CN116363590A - Energy-saving carbon reduction control method and system for public institution - Google Patents

Abstract

The invention discloses an energy-saving carbon reduction control method and system for public institutions. Two public institution images are obtained. And converting the two public institution images from RGB to HSV to obtain two corresponding converted images. And inputting the two converted images into a detection model to obtain detection information. Based on the detection information, intelligent control is performed through an intelligent control structure, and control information is obtained. By using the image detection method, the illumination and the existence of people are detected, so that the resource waste can be reduced, and the cost can be saved. The illumination can be detected according to the brightness of the image, and the existence condition and the illumination condition of people in the whole area can be judged in a large range, so that the judgment is more accurate. And subtracting the brightness of the corresponding position in the current illumination image from the fixed light brightness, so that the corresponding brightness required to be adjusted is obtained, and the light brightness is intelligently controlled to meet the brightness requirement.

Description

Energy-saving carbon reduction control method and system for public institution

Technical Field

The invention relates to the technical field of computers, in particular to an energy-saving carbon reduction control method and system for public institutions.

Background

The existing energy-saving and emission-reducing management methods of most public institutions still depend on manual management and control, such as illumination control of office places, air-conditioning temperature standard establishment and the like, are seriously dependent on-site management staff, the requirements on public energy management staff are high, the environment changes are fluctuant in the energy consumption process, different management methods are required to be established for different environments, the management methods become more complex, the dependence on manual management is far from, and in the future, large public buildings still need to rely on more automatic, more intelligent and more scientific management modes to effectively solve the current problems.

Disclosure of Invention

The invention aims to provide an energy-saving carbon reduction control method and system for public institutions, which are used for solving the problems in the prior art.

In a first aspect, an embodiment of the present invention provides a method for controlling energy-saving and carbon reduction of an public institution, including:

obtaining two public institution images; the two public institution images comprise a first public institution image and a second public institution image; the public institution images are images shot by monitoring at two different positions in the same public space;

Converting the two public institution images from RGB to HSV to obtain two corresponding converted images; the two converted images comprise a first converted image and a second converted image;

inputting the two converted images into a detection model to obtain detection information; the detection information comprises a current illumination image and a current human existence value; the current human existence value of 1 indicates that people exist in the public institution;

based on the detection information, performing intelligent control through an intelligent control structure to obtain control information; the control information comprises an air conditioner temperature value and an illumination control value;

the detection model comprises an illumination detection structure and a human body detection network.

Optionally, the inputting the two converted images into a detection model to obtain detection information includes:

extracting brightness from the two converted images to obtain two brightness images; the two brightness images comprise a first brightness image and a second brightness image; the brightness image is an image of a brightness channel in the converted image;

inputting the two brightness images into an illumination detection structure to obtain a current illumination image;

and inputting the two converted images into a human body detection network to obtain the current human body existence value.

Optionally, inputting the two brightness images into an illumination detection structure to obtain a current illumination image, including:

dividing the first brightness image into areas to obtain a first area image;

dividing the second brightness image into areas to obtain a second area image;

obtaining a superposition area; the overlapping area comprises an overlapping illumination area and an overlapping dimming area; the overlapping area is an area where the overlapping part of the first area image and the second area image is located;

dividing the sum of the value of the coincident illumination area in the first area image and the value of the coincident illumination area in the second area image by 2 to obtain a coincident illumination mean value;

dividing the sum of the value of the coincident dark region in the first region image and the value of the coincident dark region in the second region image by 2 to obtain a coincident dark mean value;

and replacing the value of the coincident illumination area in the first area image with the coincident illumination mean value, and replacing the value of the coincident dark area in the first area image with the coincident dark mean value to obtain the current illumination image.

Optionally, the dividing the first brightness image into areas to obtain a first area image includes:

Dividing the median value of the first brightness image into areas according to the position of the illumination threshold value to obtain a divided area; the segmented regions include illuminated regions and darkened regions;

obtaining an illumination area mean value; the illumination area mean value is the mean value of the values in the illumination area;

obtaining a dim area mean; the dim zone mean is the mean of the values in the dim zone;

and replacing the average value of the illumination area and the average value of the dim area according to the illumination area and the dim area corresponding to the first brightness image to obtain a first area image.

Optionally, the dividing the median of the first brightness image into regions according to the position of the illumination threshold to obtain the divided regions includes:

obtaining a first brightness set; the value in the first brightness set is the position of the median of the first brightness image which is larger than the illumination threshold value;

obtaining a first boundary set; the first boundary set is a boundary value in the first brightness set;

performing function fitting on the values in the first boundary set to obtain a boundary curve;

and taking the boundary curve as a boundary to obtain an illumination area.

Optionally, the training method of the human body detection network includes:

Obtaining a training set; the training set comprises a plurality of training images and a plurality of annotation data; the training image is an image containing a person; the labeling data comprises labeling human existence values and labeling human existence positions; the labeled human existence value is 1 to indicate that a human exists; the labeled human existence value of 0 indicates that no human exists;

inputting the training image into a human body detection network to obtain training human body information; the training human body information comprises a training human body existence value and a training human body existence position;

inputting the training human existence value and the labeling human existence value into a loss function to obtain a loss value;

obtaining the current training iteration times of a human body detection network and the preset maximum iteration times of the human body detection network training;

and stopping training when the loss value is smaller than or equal to a threshold value or the training iteration number reaches the maximum iteration number, and obtaining the trained human body detection network.

Optionally, based on the detection information, the intelligent control is performed through an intelligent control structure to obtain control information, including:

obtaining a time period value; the period value of 1 is represented as an operating period; the period value of 0 represents a non-operating period;

Obtaining a default specified range; the default specified ranges include an air quality default specified range and a temperature default specified range;

obtaining air quality; the air quality is the air quality of the current public institution;

obtaining a temperature; the temperature is the temperature of the current public institution;

if the time period value is 1, working time period control information is obtained based on the detection information, the temperature, the air quality and a default specified range; the working period control information comprises an air purifier signal, an air conditioner signal and a lamplight illumination value;

if the time period value is 0, acquiring non-working time period control information based on the detection information, the temperature, the air quality and a default specified range; the non-working period control information is control information obtained in a non-working period; the non-working period control information comprises an air purifier signal, an air conditioner signal, a lamplight illumination value and energy consumption data; the energy consumption data comprise air purifier energy consumption data, air conditioner energy consumption data and lamplight energy consumption data.

Optionally, if the period value is 1, working period control information is obtained based on the detection information, the temperature, the air quality and a default specified range, including:

If the human existence value is 1 and the air quality is not in the default specified range of the air quality, setting the air purifier signal to be 1; an air purifier signal of 1 indicates that the air purifier is on;

if the human existence value is 1 and the temperature is not in the default specified range of the temperature, setting the air conditioning signal to be 1; the air conditioner signal being 1 indicates that the air conditioner is turned on;

if the human existence value is 1, a first lamplight illumination value is obtained; the light illumination value is obtained by subtracting the brightness difference of the corresponding position in the current illumination image from the fixed light brightness;

if the human existence value is 0, or the air quality is within the air quality default specified range, setting the air purifier signal to be 0; the air purifier signal being 0 indicates that the air purifier is off;

if the human existence value is 0, or the temperature is within a default specified range of temperature, setting the air conditioning signal to be 0; the air conditioner signal being 0 indicates that the air conditioner is turned off;

if the human existence value is 0, setting the light illumination value to 0; the light illumination value of 0 indicates that the light is turned off.

Optionally, if the period value is 0, the non-working period control information is obtained based on the detection information, the temperature, the air quality and a default specified range, and the method includes:

If the human existence value is 1 and the air quality is not in the default specified range of the air quality, setting the air purifier signal as 1 to obtain the energy consumption of the first air purifier; the energy consumption of the first air purifier is the energy consumption for starting the air purifier;

if the human existence value is 1 and the temperature is not in the default specified range, obtaining the energy consumption of the first air conditioner; the energy consumption of the first air conditioner is the energy consumption for starting the air conditioner;

if the human existence value is 1, a first lamplight illumination value is obtained; the first lamplight illumination value is obtained by subtracting the brightness of the corresponding position in the current illumination image from the fixed lamplight brightness;

if the human existence value is 0, or the air quality is within the air quality default specified range, setting the air purifier signal to be 0; the air purifier on signal being 0 indicates that the air purifier is off;

if the human existence value is 0, or the temperature is within a default specified range of temperature, setting the air conditioning signal to be 0;

if the human existence value is 0, setting the light illumination value to 0;

obtaining an energy consumption value through a plurality of times if the human existence value is 1; the energy consumption values comprise a plurality of air purifier energy consumption values, a plurality of air conditioner energy consumption values and a plurality of lamplight illumination values until the human existence value is 0; adding the energy consumption values of the air purifier to obtain energy consumption data values of the air purifier; adding the energy consumption values of the air conditioner to obtain energy consumption data of the air conditioner; and adding the light illumination values to obtain light energy consumption data.

In a second aspect, an embodiment of the present invention provides an energy-saving carbon reduction control system for an public institution, including:

the acquisition module is used for: obtaining two public institution images; the two public institution images comprise a first public institution image and a second public institution image; the public institution images are images shot by monitoring at two different positions in the same public space;

and a conversion module: converting the two public institution images from RGB to HSV to obtain two corresponding converted images; the two converted images comprise a first converted image and a second converted image;

human body and illumination condition detection module: inputting the two converted images into a detection model to obtain detection information; the detection information comprises a current illumination image and a current human existence value; the current human existence value of 1 indicates that people exist in the public institution;

and the intelligent control module: based on the detection information, performing intelligent control through an intelligent control structure to obtain control information; the control information comprises an air conditioner temperature value and an illumination control value;

the detection model comprises an illumination detection structure and a human body detection network

Compared with the prior art, the embodiment of the invention achieves the following beneficial effects:

The embodiment of the invention also provides a method and a system for controlling the energy-saving carbon reduction of the public institution, wherein the method comprises the following steps: two public institution images are obtained. The two public institution images include a first public institution image and a second public institution image. The public institution image is an image shot by monitoring two different positions in the same public space. And converting the two public institution images from RGB to HSV to obtain two corresponding converted images. The two converted images include a first converted image and a second converted image. And inputting the two converted images into a detection model to obtain detection information. The detection information comprises a current illumination image and a current human body existence value. The current human presence value of 1 indicates the presence of a human in the institution. Based on the detection information, intelligent control is performed through an intelligent control structure, and control information is obtained. The control information comprises an air conditioner temperature value and an illumination control value. The detection model comprises an illumination detection structure and a human body detection network.

By using the image detection method, the illumination and the existence of people are detected, so that the resource waste can be reduced, and the cost can be saved. The illumination can be detected according to the brightness of the image, and the existence condition and the illumination condition of people in the whole area can be judged in a large range, so that the judgment is more accurate. And the overlapping area is adjusted by combining two images, so that the influence of the image angle position on illumination judgment is reduced. The brightness of sunlight projected through the window is almost the same, and the indoor is segmented into an illumination area and a dark area due to the blocking of the building, so that the illumination threshold is used for segmentation of the area, thereby not only conforming to the real life condition, but also being convenient for later calculation. Training is performed using the modified convolutional network to detect the presence of a person. And in the working time period, under the condition of default specified range, the control operation is carried out according to the detection information, the temperature and the air quality, and in the non-working time period, the energy consumption condition is recorded as well as the control operation. And subtracting the brightness of the corresponding position in the current illumination image by using the fixed light brightness, thereby obtaining the corresponding brightness to be adjusted, and intelligently controlling the light brightness to meet the brightness requirement.

When artificial intelligence big data age, through introducing intelligent management means, help public institution to carry out effective management and control in the energy consumption in-process, can also carry out real-time accounting to public institution's carbon emission simultaneously, combine energy-conserving carbon reduction index to show in daily, give full play to public institution's first demonstration effect, promote climate change and energy-conserving low carbon consciousness, guide public green low carbon life style. If the indoor human body sensor monitors that a person works in the area, the indoor intelligent sensing device is started, the indoor air conditioning running state is automatically adjusted by combining the outdoor temperature condition and various data of the indoor intelligent sensing device in the area, and the indoor air conditioning equipment is in an optimal energy-saving running mode.

Drawings

Fig. 1 is a flowchart of an energy-saving carbon reduction control method for public institutions, which is provided by the embodiment of the invention.

Fig. 2 is a schematic diagram of a current illumination area image structure obtained in an energy-saving and carbon reduction control system of a public institution according to an embodiment of the present invention.

Fig. 3 is a schematic block diagram of an electronic device according to an embodiment of the present invention.

The marks in the figure: a bus 500; a receiver 501; a processor 502; a transmitter 503; a memory 504; bus interface 505.

Detailed Description

The present invention will be described in detail with reference to the accompanying drawings.

Example 1

As shown in fig. 1, the embodiment of the invention provides an energy-saving carbon reduction control method for public institutions, which comprises the following steps:

s101: obtaining two public institution images; the two public institution images comprise a first public institution image and a second public institution image; the public institution image is an image shot by monitoring two different positions in the same public space.

Wherein the two different position monitors are a first monitor and a second monitor.

S102: converting the two public institution images from RGB to HSV to obtain two corresponding converted images; the two converted images comprise a first converted image and a second converted image;

s103: inputting the two converted images into a detection model to obtain detection information; the detection information comprises a current illumination image and a current human existence value; the current human existence value of 1 indicates that people exist in the public institution;

s104: based on the detection information, performing intelligent control through an intelligent control structure to obtain control information; the control information comprises an air conditioner temperature value and an illumination control value;

The detection model comprises an illumination detection structure and a human body detection network.

Optionally, the inputting the two converted images into a detection model to obtain detection information includes:

and extracting brightness from the two converted images to obtain two brightness images. The two brightness images include a first brightness image and a second brightness image. The brightness image is an image of a brightness channel in the converted image.

And inputting the two brightness images into an illumination detection structure to obtain a current illumination image.

And inputting the two converted images into a human body detection network to obtain the current human body existence value.

By the method, the intelligent control is required to be performed according to the existence of the person and the illumination degree during the intelligent control, and the judgment cost is increased if the judgment is performed respectively. For example, a person is identified by using a temperature sensor, etc., and the illumination is tested by using an illumination intensity testing instrument, etc., so that a plurality of hardware is required to be purchased for judgment, and the person cannot be identified in a large range. By using the image detection method, the images can be used for detecting illumination and whether people exist or not, so that the resource waste can be reduced, and the cost can be saved. And the brightness of the image represents the brightness degree of the color, and for the light source color, the brightness value is related to the brightness of the illuminant, and the existence condition and the illumination condition of people in the whole area can be judged in a large range according to the image, so that the judgment is more accurate.

Optionally, inputting the two brightness images into an illumination detection structure to obtain a current illumination image, including:

and dividing the first brightness image into areas to obtain a first area image.

And dividing the second brightness image into areas to obtain a second area image.

Obtaining a superposition area; the overlapping region includes an overlapping illumination region and an overlapping dimming region. The overlapping area is an area where the overlapping part of the first area image and the second area image is located.

And dividing the sum of the value of the coincident illumination area in the first area image and the value of the coincident illumination area in the second area image by 2 to obtain a coincident illumination mean value.

And dividing the sum of the value of the coincident dark region in the first region image and the value of the coincident dark region in the second region image by 2 to obtain a coincident dark mean value.

And replacing the value of the coincident illumination area in the first area image with the coincident illumination mean value, and replacing the value of the coincident dark area in the first area image with the coincident dark mean value to obtain the current illumination image.

The image structure of the current illumination area is shown in fig. 2, and a coincident illumination area and a coincident darkness area exist.

According to the method, the partial areas can not be detected due to the monitoring image, and the obtained pictures can generate small gaps due to different positions, so that the overlapping areas are adjusted by combining the two images, the influence of the angle position on illumination judgment is reduced, brightness in the image is obtained more accurately, and the illumination degree is obtained.

Optionally, the dividing the first brightness image into areas to obtain a first area image includes:

and dividing the median value of the first brightness image into areas according to the position of the illumination threshold value to obtain a divided area. The segmented regions include illuminated regions and darkened regions.

In this embodiment, the illumination threshold is 0.1.

And obtaining the average value of the illumination area. The illumination area mean is a mean of values in the illumination area.

A dim zone mean is obtained. The dim zone mean is the mean of the values in the dim zone.

And replacing the average value of the illumination area and the average value of the dim area according to the illumination area and the dim area corresponding to the first brightness image to obtain a first area image.

By the above method, the illumination projected by natural light, typically sunlight, through a window is almost the same, and the indoor is divided into an illuminated area and a dim area due to the blocking of a building. The illumination threshold is used for segmentation, and the illumination area mean value is used for replacing the illumination area value, and the dim area mean value is used for replacing the dim area value, so that the method meets real life conditions and is convenient for later calculation.

Optionally, the dividing the median of the first brightness image into regions according to the position of the illumination threshold to obtain the divided regions includes:

a first set of brightness is obtained. The values in the first set of brightness are locations where the first brightness image median is greater than an illumination threshold.

In this embodiment, the illumination threshold is 10%.

A first set of boundaries is obtained. The first set of boundaries are boundary values in the first set of brightness.

And comparing to obtain a boundary value, wherein the boundary value is a value of which the width of the same height position is larger than other boundary values and the width of the same height position is smaller than other boundary values.

And performing function fitting on the values in the first boundary set to obtain a boundary curve.

Wherein, the function fitting adopts a cubic spline fitting algorithm for fitting.

And taking the boundary curve as a boundary to obtain an illumination area.

In this embodiment, the area above the boundary curve is the illumination area.

By the above method, since the boundary points obtained above the illumination threshold are not points on the complete curve, sometimes even far from the boundary curve, fitting is required to construct the boundary curve from the boundary points, and the boundary curve is divided into two parts.

Optionally, the training method of the human body detection network includes:

obtaining a training set; the training set comprises a plurality of training images and a plurality of annotation data; the training image is an image containing a person. The labeling data comprises labeling human existence values and labeling human existence positions; the labeled human existence value of 1 indicates that a human exists. The labeled human presence value of 0 indicates that no human is present.

Inputting the training image into a human body detection network to obtain training human body information; the training human body information includes a training human body presence value and a training human body presence location.

Wherein, the yolov5 is used for detection, and the output is changed into 1 value representing the existence of the human body, and 4 values representing the existence position of the human body, namely a central point and a width and height.

And inputting the training human existence value and the labeling human existence value into a loss function to obtain a loss value.

The method comprises the steps of obtaining the current training iteration times of a human body detection network and obtaining the preset maximum iteration times of the human body detection network training.

The maximum iteration number of the human body detection network training preset in the embodiment is 12000.

And stopping training when the loss value is smaller than or equal to a threshold value or the training iteration number reaches the maximum iteration number, and obtaining the trained human body detection network.

By the method, the convolutional network is modified, so that a detection network which is more accurate and accords with a detection target is obtained, a trained human body detection network is used, and whether a person exists or not is detected by adopting an image for detecting illumination.

Optionally, based on the detection information, the intelligent control is performed through an intelligent control structure to obtain control information, including:

a period value is obtained. The period value of 1 is represented as an operating period; the period value of 0 represents a non-operating period.

A default prescribed range is obtained. The default specified ranges include an air quality default specified range and a temperature default specified range.

Air quality is obtained. The air quality is the air quality of the current public institution.

The temperature is obtained. The temperature is the temperature of the current institution.

In this embodiment, the default temperature range is greater than 10 degrees celsius and less than 30 degrees celsius, and the default air quality range is greater than 100.

If the time period value is 1, working time period control information is obtained based on the detection information and a default specified range; the operating period control information includes an air cleaner signal, an air conditioning signal, and a light illumination value.

If the time period value is 0, acquiring non-working time period control information based on the detection information and a default specified range; the non-working period control information is control information obtained in a non-working period; the non-working period control information comprises an air purifier signal, an air conditioner signal, a lamplight illumination value and energy consumption data; the energy consumption data comprise air purifier energy consumption data, air conditioner energy consumption data and lamplight energy consumption data.

By the method, the control operation is performed according to the detection information under the condition of the default specified range in the working time period, and the energy consumption condition is recorded when the control operation is performed in the non-working time period. The default prescribed range is used, and the air quality, the temperature and the detection information are combined to perform intelligent control.

Optionally, if the period value is 1, working period control information is obtained based on the detection information, the temperature, the air quality and a default specified range, including:

if the human presence value is 1 and the air quality is not within the air quality default prescribed range, the air purifier signal is set to 1. An air purifier signal of 1 indicates that the air purifier is on.

If the human presence value is 1 and the temperature is not within the temperature default predetermined range, the air conditioning signal is set to 1. The air conditioner signal of 1 indicates that the air conditioner is on.

And if the human existence value is 1, obtaining a lamplight illumination value. The light illumination value is the difference of the fixed light brightness minus the brightness of the corresponding position in the current illumination image.

In this embodiment, the brightness of the light is fixed to be 70%, and the light is controlled by using the illumination degree corresponding to the brightness.

If the human presence value is 0, or the air quality is within the air quality default prescribed range, the air purifier signal is set to 0. The air purifier signal of 0 indicates that the air purifier is off.

If the human existence value is 0, or the temperature is within a default specified range of temperature, setting the air conditioning signal to be 0; the air conditioner signal being 0 indicates that the air conditioner is off.

If the human existence value is 0, setting the light illumination value to 0; the light illumination value of 0 indicates that the light is turned off.

By the method, when someone exists, if the air quality and the temperature do not meet the default specified range, the air purifier and the air conditioner are controlled to be started, and the brightness is adjusted according to the illumination condition caused by the brightness of the corresponding position in the current illumination image. However, if no one is present, or the air quality and temperature meet the default specified ranges, the air purifier and the air conditioner are controlled to be turned off. If no, turning off the light, and controlling intelligently.

Optionally, if the period value is 0, the non-working period control information is obtained based on the detection information, the temperature, the air quality and a default specified range, and the method includes:

if the human existence value is 1 and the air quality is not in the default specified range of the air quality, setting the air purifier signal as 1 to obtain the energy consumption of the first air purifier; the energy consumption of the first air purifier is the energy consumption for starting the air purifier.

If the human existence value is 1 and the temperature is not in the default specified range, obtaining the energy consumption of the first air conditioner; the energy consumption of the first air conditioner is the energy consumption for starting the air conditioner.

If the human existence value is 1, a first lamplight illumination value is obtained; the first lamplight illumination value is obtained by subtracting the brightness of the corresponding position in the current illumination image from the fixed lamplight brightness.

In this embodiment, the brightness of the light is fixed to be 70%, and the light is controlled by using the illumination degree corresponding to the brightness.

If the human existence value is 0, or the air quality is within the air quality default specified range, setting the air purifier signal to be 0; the air purifier on signal of 0 indicates that the air purifier is off.

If the human existence value is 0 or the temperature is within a temperature default prescribed range, the air conditioning signal is set to 0.

If the human existence value is 0, the lamplight illumination value is set to 0.

Obtaining an energy consumption value through a plurality of times if the human existence value is 1; the energy consumption values comprise a plurality of air purifier energy consumption values, a plurality of air conditioner energy consumption values and a plurality of lamplight illumination values until the human existence value is 0; adding the energy consumption values of the air purifier to obtain energy consumption data values of the air purifier; adding the energy consumption values of the air conditioner to obtain energy consumption data of the air conditioner; and adding the light illumination values to obtain light energy consumption data.

By the method, not only is the control operation performed in the non-working period, but also the energy consumption condition is recorded.

By the method, the intelligent control is required according to the existence of the person and the illumination degree, so that the judgment cost is increased when the intelligent control is respectively judged, a plurality of hardware is required to be purchased for judgment, and the intelligent control cannot be recognized in a large range. By using the image detection method, the images can be used for detecting illumination and whether people exist or not, so that the resource waste can be reduced, and the cost can be saved. And the brightness of the image represents the brightness degree of the color, and for reflection, the brightness value is related to the brightness of the illuminant, and the existence condition and the illumination condition of people in the whole area can be judged in a large range according to the image, so that the judgment is more accurate. And the overlapping area is adjusted by combining the two images, so that the influence of the angle position on illumination judgment is reduced, the brightness in the image is obtained more accurately, and the illumination degree is obtained. The illumination projected by natural light, typically sunlight, through a window is nearly identical, and the room is segmented into illuminated and darkened areas due to the obstruction of the building. The illumination threshold is used for segmentation, and the illumination area mean value is used for replacing the illumination area value, and the dim area mean value is used for replacing the dim area value, so that the method meets real life conditions and is convenient for later calculation. For human body detection, the convolution network is modified, so that a detection network which is more accurate and accords with a detection target is obtained, a trained human body detection network is used, and whether a person exists or not is detected by adopting an image of detection illumination. And in the working time period, under the condition of default specified range, the control operation is carried out according to the detection information, and in the non-working time period, the energy consumption condition is recorded as well as the control operation. The default specified range is used, the air quality, the temperature and the detection information are combined to perform intelligent control, the brightness of the corresponding position in the current illumination image is subtracted from the fixed light brightness, so that the corresponding brightness to be adjusted is obtained, and the light brightness is intelligently controlled to meet the brightness requirement.

Example 2

Based on the energy-saving carbon reduction control method of the public institution, the embodiment of the invention also provides an energy-saving carbon reduction control system of the public institution, which comprises an acquisition module, a conversion module, a human body and illumination condition detection module and an intelligent control module.

The acquisition module is used for acquiring two public institution images. The two public institution images include a first public institution image and a second public institution image. The public institution image is an image shot by monitoring two different positions in the same public space.

The conversion module is used for converting the two public institution images from RGB to HSV to obtain two corresponding conversion images. The two converted images include a first converted image and a second converted image.

The human body and illumination condition detection module is used for inputting the two converted images into a detection model to obtain detection information. The detection information comprises a current illumination image and a current human body existence value. The current human presence value of 1 indicates the presence of a human in the institution.

And the intelligent control module: based on the detection information, intelligent control is performed through an intelligent control structure, and control information is obtained. The control information comprises an air conditioner temperature value and an illumination control value.

The detection model comprises an illumination detection structure and a human body detection network.

The specific manner in which the various modules perform the operations in the systems of the above embodiments have been described in detail herein with respect to the embodiments of the method, and will not be described in detail herein.

An embodiment of the present invention further provides an electronic device, as shown in fig. 3, including a memory 504, a processor 502, and a computer program stored in the memory 504 and capable of running on the processor 502, where the processor 502 implements the steps of any one of the foregoing methods for controlling energy saving and carbon reduction of an institutional unit when executing the program.

Where in FIG. 3 a bus architecture (represented by bus 500), bus 500 may include any number of interconnected buses and bridges, with bus 500 linking together various circuits, including one or more processors, represented by processor 502, and memory, represented by memory 504. Bus 500 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. Bus interface 505 provides an interface between bus 500 and receiver 501 and transmitter 503. The receiver 501 and the transmitter 503 may be the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 502 is responsible for managing the bus 500 and general processing, while the memory 504 may be used to store data used by the processor 502 in performing operations.

The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of any one of the methods of the energy-saving and carbon reduction control method of the public institution and the related data.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in an apparatus according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

Claims (10)

1. An energy-saving carbon reduction control method for public institutions is characterized by comprising the following steps:

obtaining two public institution images; the two public institution images comprise a first public institution image and a second public institution image; the public institution images are images shot by monitoring at two different positions in the same public space;

converting the two public institution images from RGB to HSV to obtain two corresponding converted images; the two converted images comprise a first converted image and a second converted image;

inputting the two converted images into a detection model to obtain detection information; the detection information comprises a current illumination image and a current human existence value; the current human existence value of 1 indicates that people exist in the public institution;

based on the detection information, performing intelligent control through an intelligent control structure to obtain control information; the control information comprises an air conditioner temperature value and an illumination control value;

the detection model comprises an illumination detection structure and a human body detection network.

2. The method for controlling energy-saving and carbon reduction of public institutions according to claim 1, wherein the steps of inputting the two converted images into a detection model to obtain detection information comprise:

Extracting brightness from the two converted images to obtain two brightness images; the two brightness images comprise a first brightness image and a second brightness image; the brightness image is an image of a brightness channel in the converted image;

inputting the two brightness images into an illumination detection structure to obtain a current illumination image;

and inputting the two converted images into a human body detection network to obtain the current human body existence value.

3. The method for controlling energy-saving and carbon reduction of public institutions according to claim 2, wherein the steps of inputting the two brightness images into an illumination detection structure to obtain a current illumination image comprise the following steps:

dividing the first brightness image into areas to obtain a first area image;

dividing the second brightness image into areas to obtain a second area image;

obtaining a superposition area; the overlapping area comprises an overlapping illumination area and an overlapping dimming area; the overlapping area is an area where the overlapping part of the first area image and the second area image is located;

dividing the sum of the value of the coincident illumination area in the first area image and the value of the coincident illumination area in the second area image by 2 to obtain a coincident illumination mean value;

Dividing the sum of the value of the coincident dark region in the first region image and the value of the coincident dark region in the second region image by 2 to obtain a coincident dark mean value;

and replacing the value of the coincident illumination area in the first area image with the coincident illumination mean value, and replacing the value of the coincident dark area in the first area image with the coincident dark mean value to obtain the current illumination image.

4. A method for controlling energy-saving and carbon reduction of public institutions according to claim 3, wherein the steps of dividing the first brightness image into areas to obtain a first area image comprise the following steps:

dividing the median value of the first brightness image into areas according to the position of the illumination threshold value to obtain a divided area; the segmented regions include illuminated regions and darkened regions;

obtaining an illumination area mean value; the illumination area mean value is the mean value of the values in the illumination area;

obtaining a dim area mean; the dim zone mean is the mean of the values in the dim zone;

and replacing the average value of the illumination area and the average value of the dim area according to the illumination area and the dim area corresponding to the first brightness image to obtain a first area image.

5. The method for controlling energy-saving and carbon reduction of public institutions according to claim 4, wherein the dividing the median value of the first brightness image into areas according to the position of the illumination threshold value to obtain the divided areas comprises the following steps:

obtaining a first brightness set; the value in the first brightness set is the position of the median of the first brightness image which is larger than the illumination threshold value;

obtaining a first boundary set; the first boundary set is a boundary value in the first brightness set;

performing function fitting on the values in the first boundary set to obtain a boundary curve;

and taking the boundary curve as a boundary to obtain an illumination area.

6. The method for controlling energy-saving and carbon reduction of public institutions according to claim 2, wherein the training method of the human body detection network comprises the following steps:

obtaining a training set; the training set comprises a plurality of training images and a plurality of annotation data; the training image is an image containing a person; the labeling data comprises labeling human existence values and labeling human existence positions; the labeled human existence value is 1 to indicate that a human exists; the labeled human existence value of 0 indicates that no human exists;

Inputting the training image into a human body detection network to obtain training human body information; the training human body information comprises a training human body existence value and a training human body existence position;

inputting the training human existence value and the labeling human existence value into a loss function to obtain a loss value;

obtaining the current training iteration times of a human body detection network and the preset maximum iteration times of the human body detection network training;

and stopping training when the loss value is smaller than or equal to a threshold value or the training iteration number reaches the maximum iteration number, and obtaining the trained human body detection network.

7. The method for controlling energy-saving and carbon reduction of public institutions according to claim 1, wherein the intelligent control is performed by an intelligent control structure based on the detection information to obtain control information, and the method comprises the following steps:

obtaining a time period value; the period value of 1 is represented as an operating period; the period value of 0 represents a non-operating period;

obtaining a default specified range; the default specified ranges include an air quality default specified range and a temperature default specified range;

obtaining air quality; the air quality is the air quality of the current public institution;

Obtaining a temperature; the temperature is the temperature of the current public institution;

if the time period value is 1, working time period control information is obtained based on the detection information, the temperature, the air quality and a default specified range; the working period control information comprises an air purifier signal, an air conditioner signal and a lamplight illumination value;

if the time period value is 0, acquiring non-working time period control information based on the detection information, the temperature, the air quality and a default specified range; the non-working period control information is control information obtained in a non-working period; the non-working period control information comprises an air purifier signal, an air conditioner signal, a lamplight illumination value and energy consumption data; the energy consumption data comprise air purifier energy consumption data, air conditioner energy consumption data and lamplight energy consumption data.

8. The method for controlling energy-saving and carbon-reduction of public institutions according to claim 7, wherein if the time period value is 1, the working time period control information is obtained based on the detection information, the temperature, the air quality and the default specified range, and the method comprises the following steps:

if the human existence value is 1 and the air quality is not in the default specified range of the air quality, setting the air purifier signal to be 1; an air purifier signal of 1 indicates that the air purifier is on;

If the human existence value is 1 and the temperature is not in the default specified range of the temperature, setting the air conditioning signal to be 1; the air conditioner signal being 1 indicates that the air conditioner is turned on;

if the human existence value is 1, a first lamplight illumination value is obtained; the light illumination value is obtained by subtracting the brightness difference of the corresponding position in the current illumination image from the fixed light brightness;

if the human existence value is 0, or the air quality is within the air quality default specified range, setting the air purifier signal to be 0; the air purifier signal being 0 indicates that the air purifier is off;

if the human existence value is 0, or the temperature is within a default specified range of temperature, setting the air conditioning signal to be 0; the air conditioner signal being 0 indicates that the air conditioner is turned off;

if the human existence value is 0, setting the light illumination value to 0; the light illumination value of 0 indicates that the light is turned off.

9. The method for controlling energy-saving and carbon-reduction of public institutions according to claim 7, wherein if the time period value is 0, obtaining the non-working time period control information based on the detection information, the temperature, the air quality and the default specified range comprises the following steps:

if the human existence value is 1 and the air quality is not in the default specified range of the air quality, setting the air purifier signal as 1 to obtain the energy consumption of the first air purifier; the energy consumption of the first air purifier is the energy consumption for starting the air purifier;

If the human existence value is 1 and the temperature is not in the default specified range, obtaining the energy consumption of the first air conditioner; the energy consumption of the first air conditioner is the energy consumption for starting the air conditioner;

if the human existence value is 1, a first lamplight illumination value is obtained; the first lamplight illumination value is obtained by subtracting the brightness of the corresponding position in the current illumination image from the fixed lamplight brightness;

if the human existence value is 0, or the air quality is within the air quality default specified range, setting the air purifier signal to be 0; the air purifier on signal being 0 indicates that the air purifier is off;

if the human existence value is 0, or the temperature is within a default specified range of temperature, setting the air conditioning signal to be 0;

if the human existence value is 0, setting the light illumination value to 0;

obtaining an energy consumption value through a plurality of times if the human existence value is 1; the energy consumption values comprise a plurality of air purifier energy consumption values, a plurality of air conditioner energy consumption values and a plurality of lamplight illumination values until the human existence value is 0; adding the energy consumption values of the air purifier to obtain energy consumption data values of the air purifier; adding the energy consumption values of the air conditioner to obtain energy consumption data of the air conditioner; and adding the light illumination values to obtain light energy consumption data.

10. An institutional energy conservation and carbon reduction control system, comprising:

the acquisition module is used for: obtaining two public institution images; the two public institution images comprise a first public institution image and a second public institution image; the public institution images are images shot by monitoring at two different positions in the same public space;

and a conversion module: converting the two public institution images from RGB to HSV to obtain two corresponding converted images; the two converted images comprise a first converted image and a second converted image;

human body and illumination condition detection module: inputting the two converted images into a detection model to obtain detection information; the detection information comprises a current illumination image and a current human existence value; the current human existence value of 1 indicates that people exist in the public institution;

and the intelligent control module: based on the detection information, performing intelligent control through an intelligent control structure to obtain control information; the control information comprises an air conditioner temperature value and an illumination control value;

the detection model comprises an illumination detection structure and a human body detection network.

Images