CN113108437A - Air conditioner control method and device, storage medium and air conditioner - Google Patents

Air conditioner control method and device, storage medium and air conditioner Download PDF

Info

Publication number
CN113108437A
CN113108437A CN202110468393.9A CN202110468393A CN113108437A CN 113108437 A CN113108437 A CN 113108437A CN 202110468393 A CN202110468393 A CN 202110468393A CN 113108437 A CN113108437 A CN 113108437A
Authority
CN
China
Prior art keywords
human body
temperature information
air conditioner
person
target person
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110468393.9A
Other languages
Chinese (zh)
Inventor
宋士奇
汪进
毛跃辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gree Electric Appliances Inc of Zhuhai
Original Assignee
Gree Electric Appliances Inc of Zhuhai
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Gree Electric Appliances Inc of Zhuhai filed Critical Gree Electric Appliances Inc of Zhuhai
Priority to CN202110468393.9A priority Critical patent/CN113108437A/en
Publication of CN113108437A publication Critical patent/CN113108437A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/62Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63Electronic processing
    • F24F11/64Electronic processing using pre-stored data
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00Control inputs relating to users or occupants
    • F24F2120/10Occupancy
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00Control inputs relating to users or occupants
    • F24F2120/10Occupancy
    • F24F2120/12Position of occupants

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention provides an air conditioner control method, an air conditioner control device, a storage medium and an air conditioner, wherein the method comprises the following steps: identifying persons in a preset detection area based on a preset human body detection model, and acquiring human body temperature information of the identified persons; and adjusting the set parameters of the air conditioner according to the acquired human body temperature information of the personnel. The scheme provided by the invention can realize automatic adjustment according to the human body temperature of indoor personnel, and ensure that the body feeling of the indoor personnel keeps a comfortable state.

Description

Air conditioner control method and device, storage medium and air conditioner
Technical Field
The invention relates to the field of control, in particular to an air conditioner control method and device, a storage medium and an air conditioner.
Background
In a conventional heating, ventilation and air conditioning (HVAC) system, the temperature set point and the supply air parameters of the air conditioner are fixed values that are derived assuming that the thermal and wind sensations of the occupants of the room are static and non-differing. However, the heat sensation and the wind sensation of each indoor person may be different and change along with the change of the environmental condition and the self condition, and the personalized regulation and control of the air conditioning parameters are realized through the subjective feeling of the person, so that the device has passivity and hysteresis.
Disclosure of Invention
The main purpose of the present invention is to overcome the above-mentioned drawbacks of the prior art, and to provide an air conditioner control method, an air conditioner control device, a storage medium, and an air conditioner, so as to solve the problem that the personalized regulation and control of air conditioner parameters, which is artificially achieved through human subjective feelings, in the prior art has passivity and hysteresis.
One aspect of the present invention provides an air conditioner control method, including: identifying persons in a preset detection area based on a preset human body detection model, and acquiring human body temperature information of the identified persons; and adjusting the set parameters of the air conditioner according to the acquired human body temperature information of the personnel.
In some embodiments, identifying a person in a preset detection area based on a preset human body detection model, and acquiring human body temperature information of the identified person includes: acquiring an infrared thermal imaging image of the prediction area; inputting the collected image into the human body detection model to identify personnel in the image and spatial position information of the personnel; determining a target person in the image based on the spatial location information of the identified person; acquiring the determined human body temperature information of the target person in the image; and/or, according to the acquired human body temperature information of the personnel, adjusting the set parameters of the air conditioner, comprising the following steps: and adjusting the set parameters of the air conditioner according to the acquired human body temperature information of the target person.
In some embodiments, determining the target person in the image based on the spatial location information of the identified person includes: determining the person with the highest priority in the identified persons according to the spatial position information of the identified persons and a preset first priority rule; determining the person with the highest priority as the target person, wherein the first priority rule comprises: a priority determined according to a distance of the identified person from the air conditioner.
In some embodiments, obtaining the determined human body temperature information of the target person in the image includes: dividing body parts of the target person according to a preset proportion to obtain all body parts of the target person; and acquiring temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining the human body temperature information of the target person.
In some embodiments, obtaining temperature information of each body part of the target person based on each body part obtained by segmentation, so as to obtain human body temperature information of the target person, includes: acquiring temperature information of each body part of the target person through a region temperature characteristic value pixel difference algorithm based on each body part obtained by segmentation; setting weights corresponding to all body parts according to a preset second priority rule, wherein the second priority rule comprises the following steps: a preset priority of body parts; the higher the priority, the higher the weight corresponding to the body part; and acquiring the human body temperature information of the target person by adopting a weighted average algorithm according to the temperature information of each body part obtained by identification and the set weight corresponding to each body part.
In some specific embodiments, the adjusting of the setting parameters of the air conditioner according to the obtained human body temperature information of the person includes: acquiring a corresponding relation between preset human body temperature information and set parameters; acquiring set parameters corresponding to the human body temperature information of the personnel according to the corresponding relation; and adjusting the set parameters of the air conditioner according to the acquired corresponding set parameters.
Another aspect of the present invention provides an air conditioning control apparatus, including: the device comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for identifying personnel in a preset detection area based on a preset human body detection model and acquiring human body temperature information of the identified personnel; and the adjusting unit is used for adjusting the set parameters of the air conditioner according to the human body temperature information of the personnel acquired by the acquiring unit.
In some embodiments, the obtaining unit includes: the acquisition subunit is used for acquiring the infrared thermal imaging image of the prediction area; the identification subunit is used for inputting the image acquired by the acquisition unit into the human body detection model to identify the personnel in the image and the spatial position information of the personnel; a determination subunit configured to determine a target person in the image based on spatial position information of the person identified by the identification unit; the acquisition subunit is used for acquiring the human body temperature information of the target person in the image determined by the determination subunit; and/or the adjusting unit adjusts the set parameters of the air conditioner according to the human body temperature information of the person acquired by the acquiring unit, and the adjusting unit comprises: and adjusting the set parameters of the air conditioner according to the human body temperature information of the target person acquired by the acquisition subunit.
In some embodiments, the determining subunit determines the target person in the image based on the spatial position information of the person identified by the identifying unit, including: determining the person with the highest priority in the identified persons according to the spatial position information of the identified persons and a preset first priority rule; determining the person with the highest priority as the target person, wherein the first priority rule comprises: a priority determined according to a distance of the identified person from the air conditioner.
In some specific embodiments, the acquiring sub-unit, acquiring the human body temperature information of the target person in the image determined by the determining sub-unit, includes: dividing body parts of the target person according to a preset proportion to obtain all body parts of the target person; and acquiring temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining the human body temperature information of the target person.
In some specific embodiments, the obtaining subunit obtains, based on the body parts obtained by the dividing, temperature information of the body parts of the target person, so as to obtain the body temperature information of the target person, and includes: acquiring temperature information of each body part of the target person through a region temperature characteristic value pixel difference algorithm based on each body part obtained by segmentation; setting weights corresponding to all body parts according to a preset second priority rule, wherein the second priority rule comprises the following steps: a preset priority of body parts; the higher the priority, the higher the weight corresponding to the body part; and acquiring the human body temperature information of the target person by adopting a weighted average algorithm according to the temperature information of each body part obtained by identification and the set weight corresponding to each body part.
In some specific embodiments, the adjusting unit, according to the acquired human body temperature information of the person, adjusts the setting parameters of the air conditioner, including: acquiring a corresponding relation between preset human body temperature information and set parameters; acquiring set parameters corresponding to the human body temperature information of the personnel according to the corresponding relation; and adjusting the set parameters of the air conditioner according to the acquired corresponding set parameters.
A further aspect of the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
Yet another aspect of the present invention provides an air conditioner comprising a processor, a memory, and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of any of the methods described above when executing the program.
In another aspect, the invention provides an air conditioner, which comprises the air conditioner control device.
According to the technical scheme of the invention, based on a human body target detection technology, indoor personnel are detected and identified, and the human body temperature of the indoor personnel is identified, so that the set parameters of the air conditioner are adjusted; by setting the priority for temperature detection, determining the person with the highest priority in the identified persons as a target person, so as to control the air conditioner according to the human body temperature of the target person and ensure the body feeling comfort of indoor persons; the weight of each body part in the human body temperature is determined according to the priority of each body part, so that the human body temperature of people is determined according to the weight, the air conditioner can actively realize air supply and temperature adjustment, and the body feeling of indoor people can be kept in a comfortable state.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of an embodiment of an air conditioner control method according to the present invention;
FIG. 2 is a flowchart illustrating one embodiment of the steps of identifying a person in a predetermined detection area based on a predetermined human body detection model and obtaining human body temperature information of the identified person;
FIG. 3 illustrates a human detection model architecture diagram according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart diagram illustrating one embodiment of obtaining body temperature information of a target person;
FIG. 5 is a schematic diagram of an embodiment of a method for controlling an air conditioner according to the present invention;
fig. 6 is a schematic view of a control relationship of an air conditioning control method according to the present invention;
fig. 7 is a block diagram of an embodiment of an air conditioning control apparatus according to the present invention;
fig. 8 shows a block diagram of a specific embodiment of the acquisition unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The related technology mainly realizes the personalized regulation and control of the air conditioning parameters through the human subjective experience, and has passivity and hysteresis. In order to satisfy the comfortable feeling (heat feeling and wind feeling) of each indoor user, it is important to construct an individual comfort model to realize the regulation and control of the personalized air conditioning parameters.
The human body target detection technology judges whether a human body exists in an input human body image or video stream based on target characteristic information of the human body, and further gives the direction and the spatial position of a human body target. Therefore, the human body target and the spatial position information thereof are obtained based on the human body target detection technology, and the possibility is provided for realizing the active regulation and control of the air conditioner parameters.
Fig. 1 is a schematic method diagram of an embodiment of an air conditioner control method provided by the present invention.
As shown in fig. 1, according to an embodiment of the present invention, the air conditioner control method includes at least step S110 and step S120.
Step S110, identifying the personnel in the preset detection area based on the preset human body detection model, and acquiring the human body temperature information of the identified personnel.
Fig. 2 is a flowchart illustrating an embodiment of steps of identifying a person in a predetermined detection area based on a predetermined human body detection model, and acquiring human body temperature information of the identified person. As shown in fig. 2, step S110 includes step S111, step S112, step S113, and step S114.
And step S111, acquiring an infrared thermal imaging image of the detection area.
Specifically, an infrared thermal imaging image of the predicted area is acquired by an infrared temperature detection device. For example, the image in the detection area is collected through the infrared thermal imaging unit, the thermal imaging image in the detection area is collected in an infrared thermal imaging mode, so that the privacy of a user can be prevented from being revealed, and the temperature information of each position in the detection area and the temperature information of each body part of a human body can be obtained simultaneously. The thermal infrared image has a good detection effect in different environments, particularly in low-illumination environments, and can well protect personal privacy while acquiring the temperature of a key pixel point.
And S112, inputting the acquired image into the human body detection model to identify the personnel in the image and the spatial position information of the personnel.
In one embodiment, the human body detection model is a pyramid network model, such as a multi-template multi-scale pyramid network.
FIG. 3 shows a human detection model architecture diagram according to an embodiment of the invention.
As shown in fig. 3, the human body detection model employs a multi-template multi-scale pyramid network. The human body detection process of the multi-template multi-scale pyramid network comprises the following steps: inputting an image with any size, firstly carrying out multi-template multi-scale image pyramid preprocessing (for example, setting the size of the image to be 128 x 128), then carrying out feature extraction through a depth residual convolution network, carrying out information fusion on a feature map extracted from a residual layer and a feature map extracted from a convolution layer with a corresponding scale by fusing a multi-scale feature prediction target network, then completing the determination of a personnel target and a personnel position through a Softmax function, and meanwhile, obtaining the personnel temperature.
Firstly, feature extraction is carried out through a depth residual convolution network of a human body detection model. The resolution of the feature map obtained after the processing by the residual convolution network unit is 64 × 64, then 5 groups of operations including 4 ×, 4 ×, 4 ×, 4 ×, 4 ×, 4 × residual convolution network units are executed, that is, the network depth is continuously increased, so as to obtain feature maps with the sizes of 32 × 32, 16 × 16, 8 × 8, 4 × 4, 2 × 2 respectively, in the 5 groups of residual convolution network units, except for the number of filters and the resolution of the feature map, the structure of each residual convolution network unit is very similar, the two residual convolution network units are adjusted by the convolution kernel with the corresponding size in the step size of two pixels to achieve the same effect as the pooling layer, and each residual convolution network unit is composed of convolution layers and residual layers of 1 × 1 and 3 × 3.
And then, fusing the residual error layer and the characteristic information of the convolution layer with the corresponding scale through a fused multi-scale prediction target network of the human body detection model. Specifically, features extracted by convolutional layers with different resolutions (2 × 2, 4 × 4, 8 × 8, 16 × 16, 32 × 32) are respectively subjected to cascade operation with features extracted by a residual layer, namely feature information fusion, wherein the convolutional layers mainly perform upsampling operation on feature maps, the fused information is divided into 5 groups according to the different resolutions, each group transmits the feature map information to a classifier on the basis of sharing the information obtained from the residual convolutional network, and the classifier performs target category and position judgment. And judging the features of different scales by using a Softmax function to output the probability value of each feature, selecting the target category corresponding to the maximum probability value as the target of the whole image, thereby acquiring the personnel target in the image, and simultaneously outputting the position information of the target category in the fused multi-scale feature prediction target network.
Step S113, determining a target person in the image based on the spatial position information of the identified person.
In a specific embodiment, according to the spatial position information of the identified persons, the person with the highest priority among the identified persons is determined according to a preset first priority rule, and the person with the highest priority is determined as the target person. Wherein the first priority rule comprises: a priority determined according to a distance of the identified person from the air conditioner. Specifically, the closer the person is to the air conditioner, the higher the priority, that is, the highest the priority of the person closest to the air conditioner, and the lowest the priority of the person farthest from the air conditioner.
In some embodiments, the position information of the identified person in the image is converted into the distance of the actual space person from the air conditioner by using a physical space and camera space coordinate conversion formula, for example, the physical space and camera space coordinate conversion formula may be the following formula (1):
Figure BDA0003044917460000091
where x and y are coordinate points of the image, Xc, Yc, and Zc are coordinate points of the real space, and f is a focal length of the camera, such as a focal length of an infrared camera.
And step S114, acquiring the determined human body temperature information of the target person in the image.
In a specific embodiment, body parts of the target person are segmented according to a preset proportion to obtain all body parts of the target person; and acquiring temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining the human body temperature information of the target person. That is, the body part of the identified target person in the image is divided according to the preset proportion of each body part, so that each body part of the target person is obtained, and the temperature information of each body part of the target person can be obtained according to each body part obtained by division.
For example, the target person in the image is segmented into body parts according to preset proportions of the head, the upper body limb and the lower body limb, and head temperature, upper limb temperature and lower limb temperature information can be acquired according to the segmentation result.
In some embodiments, based on each body part obtained by segmentation, obtaining temperature information of each body part of the target person through a region temperature characteristic value pixel difference algorithm; setting the weight corresponding to each body part according to a preset second priority rule; and acquiring the human body temperature information of the target person by adopting a weighted average algorithm according to the temperature information of each body part obtained by identification and the set weight corresponding to each body part.
Fig. 4 is a flowchart illustrating an embodiment of obtaining human body temperature information of a target person. As shown in fig. 4, based on each body part obtained by segmentation, a key point temperature pixel value is extracted by a region temperature feature value pixel interpolation method, SIFI feature matching is performed on the extracted pixel value and a standard temperature value (color information corresponding to the standard temperature value is matched, and determination of the temperature value is realized through related color information), and finally, body part key point coordinate temperature value information is realized, and temperature information of each body part is obtained.
After the temperature information of each body part of the target person is obtained, the weight corresponding to each body part is set according to a preset second priority rule, and the temperature information of the target person is obtained by adopting a weighted average algorithm according to the temperature information of each body part obtained through recognition and the set weight corresponding to each body part. In one embodiment, the second priority rule includes: a preset priority of body parts; the higher the priority, the higher the weight corresponding to the body part. That is, the weight corresponding to each body part is set according to a preset priority of the body part, wherein the higher the priority, the higher the weight corresponding to the body part, and vice versa. And acquiring the temperature information of the current personnel by adopting a weighted average algorithm according to the temperature of each body part obtained by identification and the set weight corresponding to each body part.
According to a preferred embodiment of the invention, the detection is performed according to a first priority and then according to a second priority. For example, when more than two persons exist in the detection area, the priorities of the more than two persons are determined according to the distances between the more than two persons and the air conditioner, the person with the highest priority among the more than two persons determined according to the priorities is a target person, the human body temperature is detected, when the human body temperature of the target person is detected, the temperature information of each body part of the target person is obtained through a regional temperature characteristic value pixel difference algorithm, the weight corresponding to each body part is set according to the preset priority of the body part, and the temperature information of the target person is obtained through a weighted average algorithm according to the temperature information of each body part obtained through recognition and the set weight corresponding to each body part.
For example, the person information at a short distance is obtained according to a first priority determination method, the obtained head temperature, upper limb temperature and lower limb temperature information are respectively set to be different weights according to the part information of the human body and a second priority determination method, the part with a high priority has a heavy weight, and the current person temperature information is obtained according to an average weighting method.
And step S120, adjusting set parameters of the air conditioner according to the acquired human body temperature information of the personnel.
In a specific embodiment, acquiring a corresponding relation between preset human body temperature information and set parameters; acquiring set parameters corresponding to the human body temperature information of the personnel according to the corresponding relation; and adjusting the set parameters of the air conditioner according to the acquired corresponding set parameters. Based on the specific implementation manner of the previous step, the obtained human body temperature information is the human body temperature information of the target person, namely the set parameters corresponding to the human body temperature information of the target person are obtained according to the corresponding relation; and adjusting the set parameters of the air conditioner according to the set parameters corresponding to the acquired human body temperature information of the target person.
The setting parameters may specifically include setting temperature and/or setting air supply parameters. The set air supply parameters may include, for example, air supply volume, air supply speed, and/or air deflector angle. Namely, temperature adjustment and/or air supply control are/is carried out according to the acquired human body temperature information of the personnel.
For example, parameter information such as the air supply volume, speed and angle set by an air conditioner is acquired for a large number of users at different body temperatures, data matching is carried out, for example, the acquired temperature information of the personnel is 36.5 ℃, the air supply volume, the speed and the angle suitable for the temperature are pushed, and the body feeling of the personnel in the room is kept in a comfortable state.
For clearly explaining the technical solution of the present invention, the following describes an execution flow of the air conditioner control method provided by the present invention with a specific embodiment.
Fig. 5 is a schematic method diagram of an embodiment of an air conditioner control method according to the present invention. As shown in fig. 5, the air conditioner is turned on and a person is in the room, the infrared thermal imaging detection unit detects the person in the detection area, obtains information of each body part of the person and spatial position information of the person through the human body detection model, detects the person by using the human body detection model architecture diagram, and realizes detection of each part according to the proportion distribution of the head, the upper limbs and the lower limbs of the body, and sets the priority of parameter detection, for example, two levels are set, wherein the priority of the first layer is entirely higher than the priority of the second layer, the first layer: the distance between the person and the air conditioner is higher than the priority of the person far away from the air conditioner; a second layer: the person body part information includes, for example, a priority of a head of a human body higher than a priority of an upper limb of the human body, and a priority of an upper limb of the human body higher than a priority of a lower limb of the human body. When a plurality of persons exist in a room, the distance between the person and the air conditioner is preferentially judged, the information of the person with the closer distance is obtained according to a first-layer priority judgment method, the obtained information of the head temperature, the obtained information of the upper limb temperature and the obtained information of the lower limb temperature are respectively set to be different weights according to the information of the part of the person and a second-layer priority judgment method, the weight of the part of the body with the higher priority is great, and the information of the body temperature of the current person is obtained according to an average weighting method. The automatic air conditioner starting parameter regulating and controlling function automatically regulates the temperature of the air conditioner according to the body temperature information of current personnel, and simultaneously ensures that the body feeling of indoor personnel keeps a comfortable state by regulating parameters such as the air supply volume, speed and angle of the air conditioner.
The comfortable state of human body feeling here mainly refers to the optimal comfortable state of human body suitable for the corresponding distance and human body temperature, namely the optimal air conditioner temperature and air supply parameters, and the optimal comfortable state of human body feeling is different along with the distance between a person and an air conditioner and the difference of human body temperature. The thermal infrared image has a good detection effect in different environments, particularly in low-illumination environments, and can well protect personal privacy while acquiring the temperature of a key pixel point.
Fig. 6 is a control relationship diagram of an air conditioner control method according to the present invention. As shown in fig. 6, the infrared imaging detection unit 001 detects and identifies the person in the detection area, obtains information of each part of the body of the person and spatial position information of the person, drives the control unit 002 according to the obtained information data to realize data processing and control instruction transmission, the temperature adjustment unit 003 automatically adjusts the temperature of the air conditioner according to the capture instruction, and the air control adjustment unit 004 adjusts air supply parameters such as the air supply volume, speed and angle of the air conditioner according to the received instruction.
Fig. 7 is a block diagram of an embodiment of an air conditioning control apparatus according to the present invention. As shown in fig. 7, the air conditioning control device 100 includes an acquisition unit 110 and an adjustment unit 120.
The obtaining unit 110 is configured to identify a person in a preset detection area based on a preset human body detection model, and obtain human body temperature information of the identified person.
Fig. 8 shows a block diagram of a specific embodiment of the acquisition unit. As shown in fig. 8, the acquiring unit 110 includes: an acquisition subunit 111, an identification subunit 112, a determination subunit 113 and an acquisition subunit 114.
The acquisition subunit 111 is configured to acquire an infrared thermal imaging image of the prediction area.
Specifically, an infrared thermal imaging image of the predicted area is acquired by an infrared temperature detection device. For example, the image in the detection area is collected through the infrared thermal imaging unit, the thermal imaging image in the detection area is collected in an infrared thermal imaging mode, so that the privacy of a user can be prevented from being revealed, and the temperature information of each position in the detection area and the temperature information of each body part of a human body can be obtained simultaneously. The thermal infrared image has a good detection effect in different environments, particularly in low-illumination environments, and can well protect personal privacy while acquiring the temperature of a key pixel point.
The identification subunit 112 is configured to input the image acquired by the acquisition unit into the human body detection model, and identify the person in the image and the spatial position information of the person.
In one embodiment, the human body detection model is a pyramid network model, such as a multi-template multi-scale pyramid network. FIG. 3 shows a human detection model architecture diagram according to an embodiment of the invention.
As shown in fig. 3, the human body detection model employs a multi-template multi-scale pyramid network. The human body detection process of the multi-template multi-scale pyramid network comprises the following steps: inputting an image with any size, firstly carrying out multi-template multi-scale image pyramid preprocessing (for example, setting the size of the image to be 128 x 128), then carrying out feature extraction through a depth residual convolution network, carrying out information fusion on a feature map extracted from a residual layer and a feature map extracted from a convolution layer with a corresponding scale by fusing a multi-scale feature prediction target network, then completing the determination of a personnel target and a personnel position through a Softmax function, and meanwhile, obtaining the personnel temperature.
Firstly, feature extraction is carried out through a depth residual convolution network of a human body detection model. The resolution of the feature map obtained after the processing by the residual convolution network unit is 64 × 64, then 5 groups of operations including 4 ×, 4 ×, 4 ×, 4 ×, 4 ×, 4 × residual convolution network units are executed, that is, the network depth is continuously increased, so as to obtain feature maps with the sizes of 32 × 32, 16 × 16, 8 × 8, 4 × 4, 2 × 2 respectively, in the 5 groups of residual convolution network units, except for the number of filters and the resolution of the feature map, the structure of each residual convolution network unit is very similar, the two residual convolution network units are adjusted by the convolution kernel with the corresponding size in the step size of two pixels to achieve the same effect as the pooling layer, and each residual convolution network unit is composed of convolution layers and residual layers of 1 × 1 and 3 × 3.
And then, fusing the residual error layer and the characteristic information of the convolution layer with the corresponding scale through a fused multi-scale prediction target network of the human body detection model. Specifically, features extracted by convolutional layers with different resolutions (2 × 2, 4 × 4, 8 × 8, 16 × 16, 32 × 32) are respectively subjected to cascade operation with features extracted by a residual layer, namely feature information fusion, wherein the convolutional layers mainly perform upsampling operation on feature maps, the fused information is divided into 5 groups according to the different resolutions, each group transmits the feature map information to a classifier on the basis of sharing the information obtained from the residual convolutional network, and the classifier performs target category and position judgment. And judging the features of different scales by using a Softmax function to output the probability value of each feature, selecting the target category corresponding to the maximum probability value as the target of the whole image, thereby acquiring the personnel target in the image, and simultaneously outputting the position information of the target category in the fused multi-scale feature prediction target network.
The determination subunit 113 is configured to determine a target person in the image based on the spatial position information of the person identified by the identification unit.
In a specific embodiment, the determining subunit 113 determines the target person in the image based on the spatial position information of the person identified by the identifying unit, and includes: determining the person with the highest priority in the identified persons according to the spatial position information of the identified persons and a preset first priority rule; and determining the person with the highest priority as the target person. Wherein the first priority rule comprises: a priority determined according to a distance of the identified person from the air conditioner. Specifically, the closer the person is to the air conditioner, the higher the priority, that is, the highest the priority of the person closest to the air conditioner, and the lowest the priority of the person farthest from the air conditioner.
In some embodiments, the position information of the identified person in the image is converted into the distance of the actual space person from the air conditioner by using a physical space and camera space coordinate conversion formula, for example, the physical space and camera space coordinate conversion formula may be the following formula (1):
Figure BDA0003044917460000151
where x and y are coordinate points of the image, Xc, Yc, and Zc are coordinate points of the real space, and f is a focal length of the camera, such as a focal length of an infrared camera.
The obtaining subunit 114 is configured to obtain the human body temperature information of the target person in the image determined by the determining subunit;
in a specific embodiment, the acquiring subunit 114 acquires the human body temperature information of the target person in the image determined by the determining subunit 114, and includes: dividing body parts of the target person according to a preset proportion to obtain all body parts of the target person; and acquiring temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining the human body temperature information of the target person. That is, the body part of the identified target person in the image is divided according to the preset proportion of each body part, so that each body part of the target person is obtained, and the temperature information of each body part of the target person can be obtained according to each body part obtained by division.
For example, the target person in the image is segmented into body parts according to preset proportions of the head, the upper body limb and the lower body limb, and head temperature, upper limb temperature and lower limb temperature information can be acquired according to the segmentation result.
In some specific embodiments, the obtaining subunit 114 obtains temperature information of each body part of the target person based on each body part obtained by the segmentation, so as to obtain human body temperature information of the target person, including: acquiring temperature information of each body part of the target person through a region temperature characteristic value pixel difference algorithm based on each body part obtained by segmentation; setting the weight corresponding to each body part according to a preset second priority rule; and acquiring the human body temperature information of the target person by adopting a weighted average algorithm according to the temperature information of each body part obtained by identification and the set weight corresponding to each body part.
Fig. 4 is a flowchart illustrating an embodiment of obtaining human body temperature information of a target person. As shown in fig. 4, based on each body part obtained by segmentation, a key point temperature pixel value is extracted by a region temperature feature value pixel interpolation method, SIFI feature matching is performed on the extracted pixel value and a standard temperature value (color information corresponding to the standard temperature value is matched, and determination of the temperature value is realized through related color information), and finally, body part key point coordinate temperature value information is realized, and temperature information of each body part is obtained.
After the temperature information of each body part of the target person is obtained, the weight corresponding to each body part is set according to a preset second priority rule, and the temperature information of the target person is obtained by adopting a weighted average algorithm according to the temperature information of each body part obtained through recognition and the set weight corresponding to each body part. In one embodiment, the second priority rule includes: a preset priority of body parts; the higher the priority, the higher the weight corresponding to the body part. That is, the weight corresponding to each body part is set according to a preset priority of the body part, wherein the higher the priority, the higher the weight corresponding to the body part, and vice versa. And acquiring the temperature information of the current personnel by adopting a weighted average algorithm according to the temperature of each body part obtained by identification and the set weight corresponding to each body part.
According to a preferred embodiment of the invention, the detection is performed according to a first priority and then according to a second priority. For example, when more than two persons exist in the detection area, the priorities of the more than two persons are determined according to the distances between the more than two persons and the air conditioner, the person with the highest priority among the more than two persons determined according to the priorities is a target person, the human body temperature is detected, when the human body temperature of the target person is detected, the temperature information of each body part of the target person is obtained through a regional temperature characteristic value pixel difference algorithm, the weight corresponding to each body part is set according to the preset priority of the body part, and the temperature information of the target person is obtained through a weighted average algorithm according to the temperature information of each body part obtained through recognition and the set weight corresponding to each body part.
For example, the person information at a short distance is obtained according to a first priority determination method, the obtained head temperature, upper limb temperature and lower limb temperature information are respectively set to be different weights according to the part information of the human body and a second priority determination method, the part with a high priority has a heavy weight, and the current person temperature information is obtained according to an average weighting method.
The adjusting unit 120 is configured to adjust the set parameters of the air conditioner according to the human body temperature information of the person acquired by the acquiring unit.
In a specific embodiment, the adjusting unit 120 adjusts the setting parameters of the air conditioner according to the acquired human body temperature information of the person, including: acquiring a corresponding relation between preset human body temperature information and set parameters; acquiring set parameters corresponding to the human body temperature information of the personnel according to the corresponding relation; and adjusting the set parameters of the air conditioner according to the acquired corresponding set parameters.
Based on the foregoing specific embodiment, the acquired human body temperature information is the human body temperature information of the target person, that is, the air conditioner is adjusted by setting parameters according to the human body temperature information of the target person acquired by the acquiring subunit. The adjusting unit 120 obtains the setting parameter corresponding to the human body temperature information of the target person according to the corresponding relationship, and adjusts the setting parameter of the air conditioner according to the setting parameter corresponding to the obtained human body temperature information of the target person.
The setting parameters may specifically include setting temperature and/or setting air supply parameters. The set air supply parameters may include, for example, air supply volume, air supply speed, and/or air deflector angle. Namely, temperature adjustment and/or air supply control are/is carried out according to the acquired human body temperature information of the personnel.
For example, parameter information such as the air supply volume, speed and angle set by an air conditioner is acquired for a large number of users at different body temperatures, data matching is carried out, for example, the acquired temperature information of the personnel is 36.5 ℃, the air supply volume, the speed and the angle suitable for the temperature are pushed, and the body feeling of the personnel in the room is kept in a comfortable state.
The present invention also provides a storage medium corresponding to the air conditioning control method, having a computer program stored thereon, which when executed by a processor, performs the steps of any of the aforementioned methods.
The invention also provides an air conditioner corresponding to the air conditioner control method, which comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the steps of any one of the methods when executing the program.
The invention also provides an air conditioner corresponding to the air conditioner control device, which comprises the air conditioner control device.
Therefore, the scheme provided by the invention is based on a human body target detection technology, carries out detection and identification on indoor personnel, and identifies the human body temperature of the indoor personnel, thereby adjusting the set parameters of the air conditioner; by setting the priority for temperature detection, determining the person with the highest priority in the identified persons as a target person, so as to control the air conditioner according to the human body temperature of the target person and ensure the body feeling comfort of indoor persons; the weight of each body part in the human body temperature is determined according to the priority of each body part, so that the human body temperature of people is determined according to the weight, the air conditioner can actively realize air supply and temperature adjustment, and the body feeling of indoor people can be kept in a comfortable state.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the invention and the following claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or a combination of any of these. In addition, each functional unit may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and the parts serving as the control device may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims (10)

1. An air conditioner control method, comprising:
identifying persons in a preset detection area based on a preset human body detection model, and acquiring human body temperature information of the identified persons;
and adjusting the set parameters of the air conditioner according to the acquired human body temperature information of the personnel.
2. The method of claim 1,
based on personnel in the predetermined detection area of predetermined human body detection model discernment to acquire discernment personnel's human body temperature information includes:
acquiring an infrared thermal imaging image of the prediction area;
inputting the collected image into the human body detection model to identify personnel in the image and spatial position information of the personnel;
determining a target person in the image based on the spatial location information of the identified person;
acquiring the determined human body temperature information of the target person in the image;
and/or the presence of a gas in the gas,
according to the obtained human body temperature information of the personnel, the air conditioner is adjusted in set parameters, and the method comprises the following steps:
and adjusting the set parameters of the air conditioner according to the acquired human body temperature information of the target person.
3. The method of claim 2, wherein determining the target person in the image based on the spatial location information of the identified person comprises:
determining the person with the highest priority in the identified persons according to the spatial position information of the identified persons and a preset first priority rule;
determining the person with the highest priority as the target person, wherein the first priority rule comprises: a priority determined according to a distance of the identified person from the air conditioner.
4. The method according to claim 2 or 3, wherein obtaining the determined human body temperature information of the target person in the image comprises:
dividing body parts of the target person according to a preset proportion to obtain all body parts of the target person;
and acquiring temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining the human body temperature information of the target person.
5. The method of claim 4, wherein obtaining temperature information of each body part of the target person based on each body part obtained by segmentation, thereby obtaining human body temperature information of the target person, comprises:
acquiring temperature information of each body part of the target person through a region temperature characteristic value pixel difference algorithm based on each body part obtained by segmentation;
setting weights corresponding to all body parts according to a preset second priority rule, wherein the second priority rule comprises the following steps: a preset priority of body parts; the higher the priority, the higher the weight corresponding to the body part;
and acquiring the human body temperature information of the target person by adopting a weighted average algorithm according to the temperature information of each body part obtained by identification and the set weight corresponding to each body part.
6. The method according to any one of claims 1 to 5, wherein the adjusting of the set parameters of the air conditioner according to the acquired human body temperature information of the person comprises:
acquiring a corresponding relation between preset human body temperature information and set parameters;
acquiring set parameters corresponding to the human body temperature information of the personnel according to the corresponding relation;
and adjusting the set parameters of the air conditioner according to the acquired corresponding set parameters.
7. An air conditioning control device, characterized by comprising:
the device comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for identifying personnel in a preset detection area based on a preset human body detection model and acquiring human body temperature information of the identified personnel;
and the adjusting unit is used for adjusting the set parameters of the air conditioner according to the human body temperature information of the personnel acquired by the acquiring unit.
8. The apparatus of claim 7,
the acquisition unit includes:
the acquisition subunit is used for acquiring the infrared thermal imaging image of the prediction area;
the identification subunit is used for inputting the image acquired by the acquisition unit into the human body detection model to identify the personnel in the image and the spatial position information of the personnel;
a determination subunit configured to determine a target person in the image based on spatial position information of the person identified by the identification unit;
the acquisition subunit is used for acquiring the human body temperature information of the target person in the image determined by the determination subunit;
and/or the presence of a gas in the gas,
the adjusting unit adjusts the set parameters of the air conditioner according to the human body temperature information of the person acquired by the acquiring unit, and comprises:
and adjusting the set parameters of the air conditioner according to the human body temperature information of the target person acquired by the acquisition subunit.
9. A storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. An air conditioner comprising a processor, a memory, and a computer program stored on the memory and operable on the processor, the processor implementing the steps of the method of any one of claims 1 to 6 when executing the program, including the air conditioning control apparatus of any one of claims 7 to 8.
CN202110468393.9A 2021-04-28 2021-04-28 Air conditioner control method and device, storage medium and air conditioner Pending CN113108437A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110468393.9A CN113108437A (en) 2021-04-28 2021-04-28 Air conditioner control method and device, storage medium and air conditioner

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110468393.9A CN113108437A (en) 2021-04-28 2021-04-28 Air conditioner control method and device, storage medium and air conditioner

Publications (1)

Publication Number Publication Date
CN113108437A true CN113108437A (en) 2021-07-13

Family

ID=76721134

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110468393.9A Pending CN113108437A (en) 2021-04-28 2021-04-28 Air conditioner control method and device, storage medium and air conditioner

Country Status (1)

Country Link
CN (1) CN113108437A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114046595A (en) * 2021-11-15 2022-02-15 珠海格力电器股份有限公司 Control method and device of air conditioning equipment and electronic equipment
CN114061074A (en) * 2021-10-21 2022-02-18 青岛海尔空调器有限总公司 Air conditioner control method, air conditioner, electronic device and storage medium
CN114320986A (en) * 2021-12-23 2022-04-12 珠海格力电器股份有限公司 Fan control method and device, electronic equipment and computer readable storage medium
CN114413443A (en) * 2022-01-14 2022-04-29 珠海格力电器股份有限公司 Self-adaptive fresh air conditioning system and air conditioner
CN114909786A (en) * 2022-04-24 2022-08-16 青岛海信日立空调系统有限公司 Air conditioning system and control method thereof

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006162168A (en) * 2004-12-08 2006-06-22 Toshiba Kyaria Kk Air conditioner
CN101334645A (en) * 2008-07-15 2008-12-31 西安交通大学 Domestic air conditioner intelligent temperature control system based on human behavior trait
CN104251538A (en) * 2014-09-12 2014-12-31 广东美的制冷设备有限公司 Air conditioner and control method and control device thereof
CN104697114A (en) * 2015-03-06 2015-06-10 广东美的制冷设备有限公司 Air conditioner control method and device
CN111121239A (en) * 2018-11-01 2020-05-08 珠海格力电器股份有限公司 Intelligent control method and system for intelligent household appliance and intelligent household appliance

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006162168A (en) * 2004-12-08 2006-06-22 Toshiba Kyaria Kk Air conditioner
CN101334645A (en) * 2008-07-15 2008-12-31 西安交通大学 Domestic air conditioner intelligent temperature control system based on human behavior trait
CN104251538A (en) * 2014-09-12 2014-12-31 广东美的制冷设备有限公司 Air conditioner and control method and control device thereof
CN104697114A (en) * 2015-03-06 2015-06-10 广东美的制冷设备有限公司 Air conditioner control method and device
CN111121239A (en) * 2018-11-01 2020-05-08 珠海格力电器股份有限公司 Intelligent control method and system for intelligent household appliance and intelligent household appliance

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114061074A (en) * 2021-10-21 2022-02-18 青岛海尔空调器有限总公司 Air conditioner control method, air conditioner, electronic device and storage medium
CN114046595A (en) * 2021-11-15 2022-02-15 珠海格力电器股份有限公司 Control method and device of air conditioning equipment and electronic equipment
CN114320986A (en) * 2021-12-23 2022-04-12 珠海格力电器股份有限公司 Fan control method and device, electronic equipment and computer readable storage medium
CN114413443A (en) * 2022-01-14 2022-04-29 珠海格力电器股份有限公司 Self-adaptive fresh air conditioning system and air conditioner
CN114909786A (en) * 2022-04-24 2022-08-16 青岛海信日立空调系统有限公司 Air conditioning system and control method thereof

Similar Documents

Publication Publication Date Title
CN113108437A (en) Air conditioner control method and device, storage medium and air conditioner
KR102121785B1 (en) Air-conditioner controlling direction of the wind using artificial intelligence by instructed position and method of controlling thereof
CN107883541B (en) Air conditioner control method and device
WO2019120252A1 (en) Systems and methods for controlling an air-conditioning system based on gait recognition
WO2022227775A1 (en) Method and device for controlling air conditioner, and air conditioner
CN108758959A (en) Method, device and system for controlling air supply for air conditioner
CN108195032B (en) Air conditioner control method, device and computer readable storage medium
CN110377961A (en) Crop growth environment control method, device, computer equipment and storage medium
CN109241634A (en) Air conditioner blowing wide-angle determining method and device and air conditioner
CN111240217B (en) State detection method and device, electronic equipment and storage medium
CN112303861A (en) Air conditioner temperature adjusting method and system based on human body thermal adaptability behavior
CN113819620B (en) Method and device for controlling air conditioner, air conditioner and storage medium
CN111256315A (en) Neural network-based air conditioner control model creation method, control method and air conditioner
KR102160128B1 (en) Method and apparatus for creating smart albums based on artificial intelligence
CN113495487A (en) Terminal and method for adjusting operation parameters of target equipment
CN114771442A (en) Vehicle personalized setting method and vehicle
CN110274367A (en) air conditioner control device, method, controller, air conditioner and storage medium
CN112699731A (en) Air conditioner music intelligent playing method and device based on human behavior recognition and air conditioner
JP6914279B2 (en) Control device, air conditioner, air conditioning system and air conditioning control method
JP6681816B2 (en) Air conditioner
CN111355992B (en) Control method and device of air-conditioning television, air-conditioning television and storage medium
CN112944611A (en) Control method and device of air conditioner, storage medium and processor
CN108826597A (en) Control method and device of air conditioning equipment
CN110966707A (en) Control method and device of air conditioner
KR20190134101A (en) Server of controlling air conditioner with area recognition and air conditioner

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210713