It may be implemented as an electronic unit or a combination thereof.

In software implementation, software composition components (elements), object-oriented software composition components, class composition components and task composition components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, data. , databases, data structures, tables, arrays, and variables. Software, data, etc. can be stored in memory and executed by a processor. The memory or processor may employ various means well known to those skilled in the art.

Figure 4 is a flowchart showing the power demand prediction process through image recognition-based land cover information according to an embodiment of the present invention. Referring to FIG. 4, video information of the new development complex according to the location information of the new development complex is collected in connection with the service API provided to the video information providing server 210 (steps S410 and S420). To elaborate, among the collected video information, video information of the new development complex is extracted according to the location information of the new development complex.

Afterwards, image processing is performed on this image information (step S430). In other words, image processing techniques are used to classify sections of bare land in the early stage of construction in the area and recognize objects within the new development complex (steps S431 and S432). In other words, the development area and section are classified through image processing techniques for image information (satellite image or aerial image) of the new development complex provided from the service API, and the new object is classified through a pre-trained object recognition model for object recognition. Estimate the area of buildings within the development complex or estimate the area of added buildings through comparison with past images at the beginning of construction.

In addition, the height characteristics of buildings (objects) can also be estimated through satellite 3D images, and by reflecting the power demand characteristics of each object, it is possible to derive power demand forecasts based on the entire development complex.

In addition, the land cover status of the object is analyzed from the land cover information through comparison of periodically collected satellite images and image recognition, and the object according to the change in the object (e.g., building) (i.e., height change, area change) Estimate the power demand forecast for each star (step S440).

For buildings with expected power demand, individual demand forecasts are calculated by reflecting the power demand characteristics of each object through image-based object recognition, and finally, the total power demand for the new development complex is calculated by summing the power demand forecasts for each object. Generates overall power demand forecast information that estimates the forecast.

Figure 5 is a flowchart showing a process for predicting power demand for an object according to an embodiment of the present invention. Referring to FIG. 5, video information of the development complex according to the location information of the new development complex is collected in connection with the service API provided to the video information provision server 210, and image processing is performed on this video information to create a new Classify the area of the development complex (step S510).

Afterwards, image processing techniques are used to classify the sections in the initial state of bare land in the area, and to recognize objects within the new development complex (step S511).

Afterwards, object recognition feature information is calculated for the recognized object (step S513).

Meanwhile, public information on new development complexes is obtained and uses for residential, non-residential, industrial complexes, etc. are confirmed (steps S520 and S521).

Here, land use classification based on public information can generally be confirmed as a single use for the entire development complex, but in the case of land cover information subdivided into unit parcels, land use can be classified by subdividing according to various parcels within the large complex. When applying various land uses, power demand prediction results based on land classification can be used in more detail.

Once it is confirmed whether the new development complex falls under residential land, non-residential land, or industrial complex land, the standard load density for each use is calculated, and the calculated standard load density for each use is applied to the object recognition feature information to provide power demand prediction information for each object. Generate (steps S523, S530). In other words, the standard load density for each purpose can be applied to the area and height information extracted through object recognition to modify and transform the existing mathematical equation for power demand prediction to estimate the power demand forecast for each object. The equation for predicting existing power demand is as follows.

Here, the standard load density for each application is a predetermined value. The inequality rate is a predetermined value that represents the relationship between the received power between two or more loads and indicates the degree to which power consumption devices are used simultaneously.

In detail, the object power demand (W) is the product of the object's area and its standard load density divided by the inequality rate. Alternatively, it is the product of the height of the object and its standard load density divided by the inequality rate.

Finally, the predicted power demand for the new development complex is derived by summing the predicted power demand for each object (step S540).

Figure 6 is a flowchart showing a periodic power demand prediction process through image information according to an embodiment of the present invention. Referring to FIG. 6, a construction plan for a new development complex is established, and public information about the new development complex is obtained (steps S610 and S620).

Afterwards, the power demand forecast is calculated based on the publicly announced information (step S630). To calculate the power acceptance prediction value, image information is acquired, power demand prediction value is calculated through this image information, and power facilities are built accordingly (steps S631, S632, and S633).

Of course, at each planning stage, satellite images of the development complex can be periodically collected from the video service API to estimate power demand forecasts based on image recognition-based land cover information.

Therefore, unlike the method of estimating the predicted power demand at the time of construction completion using only existing publicly announced information, satellite images or aerial images (i.e., image information measured using aircraft) are acquired at preset intervals or key points in time for the relevant area. Power demand forecasts can be reviewed at any time, and based on this, power facility construction plans and responses according to demand forecasts can be adaptively performed.

Figure 7 is a conceptual diagram of extracting object features based on image recognition according to an embodiment of the present invention. Referring to Figure 7, this is an example showing object recognition results according to construction progress (steps S710, S720, and S730) in a new development complex through a pre-trained object recognition model.

Even in the state where foundation construction is in progress, the power demand forecast for each object can be calculated by referring to the placement location of each object in area 701, and the power demand forecast for each object can be added to calculate the power demand forecast for the new development complex. It can be done (steps S710, S711, S713).

Extract the features of the object (702) for the area (701) where development is in progress through an object recognition model pre-trained using an image database for residential and industrial areas, etc., which is used to extract land cover information based on image recognition. (i.e., object recognition feature information) is possible (step S720). Of course, in this case as well, the predicted power demand for each object can be added to calculate the predicted power demand for the new development complex (steps S721 and S723).

When extracting the area by area, the integrated area 703 can be estimated by combining only the outer boundary lines using the extracted area and location information for each object (step S730). Of course, in this case as well, the predicted power demand for the new development complex can be calculated by adding up the predicted power demand for each object (steps S731 and S733).

Even while development is in progress, if the power demand forecast is calculated, a power facility construction plan is established based on this and responses are made according to this plan (step S740).

Additionally, the steps of the method or algorithm described in relation to the embodiments disclosed herein are implemented in the form of program instructions that can be executed through various computer means such as a microprocessor, processor, CPU (Central Processing Unit), etc., and are computer readable. Can be recorded on any available medium. The computer-readable medium may include program (instruction) codes, data files, data structures, etc., singly or in combination.

The program (instruction) code recorded on the medium may be specially designed and constructed for the present invention, or may be known and usable by those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROM, DVD, Blu-ray, and ROM (Read Only Memory). ), RAM (Random Access Memory), flash memory, etc. may include specially configured semiconductor memory elements to store and execute program (instruction) codes.

Here, examples of program (instruction) code include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

200: Power demand prediction system
210: Video information provision server
220: communication network
230: Power prediction server
240: terminal
310: collection module
320: Classification module
330: Object recognition module
340: prediction module
350: display unit
701: Zone
702: Object
703: Integrated area

Claims (18)

An image information providing server 210 that generates image information; and
Land cover information based on image recognition of the image information is generated through the communication network 220, and standard load density is selectively applied according to object recognition feature information for infrastructure constructed in a specific complex through the land cover information to generate power. Power prediction server 230 that generates demand prediction information;
A power demand prediction system using image recognition-based land cover information, comprising:
According to claim 1,
The power prediction server 230,
A collection module 310 that collects the image information;
a classification module 320 that extracts image information according to the location information of a new development complex from the image information and generates land cover information from the extracted image information;
An object recognition module 330 that generates object recognition feature information through object recognition and generates power demand prediction information for each object according to the object recognition feature information; and
A prediction module 340 that generates total power demand prediction information for the new development complex by adding up the power demand prediction information for each object. A power demand prediction system using image recognition-based land cover information.
According to claim 2,
A power demand prediction system using image recognition-based land cover information, wherein the object recognition feature information includes the area and height of the object.
According to claim 2,
The land cover information is a power demand prediction system through image recognition-based land cover information, characterized in that it is generated by classifying a parcel in a bare land state at the beginning of the construction of the new development complex into a bare land area.
According to claim 2,
The image information is periodically collected and compared, and according to the comparison result, power demand prediction information for each object is generated based on changes in the land cover status of the object in the land cover information. Power demand prediction system using covering information. According to claim 5,
The change is calculated by estimating the added area or height of the object through comparison with past image information at the beginning of the construction of the new development complex. A power demand prediction system through image recognition-based land cover information.
According to claim 6,
The power demand prediction information for each object is calculated by applying a standard load density predetermined according to public information to the object recognition feature information. A power demand prediction system through image recognition-based land cover information.
According to claim 7,
The power demand prediction information for each object is the product of the area of the object and the standard load density divided by the inequality rate, or the product of the height of the object and the standard load density divided by the inequality rate, and the inequality rate is a power demand prediction system using image recognition-based land cover information, characterized in that it represents the relationship of received power between two or more loads with a predetermined value.
According to claim 1,
A power demand prediction system using image recognition-based land cover information, wherein the image information is satellite image information or aerial image information.
(a) the video information providing server 210 generating video information; and
(b) The power prediction server 230 generates land cover information based on image recognition for the image information through the communication network 220, and provides object recognition feature information for infrastructure built within a specific complex through the land cover information. generating power demand prediction information by selectively applying a standard load density;
A method for predicting power demand through image recognition-based land cover information, comprising:
According to claim 10,
In step (b),
Collecting the image information by the collection module 310;
The classification module 320 extracts corresponding image information according to the location information of a new development complex from the image information and generates land cover information from the extracted corresponding image information;
The object recognition module 330 generates object recognition feature information through object recognition, and generates power demand prediction information for each object according to the object recognition feature information; and
Predicting power demand through image recognition-based land cover information, wherein the prediction module 340 generates overall power demand prediction information for the new development complex by adding up the power demand prediction information for each object. method.
According to claim 11,
A power demand prediction method using image recognition-based land cover information, wherein the object recognition feature information includes the area and height of the object.
According to claim 11,
The land cover information is a method for predicting power demand through image recognition-based land cover information, characterized in that the land cover information is generated by classifying a parcel in a bare land state at the initial stage of construction of the new development complex into a bare land area.
According to claim 11,
The image information is periodically collected and compared, and according to the comparison result, power demand prediction information for each object is generated based on changes in the land cover status of the object in the land cover information. Electricity demand prediction method using land cover information.
According to claim 14,
The change is calculated by estimating the added area or height of the object through comparison with past image information at the beginning of the construction of the new development complex. A power demand prediction method through image recognition-based land cover information.
According to claim 15,
The power demand prediction information for each object is calculated by applying a standard load density predetermined according to public information to the object recognition feature information. A power demand prediction method through image recognition-based land cover information.
According to claim 16,
The power demand prediction information for each object is the product of the area of the object and the standard load density divided by the inequality rate, or the product of the height of the object and the standard load density divided by the inequality rate, and the inequality rate is a method for predicting power demand through image recognition-based land cover information, characterized in that it represents the relationship of received power between two or more loads with a predetermined value.
According to claim 10,
A method for predicting power demand through image recognition-based land cover information, wherein the image information is satellite image information or aerial image information.