CN116753919A - Air Conditioning System - Google Patents
Air Conditioning System Download PDFInfo
- Publication number
- CN116753919A CN116753919A CN202310531866.4A CN202310531866A CN116753919A CN 116753919 A CN116753919 A CN 116753919A CN 202310531866 A CN202310531866 A CN 202310531866A CN 116753919 A CN116753919 A CN 116753919A
- Authority
- CN
- China
- Prior art keywords
- distance
- physical
- pixel
- target object
- coordinate system
- 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
Links
- 238000004378 air conditioning Methods 0.000 title claims abstract description 129
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000009434 installation Methods 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000036544 posture Effects 0.000 description 23
- 239000011159 matrix material Substances 0.000 description 14
- 230000006870 function Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 239000003507 refrigerant Substances 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 239000007789 gas Substances 0.000 description 5
- 238000007664 blowing Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000009833 condensation Methods 0.000 description 3
- 230000005494 condensation Effects 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 239000007791 liquid phase Substances 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 229910044991 metal oxide Inorganic materials 0.000 description 2
- 150000004706 metal oxides Chemical class 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 241000226585 Antennaria plantaginifolia Species 0.000 description 1
- 239000011358 absorbing material Substances 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/06—Interpretation of pictures by comparison of two or more pictures of the same area
- G01C11/12—Interpretation of pictures by comparison of two or more pictures of the same area the pictures being supported in the same relative position as when they were taken
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
- F24F2120/12—Position of occupants
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Software Systems (AREA)
- Radar, Positioning & Navigation (AREA)
- Multimedia (AREA)
- Fuzzy Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an air conditioning system, comprising: a distance measuring module is provided with: an image collection part including a monocular camera, the image collection part being configured to collect an air-conditioning room image by photographing, the air-conditioning room image including a target object and a reference object; and a distance generation section configured to estimate a physical distance of a vertical axis component of the set pixel point in the physical ground coordinate system on the target object based on the own position and posture of the monocular camera; estimating the physical distance of the horizontal axis component of the set pixel point in the physical ground coordinate system on the target object based on the vanishing points of the target object and the reference object in the air-conditioning room image; estimating an estimated distance between the ranging module itself and the target object based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component; wherein the target object in the air-conditioned room image is identified using a target detection model. The invention has the advantages of high operation speed, high ranging precision and suitability for embedded equipment.
Description
Technical Field
The invention relates to the technical field of air conditioning, in particular to an air conditioning system.
Background
Air conditioning technology tends to mature, and the requirements of users on comfort and energy conservation are also increasing. The air conditioning equipment can acquire various information such as target distance, posture, movement state and the like of a human body or an article, can provide a data source for intelligent operation of the air conditioner well, and can perform functions such as automatic startup when a person in an air conditioning room is detected, automatic shutdown when no person is in the air conditioning room, intelligent air supply and the like.
In the prior art, the target distance can be detected by adopting sound waves, for example, the technical scheme disclosed in Chinese patent application (CN 1133048C): "a method of detecting a target distance by an air conditioner having an acoustic wave transmitter and a receiver, the method comprising the steps of: transmitting, by the sonic transmitter, a first sonic wave to the target for a predetermined time; if the target reflects the first sound wave and the sound wave receiver receives the first sound wave within a first predetermined time T1, calculating a distance of the first target; if the acoustic receiver does not receive the first acoustic wave within the first predetermined time T1, transmitting, by the acoustic transmitter, a second acoustic wave for a time longer than the predetermined time; if the target reflects a second sound wave of a strength stronger than the predetermined strength for a second time period T2 and the sound wave receiver receives the second sound wave, calculating a second target distance; and if the acoustic receiver does not receive the second acoustic wave of greater than the predetermined intensity within the second time period T2, determining that no target is detected. "and its application
However, ultrasonic detection is susceptible to temperature interference, and particularly when used indoors, it is easily absorbed by wall sound absorbing materials or sound insulating materials, and ultrasonic detection cannot measure azimuth.
The above information disclosed in this background section is only for enhancement of understanding of the background section of the application and therefore it may not form the prior art that is already known to those of ordinary skill in the art.
Disclosure of Invention
In order to solve the problems that the existing air conditioner adopting ultrasonic ranging is easily affected by the environment and the ultrasonic detection cannot detect the azimuth, the first aspect of the application designs and provides an air conditioning system.
An air conditioning system comprising: a distance measuring module is provided with: an image acquisition section including a monocular camera, the image acquisition section configured to acquire an air-conditioning room image by photographing, the air-conditioning room image including a target object and a reference object.
The distance measurement module further comprises a distance generation part, wherein the distance generation part is configured to estimate the physical distance of the vertical axis component of the set pixel point on the target object in the physical ground coordinate system based on the self position and the gesture of the monocular camera; estimating a physical distance of a horizontal axis component of a set pixel point in a physical ground coordinate system on the target object based on vanishing points of the target object and the reference object in the air-conditioning room image; the estimated distance between the ranging module itself and the target object is estimated based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component.
In some embodiments of the present application, the target object in the air-conditioned room image is identified using a target detection model.
In some embodiments of the present application, the distance generation section is configured to execute a method of estimating a physical distance of a vertical axis component of a pixel point in a physical ground coordinate system on the target object based on a self position and posture of the monocular camera: acquiring the installation height, pitch angle and installation angle of the monocular camera; the installation angle is an included angle between the monocular camera and the height direction of the air-conditioning room; estimating the length of the boundary line in the pitching visual field based on the installation height and the installation angle of the monocular camera; estimating a half-shaft pitch angle; estimating the length of a central line segment of the pitching field of view based on the pitch angle of the half shaft and the length of the inner edge of the pitching field of view; calculating a vertical axis direction half-axis mapping physical distance based on the length of the inner edge of the pitching field and the pitch angle of the half-axis; acquiring a vertical axis pixel distance of a set pixel point under a pixel coordinate system; estimating a mapping physical distance of the set pixel point based on the vertical axis pixel distance, the half axis mapping physical distance and the half axis pixel distance; estimating a pitching angle based on the mapping physical distance of the set pixel point and the pitching field of view central line segment length; and estimating and setting the physical distance of the longitudinal axis component of the pixel point in the physical ground coordinate system based on the installation height, the half-axis pitch angle, the pitching angle and the installation angle of the monocular camera, namely, estimating the physical distance of the longitudinal axis component under the principle of vanishing point method.
In some embodiments of the present application, the distance generation section is configured to perform a method of estimating a physical distance of a horizontal axis component of a set pixel point on a target object in a physical ground coordinate system based on vanishing points of the target object and a reference object in an air-conditioning room image: setting an extension line of a pixel point on a target object and taking intersection points generated by extension lines of a plurality of reference objects as vanishing points; establishing a computing coordinate system, wherein the vertical axis of the computing coordinate system is a vertical line which passes through vanishing points and is perpendicular to the length direction of the air-conditioning room image; acquiring a horizontal axis pixel distance and a vertical axis pixel distance of a set pixel point under a pixel coordinate system; acquiring vanishing point pixel distances between vanishing points and longitudinal edges of the air-conditioning room image that are away from the vanishing points; calculating a calculation included angle of a set pixel point based on the horizontal axis pixel distance, the vertical axis pixel distance and the vanishing point pixel distance; generating a standard reference line in an air-conditioning room image, wherein the standard reference line is a straight line which passes through an extension line and has minimum distortion; and acquiring a standard reference intersection point between an extension line of the set pixel point and a standard reference line, and taking the distance between the standard reference intersection point and the vertical axis of the calculation coordinate system as the physical distance of the horizontal axis component of the set pixel point in the physical ground coordinate system on the target object.
In some optional embodiments of the application, the distance generation section is further configured to perform the following method to estimate a physical distance of a horizontal axis component of the set pixel point in the physical floor coordinate system on the target object based on vanishing points of the target object and the reference object in the air-conditioning room image: dividing a standard reference line into a plurality of length units based on the physical distance of the reference object; acquiring a unit pixel distance of a corresponding length unit; calculating the ratio of the physical distance of the length unit to the unit pixel distance as a pixel unit; acquiring a pixel distance between a standard reference intersection point and a longitudinal axis of a calculation coordinate system; the pixel distance between the standard reference intersection point and the vertical axis of the calculation coordinate system is converted into a physical distance by using a pixel unit as the physical distance of the horizontal axis component of the set pixel point in the physical ground coordinate system on the target object.
In some optional embodiments of the application, the distance generation section is further configured to correct distortion of the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component using a neural network.
In some optional embodiments of the application, the distance generation section is further configured to perform the following steps to correct distortion of the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component with a neural network: obtaining a real distance matrix; identifying and framing the human body in the N images by utilizing the target identification model, and acquiring a set pixel point corresponding to the rectangular frame and the foot center point; obtaining a deviation value matrix; setting a neural network structure and inputting a deviation value matrix; setting a loss function and an optimizer of the neural network; training a neural network and acquiring distortion correction parameters; and correcting distortion of the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component by using the trained neural network.
In some alternative embodiments of the application, the target object is a person.
In some alternative embodiments of the application, the target object is an animal or a stationary object.
In some optional embodiments of the present application, the set pixels of the target object include foot set pixels and head set pixels.
To achieve intelligent control of the air conditioning system, in some optional embodiments of the present application, the distance generation section is further configured to estimate the height of the target object based on the physical distance of the longitudinal axis component of the foot-set pixel point in the physical ground coordinate system, the physical distance of the longitudinal axis component of the head-set pixel point in the physical ground coordinate system, and the mounting height of the monocular camera.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to estimate the estimated distance of the foot-setting pixel point from the estimation module itself based on the physical distance of the vertical axis component of the foot-setting pixel point in the physical ground coordinate system and the mounting height of the monocular camera.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to set the estimated distance between the pixel point and the estimation module itself based on the physical distance of the vertical axis component of the foot-set pixel point in the physical ground coordinate system, the installation height of the monocular camera, and the height estimation head of the target object.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to estimate the head pitch angle based on the mounting height and height of the monocular camera, the foot setting the physical distance of the longitudinal axis component of the pixel point in the physical ground coordinate system.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to estimate the foot pitch angle based on the mounting height and height of the monocular camera, based on the physical distance of the foot-set pixel's longitudinal axis component in the physical ground coordinate system.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to estimate the head heading angle based on a physical distance of a longitudinal axis component of the foot-setting pixel point in the physical ground coordinate system, and an abscissa of the head-setting pixel point in the pixel coordinate system.
To achieve intelligent control of the air conditioning system, in some alternative embodiments of the present application, the distance generation section is further configured to estimate the foot course angle based on the physical distance of the vertical axis component of the foot-setting pixel point in the physical ground coordinate system, and the abscissa of the foot-setting pixel point in the pixel coordinate system.
A second aspect of the present invention provides an air conditioning system, in which a ranging module is provided, which can estimate a longitudinal distance between a target object and the ranging module itself; a distance measuring module is provided with: an image collection part including a monocular camera, the image collection part being configured to collect an image of an air-conditioning room by photographing, the air-conditioning room image including a target object; and a distance generation section configured to execute the following method to estimate a longitudinal distance between a set pixel point and the ranging module on the target object based on a self position and an attitude of the monocular camera, the self position and the attitude of the monocular camera including a mounting height, a pitch angle, and a mounting angle of the monocular camera, the mounting angle being an angle between the monocular camera itself and a height direction of the air-conditioning room: estimating the length of the boundary line in the pitching visual field based on the installation height and the installation angle of the monocular camera; estimating a half-shaft pitch angle; estimating the length of a central line segment of the pitching field of view based on the pitch angle of the half shaft and the length of the inner edge of the pitching field of view; calculating a vertical axis direction half-axis mapping physical distance based on the length of the inner edge of the pitching field and the pitch angle of the half-axis; acquiring a vertical axis pixel distance of a set pixel point under a pixel coordinate system; estimating a mapping physical distance of the set pixel point based on the vertical axis pixel distance, the half axis mapping physical distance and the half axis pixel distance; estimating a pitching angle based on the mapping physical distance of the set pixel point and the pitching field of view central line segment length; and estimating the physical distance of the vertical axis component of the set pixel point in the physical ground coordinate system based on the installation height, the half-axis pitch angle, the pitching angle and the installation angle of the monocular camera, and taking the physical distance of the vertical axis component as the longitudinal distance between the set pixel point and the monocular camera.
A second aspect of the present invention provides an air conditioning system, in which a ranging module is provided, which can estimate a lateral distance between a target object and the ranging module itself; a distance measuring module is provided with: an image collection part including a monocular camera, the image collection part being configured to collect an image of an air-conditioning room by photographing, the air-conditioning room image including a target object and a reference object; and a distance generation section configured to perform the following method to estimate a lateral distance between a set pixel point on the target object and the ranging module based on vanishing points of the target object and the reference object in the air-conditioning room image: setting an extension line of a pixel point on a target object and taking intersection points generated by extension lines of a plurality of reference objects as vanishing points; establishing a computing coordinate system, wherein the vertical axis of the computing coordinate system is a vertical line which passes through vanishing points and is perpendicular to the length direction of the air-conditioning room image; acquiring a horizontal axis pixel distance and a vertical axis pixel distance of a set pixel point under a pixel coordinate system; acquiring vanishing point pixel distances between vanishing points and longitudinal edges of the air-conditioning room image that are away from the vanishing points; calculating a calculation included angle of a set pixel point based on the horizontal axis pixel distance, the vertical axis pixel distance and the vanishing point pixel distance; generating a standard reference line in an air-conditioning room image, wherein the standard reference line is a straight line which passes through an extension line and has minimum distortion; and acquiring a standard reference intersection point between an extension line passing through the set pixel point and a standard reference line, and taking the distance between the standard reference intersection point and the longitudinal axis of the calculation coordinate system as the transverse distance between the set pixel point and the ranging module on the target object.
Compared with the prior art, the invention has the advantages and positive effects that: the method has the advantages of high operation speed and high ranging precision, and is applicable to embedded equipment.
Other features and advantages of the present invention will become apparent upon review of the detailed description of the invention in conjunction with the drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic block diagram of a ranging module in an air conditioning system according to some embodiments of the present invention;
fig. 2 is a schematic block diagram of a ranging module in an air conditioning system according to some embodiments of the present invention;
FIG. 3 is a flow chart of a ranging module in an air conditioning system according to some embodiments of the present invention;
fig. 4 is a schematic diagram of a physical ground coordinate system in an air conditioning system according to some embodiments of the present invention;
FIG. 5 is a schematic diagram of a physical floor coordinate system in an air conditioning system according to some embodiments of the present invention;
FIG. 6 is a flow chart of a ranging module in an air conditioning system according to some embodiments of the present invention;
fig. 7 is a schematic diagram of a distance measurement module in an air conditioning system according to some embodiments of the present invention estimating a physical distance of a longitudinal axis component;
fig. 8 is a schematic diagram of a distance measurement module in an air conditioning system according to some embodiments of the present invention when obtaining a vertical axis pixel distance of a set pixel point in a pixel coordinate system;
FIG. 9 is a flow chart of a ranging module in an air conditioning system according to some embodiments of the present invention;
fig. 10 is an example of an air-conditioned room image, in which the locations of vanishing points are illustrated;
FIG. 11 is a schematic diagram of a ranging module in an air conditioning system according to some embodiments of the present invention estimating a physical distance of a longitudinal axis component;
FIG. 12 is a flow chart of a ranging module in an air conditioning system according to some embodiments of the present invention; the method comprises the steps of carrying out a first treatment on the surface of the
FIGS. 13 to 15 are schematic diagrams of different distortion phenomena;
FIG. 16 is a schematic view of a two-dimensional field of view range of a ranging module in an air conditioning system according to some embodiments of the present invention when the ranging module acquires a real distance matrix;
FIG. 17 is a flow chart illustrating a distance measurement module in an air conditioning system according to some embodiments of the present application;
FIG. 18 is a schematic diagram showing the comparison of the images before and after distortion correction;
fig. 19 is a schematic diagram of a distance measurement module in an air conditioning system according to some embodiments of the present application when estimating the height of a target object.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, it should be understood that the orientations or positional relationships indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., are based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present application.
The terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second" or the like may include one or more such features, either explicitly or implicitly. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted", "connected" and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
In the present application, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above", "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "under" and "beneath" the second feature includes the first feature being directly under and obliquely under the second feature, or simply means that the first feature is less horizontal than the second feature.
The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. In order to simplify the present disclosure, components and arrangements of specific examples are described below. They are, of course, merely examples and are not intended to limit the invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples, which are for the purpose of brevity and clarity, and which do not themselves indicate the relationship between the various embodiments and/or arrangements discussed. In addition, the present invention provides examples of various specific processes and materials, but one of ordinary skill in the art will recognize the application of other processes and/or the use of other materials.
Aiming at the problems that the prior air conditioner adopting ultrasonic ranging is easy to be influenced by environment and the ultrasonic detection cannot detect the azimuth, the invention designs and provides an air conditioning system 1.
First, the air conditioning system 1 is explained for maintaining good indoor air conditions to improve and enhance the use functions of the building. The air-conditioning room or building adopting the air conditioning technology has the characteristics of comfort, health and energy conservation, the air-conditioning room has good thermal environment, and parameters such as indoor air temperature, humidity, air flow speed, cleanliness, freshness and the like are suitable, so that indoor personnel can be ensured to have good living conditions and working conditions. In the industrial field, the proper indoor environment is kept to meet the production process requirement, the product quality is ensured, meanwhile, the air quality is good, excessive substances harmful to human bodies (including microorganisms, volatile organic gases and the like) are not contained, and the optimal indoor environment is maintained by using the minimum energy consumption. Therefore, the air conditioning system 1 is a device for performing heat, humidity and purification treatment on air to meet the air supply requirement of an air-conditioned room; among these, the devices for heat and humidity treatment of air include, but are not limited to, heating devices, cooling devices, humidifying devices, dehumidifying devices, and the like.
In the present application, an air conditioning system is described as an example. A typical air conditioning method of an air conditioning system is to send air of a certain parameter into a room (supply air) while discharging a corresponding amount of air from the room (exhaust air). Under the simultaneous action of air supply and air exhaust, the indoor air can be kept in a required state. The supply air is previously treated (e.g., heated, cooled, humidified, dehumidified, filtered, purified, etc.) by the air treatment device. The air conditioning system comprises the components of an air conditioning cold and heat source, air treatment, air transportation, air distribution, a controller and the like.
In the present application, the air conditioning system performs a refrigerating cycle of the air conditioning system by using a compressor, a condenser, an expansion valve, and an evaporator. The refrigeration cycle includes a series of processes involving compression, condensation, expansion, and evaporation, and refrigerating or heating an indoor space.
The low-temperature low-pressure refrigerant enters the compressor, the compressor compresses the refrigerant gas into a high-temperature high-pressure state, and the compressed refrigerant gas is discharged. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, and heat is released to the surrounding environment through the condensation process.
The expansion valve expands the liquid-phase refrigerant in a high-temperature and high-pressure state formed by condensation in the condenser into a low-pressure liquid-phase refrigerant. The evaporator evaporates the refrigerant expanded in the expansion valve and returns the refrigerant gas in a low-temperature and low-pressure state to the compressor. The evaporator may achieve a cooling effect by exchanging heat with a material to be cooled using latent heat of evaporation of a refrigerant. Throughout the cycle, the air conditioning system may adjust the temperature of the indoor space.
An outdoor unit of an air conditioning system refers to a portion of a refrigeration cycle including a compressor and an outdoor heat exchanger, an indoor unit of the air conditioning system includes an indoor heat exchanger, and an expansion valve may be provided in the indoor unit or the outdoor unit.
The indoor heat exchanger and the outdoor heat exchanger function as a condenser or an evaporator. When the indoor heat exchanger is used as a condenser, the air conditioner is used as a heater of a heating mode, and when the indoor heat exchanger is used as an evaporator, the air conditioner is used as a cooler of a cooling mode.
A ranging module 10 is provided in the air conditioning system. Hereinafter, an embodiment of an air conditioning system provided with the ranging module 10 will be described with reference to the drawings.
First, a basic configuration of a ranging module 10 according to one embodiment will be described with reference to fig. 1 and 2.
In terms of physical form, the ranging module 10 may be an independent intelligent camera unit integrated with the processor 120, or an integrated intelligent module with the camera unit, or a combination of an independent camera unit and a processing unit in communication connection with the camera unit, or a camera unit built in other intelligent electronic devices, and the intelligent electronic devices are detachably arranged in an air conditioning system, or are matched with the air conditioning system for use.
In terms of the functional modules, the distance measuring module 10 includes an image acquisition section 11 and a distance generation section 12.
The image pickup section 11 includes at least one monocular camera 110, and the monocular camera 110 can take an image of an air-conditioned room. The image acquisition section 11 is configured to acquire an image of an air-conditioned room by photographing. The monocular camera 110 may be an RGB monocular camera. Specifically, the monocular camera 110 includes an optical component 111 (including an optical lens, a filter, a protective film, and the like), an image sensor 112, and a digital signal processing chip 113.
The image sensor 112 in the monocular camera 110 receives light transmitted by the optical component 111 and performs photoelectric conversion. The image sensor 112 may be a charge coupled device (Charge Coupled Device, CCD) or a complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS). The digital signal processing chip 113 is used for performing post-processing on the signal output by the front-end image sensor 112, and includes functions such as linear correction, noise removal, dead pixel removal, white balance, automatic exposure control, etc.
The distance generation unit 12 receives the image captured by the image acquisition unit 11, and estimates the physical distance of the vertical axis component of the pixel point in the physical ground coordinate system on the target object based on the position and posture of the monocular camera 110 in the image acquisition unit 11; estimating a physical distance of a horizontal axis component of a set pixel point in a physical ground coordinate system on the target object based on vanishing points of the target object and the reference object in the air-conditioning room image; the estimated distance between the ranging module itself and the target object is estimated based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component.
The image acquisition unit 11 and the distance generation unit 12 of the distance measurement module 10 may be integrally provided or may be separately provided. When the image pickup section 11 and the distance generation section 12 are provided independently, the image pickup section 11 and the distance generation section 12 are communicatively connected to each other to transmit and receive data to and from each other.
The distance generation section 12 includes a processor 120 and a memory 130. Memory 130 includes, but is not limited to, volatile memory 131, nonvolatile memory 132, and/or memory card slot 133, among others. The processor 120 may cause the distance generating section 12 to realize the corresponding function by executing a specific program stored in the memory 130.
The processor 120 is provided with a communication interface 121, and when the image capturing section 11 and the distance generating section 12 are independently provided, they are connected through the communication interface 121, so that the image capturing section 11 and the distance generating section 12 are communicatively connected to each other to transmit and receive data. The communication interface 121 may be a wired communication interface 121 or a wireless communication interface 121.
The processor 120 in the distance generating section 12 is also configured to control the operation of the image capturing section 11, for example, to control the operation of the monocular camera 110, that is, the processor 120 causes the monocular camera 110 in the image capturing section 11 to capture an air-conditioned room image or to stop capturing an air-conditioned room image by executing a specific program stored in the memory 130. The storage section is also configured to hold the air-conditioning room image and/or the image processed in the middle process acquired by the image acquisition section 11.
The memory card slot 133 may be inserted with a removable medium such as a memory card, and the processor 120 may perform writing or reading operations on the memory card when the memory card is inserted, for example, may store or read images including the virtual reference object and/or the target object and/or images processed in the middle acquired by the image acquisition unit 11 into or from the memory card.
In some alternative embodiments of the present application, an air conditioning system may include an indoor unit; in other alternative embodiments of the present application, an air conditioning system may include a plurality of indoor units. The indoor unit may employ a wall-mounted air-blowing structure, a floor-mounted air-blowing structure, a duct-type air-blowing structure, or an air-blowing structure embedded in a ceiling, etc. The air supply structure comprises a shell, wherein the shell is provided with an air return port for sucking air and an air supply port for supplying the treated air into an air-conditioning room. An indoor fan is arranged in the shell. The ranging module 10 is disposed in the indoor unit, and may be located in the indoor unit, with the monocular camera 110 embedded in the housing or protruding outside the housing, or used in cooperation with the indoor unit.
The indoor unit is provided with an indoor unit control circuit, and the indoor unit control circuit is preferably provided with an indoor controller. The indoor controller is configured to drive the indoor fan to work, display various parameters on the display panel, interact with human, receive and process sampling signals of various sensors and realize necessary communication functions. The indoor controller is communicatively connected to the ranging module 10 to transmit data. The indoor controller may drive the indoor fan to operate in different modes based on the distance estimated by the ranging module 10, or communicate with an outdoor controller in the outdoor unit, and further drive the compressor, expansion valve, four-way valve, etc. in the air conditioning system to operate by the outdoor controller.
The processing performed by the ranging module 10 will be described below with reference to the flowchart of fig. 3.
Step S101: the distance generation section 12 acquires the own position and posture of the monocular camera 110 in the image acquisition section 11. The position and posture of the monocular camera 110 can be written in the memory 130 of the ranging module 10 in advance by a technician for calling at any time, or can be measured by a position sensor, an inertial sensor and the like and stored in the memory 130 of the ranging module 10 for calling at any time. The self-position and attitude of the monocular camera 110 includes, but is not limited to, the mounting height, pitch angle, and mounting angle of the monocular camera 110.
Illustratively, in some alternative embodiments of the present application, according to the invoked self position and posture of the monocular camera 110, an installer is guided to debug the self position and posture of the monocular camera 110 in an air conditioner installation room on site, so as to ensure that the self position and posture of the monocular camera 110 are consistent with the values written and stored in advance. The pre-stored position and posture of the monocular camera 110 itself can ensure that the photographed image can cover the entire floor of the air-conditioned room (or effective supply area).
Illustratively, in some alternative embodiments of the present application, one or more position sensors are provided on the housing of the indoor unit. The position sensor may detect the position and the posture of the monocular camera 110 with respect to the indoor unit housing. If the position and the posture of the monocular camera 110 are changed during the use process, the position and the posture of the monocular camera 110 can be adjusted to be consistent with the pre-stored position and posture of the monocular camera 110 based on the detection result of the position sensor, so that the ranging module 10 can be used normally.
Illustratively, in some alternative embodiments of the present application, an inertial sensor is provided in the ranging module 10. The inertial sensor may detect the position and the posture of the monocular camera 110 with respect to the indoor unit housing. If the position and the posture of the monocular camera 110 are changed during the use process, the position and the posture of the monocular camera 110 can be adjusted to be consistent with the pre-stored position and posture of the monocular camera 110 based on the detection result of the inertial sensor, so that the ranging module 10 can be used normally.
Illustratively, in some alternative embodiments of the present application, a position for installing the monocular camera 110 is provided on the housing of the indoor unit, for example, a wall-mounted indoor unit, and in an installed state, a height between the monocular camera 110 and the ground is 2.6 meters, and the inclination angle (hereinafter simply referred to as an installation angle) is 40 ° from top to bottom with respect to a vertical direction (wall direction). The field of view of the monocular camera 110 may cover the entire air-conditioned room, with the monocular camera having a horizontal field angle of 122 ° and a tilt field angle (hereinafter referred to simply as a pitch angle, pitch in the z-axis direction) of 67 ° as an example.
The air-conditioning room images photographed by the monocular camera 110 are stored in a picture format and can be classified into 320×240, 640×480, 1024×768, 1280×1024, 1920×1080, and the like according to the camera resolution, and 1920×1080 will be taken as an example hereinafter.
Step S102: the distance generation section 12 acquires the air-conditioning room image including the target object acquired by the image acquisition section 11 through photographing, and selects the target object in its middle frame using the target detection model.
Illustratively, in some alternative embodiments of the present application, the object detection model may be YOLO (You Only Look Once), which refers to the category and location of objects in the map that need to be viewed once to be identified. Specifically, firstly, analyzing an air conditioner room image through computer graphics (or deep learning), finding out a plurality of areas where objects possibly exist, cutting the areas in a rectangular frame form, putting the areas into a picture classifier, classifying the areas by the classifier, namely, identifying a target object, and determining the position of the target object; the pose of the target object, such as standing, sitting and prone, may be further determined. The training of the object detection model is not the protection focus of the present application, and is not described herein by using the mature technology in the prior art. In the following embodiments of the present application, description will be made taking as an example a target object (person) and sitting and standing postures. The target object may also be an animal or other static object.
Step S103: after the target object is selected by the target detection model frame, storing pixel coordinates of a starting point and an ending point of a rectangular frame where the target object is located. The pixel at the starting point of the target object is marked as (x min ，y min ) The pixel at the end point of the target object is marked as (x max ，y max ). The starting point and the ending point of the target object are a group of diagonal points of the rectangular frame where the target object is located.
Step S104: and determining a set pixel point of the target object.
The set pixel point may be any set point on the first position of the target object; when the target object is a person, the first position may be a foot of the person, and the setting pixel point as a midpoint of the foot may be:
the set pixel point can also be any set point on the second position of the target object; when the target object is a person, the second position may be the head of the person, the pixel point is set as the midpoint of the head,
in this embodiment, a description will be given of a midpoint of the leg portion as a set pixel point.
Step S105: the distance generation unit estimates the physical distance of the vertical axis component of the pixel point in the physical ground coordinate system on the target object based on the position and posture of the monocular camera.
For a monocular camera, the depth of field cannot be judged and the distance cannot be estimated by only imaging an air-conditioning room image, but the angle between a certain point in the image and the monocular camera with a specific self position and posture is fixed. Based on this, a physical ground coordinate system can be established, the specific principle of which is shown in fig. 4 and 5.
Specifically, in the rectangular space coordinate system, 3 unit vectors i, j, k in the same directions as the x-axis, y-axis and z-axis are taken as a group of substrates, a coordinate origin O is taken as a starting point, and as known from the basic space theorem, there are only one group of real numbers x, y and z such that a=xi+yj+zk, (x, y and z) are coordinates of the P point, and a is a position vector of the P point. Correspondingly, in the physical ground coordinate system, the physical distance of the transverse axis component of the position vector a in the x-axis direction in the physical ground coordinate system is recorded as xbar, and the position vector a sits on the physical groundThe physical distance of the vertical axis component in the y-axis direction in the system is denoted as y bar . In the embodiment of the present invention, as shown in fig. 5, the left-right direction is defined as the x-axis, the front-rear direction is defined as the y-axis, and the height direction is defined as the z-axis.
Step S106: the distance generation unit estimates a physical distance of a horizontal axis component of the pixel point in the physical floor coordinate system on the target object based on vanishing points of the target object and the reference object in the air-conditioning room image.
Step S107: the estimated distance between the ranging module itself and the target object is estimated based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component.
The method and the device respectively calculate the physical distance of the horizontal axis component and the physical distance of the vertical axis component of the target object, improve the accuracy of the estimated physical distance, and have the advantages of high operation speed and suitability for embedded equipment.
In some alternative embodiments of the present application, the distance generation section is configured to execute a method as shown in fig. 6 to estimate the physical distance y of the vertical axis component of the set pixel point in the physical ground coordinate system on the target object based on the own position and posture of the monocular camera bar 。
Step S201: and acquiring the installation height, the pitch angle and the installation angle of the monocular camera. The installation angle is an included angle between the monocular camera and the height of the air-conditioning room. As shown in fig. 7, the mounting height of the monocular camera is expressed as: h 1 =case_to_group=2.6m; pitch angle is denoted as α=camera_high=67 °; the mounting angle is denoted γ=40°.
Step S202: and estimating the length of the boundary line in the pitching field of view based on the installation height and the installation angle of the monocular camera. As shown in fig. 7, the length of the inner edge of the tilting field of view of the monocular camera, that is, the distance between the monocular camera itself C and the first intersection point P1 when in the lowest top view attitude, the first intersection point being the intersection point of the field of view and the ground when in the lowest top view attitude. As shown in fig. 7, the length of the inner edge of the tilting field of view of the monocular camera is denoted as d, d=h 1 ×cosγ。
Step S203: and estimating a half-shaft pitching view field. The pitch angle of the half shaft is camera shootingHalf of the head pitch field of view, as shown in FIG. 7, half axis pitch angle is denoted as α 0 ，α 0 =pi/360; half-shaft pitching view field a 0 ＝H 1 ×π/360。
Step S204: and estimating the length of a center line segment of the pitching field of view based on the pitch angle of the half shaft and the length of the inner edge line of the pitching field of view. As shown in fig. 7, the length d of the inner side line of the pitching view field of the monocular camera is taken as the waist, the pitch angle alpha is taken as the apex angle, and the length of the central line segment of the pitching view field of the monocular camera is the length of the isosceles triangle perpendicular to the base. As shown in fig. 7, the pitch field centerline segment length is denoted as e, e=d×cos α 0 。
Step S205: and calculating the vertical axis direction half-axis mapping physical distance based on the length of the inner edge of the pitching field and the half-axis pitch angle. According to the principle set forth above, each angle of the monocular camera and the variation range of the angle are fixed values, so that the half-axis mapping physical distance of the half longitudinal axis corresponding to the half-axis pitch angle, namely half of the isosceles triangle base, can be calculated based on the obtained half-axis pitch angle. As shown in fig. 7, the half-axis map physical distance is denoted as c, c=d×sin α 0 The half-axis map physical distance c may be used as a unit of conversion for converting other pixel distances and physical distances.
Step S206: and acquiring the vertical axis pixel distance of the set pixel point under the pixel coordinate system. In the pixel coordinate system, the pixel distance of the set pixel point A1 in the vertical axis direction is calculated. Based on the convention of computer graphics, the origin of the pixel coordinate system is set at the upper left corner of the image, the u-axis is the horizontal direction, and the v-axis is the vertical direction. To facilitate the half-axis calculation, it can be understood that the origin of the pixel coordinate system is set at the center of the image at the time of the calculation below, and the directions of the u-axis and v-axis are unchanged (as shown in fig. 8). Based on the pixel coordinate system of the graph, the vertical axis pixel distance of the set pixel point A1 under the pixel coordinate system can be expressed as a, a=540-y a1 . When the pixel point A1 is set as the midpoint of the foot, there is y a1 ＝y max The method comprises the steps of carrying out a first treatment on the surface of the I.e. a=540-y max 。
Step S207: presume the set image on the basis of the pixel distance of vertical axis, half axis map physical distance and half axis pixel distance presumptionThe mapped physical distance of the pixel. In the pixel coordinate system shown in fig. 7, the vertical axis pixel distance corresponds to half of the maximum pixel value in the vertical direction, i.e., 540 pixels. Setting the mapping physical distance a of the pixel point bar The calculation can be made by the following formula: a, a bar The physical distance of projection of pixel point A1 on the bottom side of the isosceles triangle is set.
Step S208: estimating a pitching angle based on the mapping physical distance of the set pixel point and the pitching field of view central line segment length; as shown in FIG. 7, the pitch angle is denoted as α 1 ，α 1 ＝arctan(a bar /e)。
Step S209: based on the installation height, the half-axis pitch angle, the pitching angle and the installation angle of the monocular camera, the physical distance y of the longitudinal axis component of the pixel point in the physical ground coordinate system is estimated and set bar ，y bar ＝H 1 ×tan(a 0 -α 1 +γ)。
In some alternative embodiments of the present application, the distance generating section is configured to perform a method as shown in fig. 9 to estimate a physical distance of a horizontal axis component of a set pixel point on the target object in the physical floor coordinate system based on vanishing points of the target object and the reference object in the air-conditioning room image.
Step S301: the intersection points generated by the extension lines of the set pixel points on the target object (shown as Lr in fig. 11) and the extension lines of the plurality of reference objects are taken as vanishing points (shown as Vp in fig. 11).
An example of an air-conditioning room image acquired by a monocular camera based on photographing is shown in fig. 10, in which a rectangular frame is a framed target object and square tiles in the image are reference images. According to computer graphics, when a monocular camera is used, in a two-dimensional air-conditioning room image at a monocular viewing angle, in a front-rear direction (i.e., a longitudinal axis direction) with the monocular camera as a starting point, all lines parallel to the longitudinal axis are extended and compared with the same point, i.e., a vanishing point of the air-conditioning room image. The physical distance from each point on these lines parallel to the longitudinal axis is equal. That is, as shown in the exemplary picture, the physical distances from each point on the target object set pixel extension line to the vertical axis are equal with respect to the image, i.e., the point on the edge of the same tile to the vertical axis. Based on this principle, the physical distance of the horizontal axis component of the set pixel point in the physical ground coordinate system on the target object can be estimated.
Step S302: a calculation coordinate system is established, and the vertical axis (shown as Y2' in fig. 11) of the calculation coordinate system is a vertical line passing through the vanishing point Vp and perpendicular to the longitudinal direction of the air-conditioning room image (shown as lmg in fig. 11).
Step S303: acquiring a horizontal axis pixel distance and a vertical axis pixel distance of a set pixel point under a pixel coordinate system (o 1-x1y1 coordinate system); taking the foot of the human body as an example, namelyAnd y max 。
Step S304: the vanishing point pixel distance b, b between the vanishing point Vp and the lengthwise edge of the image of the air-conditioned room away from itself is obtained from the measurement.
Step S305: the calculation included angle β of the set pixel point is calculated based on the horizontal axis pixel distance, the vertical axis pixel distance, and the vanishing point pixel distance, and as shown in fig. 11, there is:for ease of calculation, in the method shown in fig. 9, the origin of the pixel coordinate system is shown at o1 in the upper left corner of the picture.
Step S306: generating a standard reference line in an air-conditioned room image (e.g., L in FIG. 11 s As shown), the standard reference line is a straight line which passes through the extension line of the set pixel point on the target object and the extension lines of a plurality of reference objects and has the minimum distortion, for example, a connecting line with the minimum distortion of the edges of a plurality of tiles in the horizontal direction, and the standard reference line L s Seen perpendicular to the longitudinal axis of the calculated coordinate system. Standard reference line L s May be measured or directly specified.
Step S307: a standard reference intersection point (shown as M1 in fig. 11) between the extended line passing through the set pixel point and the standard reference line is acquired, and the physical distance between the standard reference intersection point M1 and the vertical axis Y2' of the calculation coordinate system is taken as the physical distance of the horizontal axis component of the set pixel point in the physical ground coordinate system on the target object.
More specifically, the physical distance between the standard reference intersection point M1 and the longitudinal axis Y2' of the calculation coordinate system can be calculated by the method as shown in fig. 12.
Step S401: dividing a standard reference line into a plurality of length units based on the physical distance of the reference object; for example, in the real world, the edge length of a tile may be 0.6 meters, 0.8 meters, 1 meter, etc. When the standard reference line comprises a plurality of tiles, i.e. the standard reference line is divided into a plurality of length units based on the edge length of the tiles, the physical distance of each length unit is denoted as the edge length of the tile.
Step S402: obtaining a unit pixel distance corresponding to the length unit, where the unit pixel distance of the length unit may be measured, as shown, and the unit pixel distance is denoted as x tile 。
Step S403: the ratio of the physical distance in length units and the unit pixel distance is calculated as the pixel unit, i.e., the actual physical distance represented by each pixel.
Step S404: obtaining a pixel distance between the standard reference intersection point and the vertical axis of the calculation coordinate system, as shown in fig. 11, the pixel distance between the standard reference intersection point and the vertical axis of the calculation coordinate system is expressed as x pi ；x pi =tan β× (b-b'); where b 'is the pixel distance between the standard reference line and the lengthwise edge of the air-conditioning room image away from the vanishing point, b' can be measured.
Step S405: pixel distance x between standard reference intersection point and vertical axis of calculation coordinate system by pixel unit pi Converting into a physical distance as a physical distance x of a horizontal axis component of a pixel point set on the target object in a physical ground coordinate system bar 。
In some embodiments of the present application, the distance generation section is further configured to correct distortion of the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component using a neural network. The physical distance of the horizontal axis component and the physical distance of the vertical axis component are recorded in a two-dimensional plane in a plurality of points, that is, the positions of the plurality of points are corrected by the distance generating section to obtain a plurality of points after distortion correction, that is, the physical distance of the horizontal axis component and the physical distance of the vertical axis component after distortion correction.
In principle, the distortion of a monocular camera that takes a picture is caused by a lens distortion lens in an optical assembly, and common distortion classifications include barrel distortion as shown in fig. 13, pincushion distortion as shown in fig. 14, and moustache distortion as shown in fig. 15, etc. The lens purchased by the monocular camera is determined, and the distortion is the same. After the physical distance of the horizontal axis component and the physical distance of the vertical axis component are obtained, distortion is required to be corrected, generally, distortion is less on the axes in the horizontal direction and the vertical direction, distortion gradually increases from the near to the far along with the distance from the center point, and the deviation of the correction effect of the traditional Zhang Zhengyou calibration correction formula and the coincidence degree of measured data is larger. Thus, in some embodiments of the application, a neural network is constructed by a deep learning method, with known points being used to train the neural network. And inputting the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component into a trained neural network, and then automatically correcting distortion.
Specifically, the steps shown in fig. 17 are included:
step S501: obtaining a real distance matrix
In order to conveniently acquire real world coordinate values, as shown in fig. 16, the two-dimensional view field range of the monocular camera is divided into N square grids by taking the right lower side of the monocular camera as the origin of coordinates and 0.8 meter in unit length; wherein the unit length may be of other dimensions. One person stands successively on the vertices of all squares, N images are taken with a monocular camera, and the image obtained by the taking is combined with the coordinates (x actx ,y actx ) In association, where x=1, 2, N; a true distance matrix is obtained for each measurement point, wherein repeated vertices are recorded only once.
Step S502: recognition using the object recognition model in the N images photographed in step S501And selecting the human body by the frame, and obtaining a set pixel point corresponding to the rectangular frame and the foot center point. Estimating a physical distance (x) of a horizontal axis component and a physical distance (x) of a vertical axis component of a pixel point set on the target object in the physical ground coordinate system prex ，y prex ) Wherein x=1, 2, N; and obtaining a prediction distance matrix of each prediction point.
Step S503: obtaining a deviation value matrix: taking a matrix formed by deviation values of corresponding matrix elements in the real distance matrix and the predicted distance matrix as a deviation value matrix D, D= (D) x ，d y ) Wherein d is x ＝x actx -x prex ；d y ＝y actx -y prex 。
Step S504: and setting a neural network structure and inputting a deviation value matrix. The neural network structure includes input_size, hidden_size, output_size, batch_size, input layer function, activation function, and output layer function of the neural network.
Step S505: and setting a loss function and an optimizer of the neural network.
Step S506: training the neural network and obtaining distortion correction parameters.
Step S507: and correcting distortion of the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component by using the trained neural network. The distribution of vertices before correction and vertices after correction is shown in fig. 18.
The real distance data is collected by using a gridding method, and training data is formed by the real distance data and the predicted data obtained by a vanishing point method, so that the influence of distortion is eliminated, the detection precision is further improved, and the method is particularly suitable for wide-angle lenses.
In some embodiments of the present application, the target object is a person, and after the relative distance between the target object and the ranging module is identified, an intelligent air conditioning effect is achieved by using the air conditioning system. The target object has a certain set height in the height direction of the air-conditioned room. To achieve more precise control of the air conditioning system, for example, zoned air supply or starting of indoor fans at different positions according to height.
In other embodiments of the application, in an air conditioning roomDetermining foot setting pixel point A on target object of inter-image 1 And a head set pixel point A 2 . The distance generation unit is further configured to estimate the height of the target object based on the physical distance of the vertical axis component of the foot-set pixel point in the physical ground coordinate system, and the physical distance of the vertical axis component of the head-set pixel point in the physical ground coordinate system.
As shown, the height of the target object is defined by line segment A 1 A 2 The representation, based on the similarity of triangles, is:
A 1 A 2 ＝H 1 ×(a 2 -a 1 )/a 2
wherein a is 2 Representing the physical distance of the vertical axis component of the head set pixel point in the physical ground coordinate system, a 1 The physical distance of the vertical axis component of the foot-setting pixel point in the physical ground coordinate system is represented.
In some embodiments of the present application, the distance generating unit is configured to estimate an estimated distance between the foot setting pixel and the estimation module itself, and the distance for estimating the distance between the foot setting pixel and the estimation module itself foot The representation is:
in some embodiments of the present application, the distance generating unit is configured to estimate an estimated distance between the head-set pixel and the estimation module itself, and the distance for estimating the distance between the head-set pixel and the estimation module itself head The representation is:
in some embodiments of the present application, the distance generation section is configured to estimate the head pitch angle and the foot pitch angle based on a physical distance of a longitudinal axis component of the foot-setting pixel point in the physical ground coordinate system, a mounting height of the monocular camera, and a height.
Head pitch angleExpressed as: angle of pitch_head ；angle pitch_head ＝arctan(a 1 /(H 1 -A 1 A 2 ))；
The foot pitch angle is expressed as: angle of pitch_foo t；angle pitch_foot ＝arctan(a 1 /H 1 )。
In some embodiments of the present application, the distance generation section is configured to estimate the head heading angle and the foot heading angle based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component of the foot-setting pixel point in the physical ground coordinate system, and the physical distance of the vertical axis component of the head-setting pixel point in the physical ground coordinate system.
The head heading angle is expressed as: angle of yaw_head ；angle vaw_head ＝arctan(x head /a 1 )+π/2；
The foot heading angle is expressed as: angle of yaw_foot ；angle yaw_foot ＝arctan(x foot /a 1 )+π/2。
The head pitch angle, the foot pitch angle, the head course angle and the foot course angle are all expressed by radians. Based on the estimated distance foot 、distance head And the head pitch angle, the foot pitch angle, the head course angle and the foot course angle, the air deflector of the air conditioner air outlet can be controlled more accurately, and the use comfort of a user is improved.
In some embodiments of the present application, the distance generating part in the air conditioning system may estimate the longitudinal distance between the set pixel point and the ranging module on the target object based on the position and the posture of the monocular camera alone, for example, under the condition that the air supply angle is determined, the air conditioning system may precisely adjust the wind speed of the indoor fan or adjust the operation frequency of the compressor according to the longitudinal distance. The self position and posture of the monocular camera comprise the installation height, pitch angle and installation angle of the monocular camera. The installation angle is the included angle between the monocular camera and the height direction of the air-conditioning room. In such an application scenario, the ranging module performs the steps as shown. The detailed description of the steps in the drawings is referred to above, and will not be repeated here.
In some embodiments of the present application, the distance generating unit of the air conditioning system may further estimate a lateral distance between the set pixel point on the target object and the ranging module based on only vanishing points of the target object and the reference object in the air conditioning room image, for example, further adjust an air deflector of the air outlet, so as to implement control targets of the air supply following the user or the air supply avoiding user. In such an application scenario, the ranging module performs the steps as shown. The detailed description of the steps in the drawings is referred to above, and will not be repeated here.
In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present application should be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. An air conditioning system, comprising:
a distance measuring module is provided with:
An image acquisition section including a monocular camera, the image acquisition section configured to acquire an air-conditioning room image by photographing, the air-conditioning room image including a target object and a reference object; and
a distance generation unit configured to estimate a physical distance of a vertical axis component of a set pixel point in a physical ground coordinate system on the target object based on a position and a posture of the monocular camera; estimating the physical distance of a horizontal axis component of a set pixel point in a physical ground coordinate system on the target object based on vanishing points of the target object and a reference object in an air-conditioning room image; based on the physical distance of the horizontal axis component and the physical distance of the vertical axis component, an estimated distance between the ranging module and the target object is estimated; wherein the target object in the air-conditioned room image is identified using a target detection model.
2. An air conditioning system according to claim 1, wherein,
the distance generation section is configured to execute a method of estimating a physical distance of a vertical axis component of a set pixel point in a physical ground coordinate system on the target object based on a self position and an attitude of the monocular camera:
Acquiring the installation height, the pitch angle and the installation angle of the monocular camera; the installation angle is an included angle between the monocular camera and the height direction of the air-conditioning room;
estimating the length of the boundary line in the pitching visual field based on the installation height and the installation angle of the monocular camera;
estimating a half-shaft pitch angle;
estimating a pitch field centerline length based on the semi-axis pitch angle and the pitch field inner edge length;
calculating a vertical axis direction half-axis mapping physical distance based on the length of the inner side line of the pitching field and the half-axis pitch angle;
acquiring a vertical axis pixel distance of a set pixel point under a pixel coordinate system;
estimating a mapping physical distance of the set pixel point based on the vertical axis pixel distance, the half axis mapping physical distance and the half axis pixel distance;
estimating a pitching angle based on the mapping physical distance of the set pixel point and the pitching field of view centerline segment length;
and estimating the physical distance of the longitudinal axis component of the set pixel point in a physical ground coordinate system based on the installation height of the monocular camera, the semi-axis pitch angle, the pitch angle and the installation angle.
3. An air conditioning system according to claim 1, wherein,
The distance generation section is configured to execute a method of estimating a physical distance of a horizontal axis component of a set pixel point on a target object in a physical ground coordinate system based on vanishing points of the target object and a reference object in an air-conditioning room image:
setting an extension line of a pixel point on a target object and taking intersection points generated by extension lines of a plurality of reference objects as vanishing points;
establishing a computing coordinate system, wherein the vertical axis of the computing coordinate system is a vertical line passing through the vanishing point and perpendicular to the length direction of the air-conditioning room image;
acquiring a horizontal axis pixel distance and a vertical axis pixel distance of a set pixel point under a pixel coordinate system;
acquiring vanishing point pixel distances between the vanishing points and longitudinal edges of the air-conditioning room image that are away from the vanishing points;
calculating a calculation included angle of a set pixel point based on the horizontal axis pixel distance, the vertical axis pixel distance and the vanishing point pixel distance;
generating a standard reference line in the air-conditioning room image, wherein the standard reference line is a straight line which passes through the extension line and has minimum distortion;
acquiring a standard reference intersection point; taking the distance between the standard reference intersection point and the vertical axis of the calculation coordinate system as the physical distance of the horizontal axis component of the pixel point in the physical ground coordinate system on the target object; the standard reference intersection point is an intersection point between an extension line passing through the set pixel point and a standard reference line.
4. An air conditioning system according to claim 3, wherein,
the distance generation section is further configured to execute a method of estimating a physical distance of a horizontal axis component of a set pixel point on a target object in a physical ground coordinate system based on vanishing points of the target object and a reference object in an air-conditioning room image:
dividing the standard reference line into a plurality of length units based on the physical distance of the reference object;
acquiring a unit pixel distance corresponding to the length unit;
calculating the ratio of the physical distance of the length unit to the unit pixel distance as a pixel unit;
acquiring a pixel distance between the standard reference intersection point and a longitudinal axis of the calculation coordinate system;
and converting the pixel distance between the standard reference intersection point and the vertical axis of the calculation coordinate system into a physical distance by using the pixel unit, wherein the physical distance is used as the physical distance of the horizontal axis component of the pixel point on the target object in the physical ground coordinate system.
5. An air conditioning system according to any of claims 1 to 4, characterized in that,
the distance generation section is further configured to perform distortion correction on the obtained physical distance of the horizontal axis component and the physical distance of the vertical axis component using a neural network.
6. An air conditioning system according to claim 5, wherein,
the target object is a person;
the set pixel points of the target object comprise foot set pixel points and head set pixel points;
the distance generation section is further configured to:
estimating the height of the target object based on the physical distance of the vertical axis component of the foot set pixel point in the physical ground coordinate system, the physical distance of the vertical axis component of the head set pixel point in the physical ground coordinate system, and the installation height of the monocular camera;
and/or calculating an estimated distance between the foot-setting pixel point and the estimation module itself based on a physical distance of a vertical axis component of the foot-setting pixel point in a physical ground coordinate system and a mounting height of the monocular camera;
and/or calculating an estimated distance between the head set pixel point and an estimation module itself based on a physical distance of a vertical axis component of the foot set pixel point in a physical ground coordinate system, an installation height of a monocular camera, and a height of the target object.
7. An air conditioning system according to claim 6, wherein,
the distance generation section is further configured to:
Estimating a head pitch angle based on the physical distance of the vertical axis component of the foot-set pixel point in a physical ground coordinate system, the installation height of the monocular camera and the height of the target object;
and/or estimating the foot pitch angle based on the physical distance of the vertical axis component of the foot setting pixel point in the physical ground coordinate system and the mounting height of the monocular camera.
8. An air conditioning system according to claim 5, wherein,
the target object is a person;
the set pixel points of the target object comprise foot set pixel points and head pixel points;
the distance generation section is further configured to:
estimating a head course angle based on the physical distance of the vertical axis component of the foot setting pixel point in the physical ground coordinate system and the abscissa of the head setting pixel point in the pixel coordinate system;
and/or estimating the foot course angle based on the physical distance of the vertical axis component of the foot setting pixel point in the physical ground coordinate system and the abscissa of the foot setting pixel point in the pixel coordinate system.
9. An air conditioning system, comprising:
a distance measuring module is provided with:
an image acquisition section including a monocular camera, the image acquisition section configured to acquire an image of an air-conditioning room by photographing, the air-conditioning room image including a target object; and
A distance generation part configured to perform a method of estimating a longitudinal distance between a set pixel point on the target object and the ranging module based on a self position and an attitude of the monocular camera, wherein the self position and the attitude of the monocular camera include a mounting height, a pitch angle, and a mounting angle of the monocular camera, and the mounting angle is an included angle between the monocular camera itself and a height direction of an air-conditioning room:
estimating the length of the boundary line in the pitching visual field based on the installation height and the installation angle of the monocular camera;
estimating a half-shaft pitch angle;
estimating a pitch field centerline length based on the semi-axis pitch angle and the pitch field inner edge length;
calculating a vertical axis direction half-axis mapping physical distance based on the length of the inner side line of the pitching field and the half-axis pitch angle;
acquiring a vertical axis pixel distance of a set pixel point under a pixel coordinate system;
estimating a mapping physical distance of a set pixel point based on the vertical axis pixel distance, the half-axis mapping physical distance and the half-axis pixel distance;
estimating a pitching angle based on the mapping physical distance of the set pixel point and the pitching field of view centerline segment length;
And estimating the physical distance of a longitudinal axis component of the set pixel point in a physical ground coordinate system based on the installation height, the semi-axis pitch angle, the pitch angle and the installation angle of the monocular camera, and taking the physical distance of the longitudinal axis component as the longitudinal distance between the set pixel point and the monocular camera.
10. An air conditioning system, comprising:
a distance measuring module is provided with:
an image acquisition section including a monocular camera configured to acquire an image of an air-conditioning room by photographing, the air-conditioning room image including a target object and a reference object; and
a distance generation section configured to perform a method of estimating a lateral distance between a set pixel point on a target object and the ranging module based on vanishing points of the target object and a reference object in an air-conditioning room image:
setting an extension line of a pixel point on a target object and taking intersection points generated by extension lines of a plurality of reference objects as vanishing points;
establishing a computing coordinate system, wherein the vertical axis of the computing coordinate system is a vertical line passing through the vanishing point and perpendicular to the length direction of the air-conditioning room image;
Acquiring a horizontal axis pixel distance and a vertical axis pixel distance of a set pixel point under a pixel coordinate system;
acquiring vanishing point pixel distances between the vanishing points and longitudinal edges of the air-conditioning room image that are away from the vanishing points;
calculating a calculation included angle of a set pixel point based on the horizontal axis pixel distance, the vertical axis pixel distance and the vanishing point pixel distance;
generating a standard reference line in the air-conditioning room image, wherein the standard reference line is a straight line which passes through the extension line and has minimum distortion;
acquiring a standard reference intersection point; taking the distance between the standard reference intersection point and the longitudinal axis of the calculation coordinate system as the transverse distance between the set pixel point on the target object and the ranging module; the standard reference intersection point is an intersection point between an extension line passing through the set pixel point and a standard reference line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310531866.4A CN116753919A (en) | 2023-05-11 | 2023-05-11 | Air Conditioning System |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310531866.4A CN116753919A (en) | 2023-05-11 | 2023-05-11 | Air Conditioning System |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116753919A true CN116753919A (en) | 2023-09-15 |
Family
ID=87956085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310531866.4A Pending CN116753919A (en) | 2023-05-11 | 2023-05-11 | Air Conditioning System |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116753919A (en) |
-
2023
- 2023-05-11 CN CN202310531866.4A patent/CN116753919A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5815490B2 (en) | Air conditioner | |
| US9715627B2 (en) | Area information estimating device, area information estimating method, and air conditioning apparatus | |
| JP5819271B2 (en) | Air conditioner | |
| JP5238679B2 (en) | Air conditioning control device, air conditioning control method, and radiation temperature measuring device | |
| JP6335425B2 (en) | Air conditioner | |
| JP6596269B2 (en) | Air conditioner | |
| CN107305035B (en) | Air conditioner | |
| CN109477655B (en) | Air conditioner | |
| JP5879221B2 (en) | Air conditioner | |
| JP2010190432A (en) | Spatial recognition device and air conditioner | |
| JP2016048128A (en) | Air conditioner | |
| CN109564023A (en) | Air-conditioning device | |
| JP2015190666A (en) | Indoor machine of air conditioning machine, and air conditioning machine using the same | |
| CN111104904A (en) | Human body identification method and device and courtyard machine | |
| JP2016017707A (en) | Air conditioning system | |
| JP5289118B2 (en) | Air conditioner | |
| JP5879220B2 (en) | Air conditioner | |
| JP6925530B2 (en) | Air conditioner, air conditioner system and temperature measurement method | |
| JP4227037B2 (en) | Imaging system and calibration method | |
| CN104422084B (en) | Air conditioner | |
| CN211427362U (en) | Human body recognition device and courtyard machine | |
| CN116753919A (en) | Air Conditioning System | |
| JP5289518B2 (en) | Air conditioner and radiation temperature calculation method | |
| JP7061917B2 (en) | Air conditioner | |
| CN116734807A (en) | Air conditioning device |
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 |