CN112032987A - Air conditioner control method and device based on infrared human body tracking - Google Patents

Air conditioner control method and device based on infrared human body tracking Download PDF

Info

Publication number
CN112032987A
CN112032987A CN202010740565.9A CN202010740565A CN112032987A CN 112032987 A CN112032987 A CN 112032987A CN 202010740565 A CN202010740565 A CN 202010740565A CN 112032987 A CN112032987 A CN 112032987A
Authority
CN
China
Prior art keywords
human body
position information
body position
unit
motion track
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.)
Granted
Application number
CN202010740565.9A
Other languages
Chinese (zh)
Other versions
CN112032987B (en
Inventor
许德海
李昱兵
汪伟
任明艺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Hongmei Intelligent Technology Co Ltd
Original Assignee
Sichuan Hongmei Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Hongmei Intelligent Technology Co Ltd filed Critical Sichuan Hongmei Intelligent Technology Co Ltd
Priority to CN202010740565.9A priority Critical patent/CN112032987B/en
Publication of CN112032987A publication Critical patent/CN112032987A/en
Application granted granted Critical
Publication of CN112032987B publication Critical patent/CN112032987B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/89Arrangement or mounting of control or safety devices
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/62Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63Electronic processing
    • F24F11/64Electronic processing using pre-stored data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00Control inputs relating to users or occupants
    • F24F2120/10Occupancy
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10048Infrared image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30196Human being; Person

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Combustion & Propulsion (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Signal Processing (AREA)
  • Mechanical Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Air Conditioning Control Device (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides an air conditioner control method and device based on infrared human body tracking, which utilizes an infrared detector to acquire an infrared image for a preset image acquisition area at one time, identifies human body images from the infrared image acquired at the current time, determines first human body position information of a corresponding user according to the position of each human body image in the infrared image, acquires at least one piece of second human body position information, generates a cost matrix according to each first human body position information and each second human body position information, solves the cost matrix by using a Hungarian algorithm to acquire the optimal solution of the cost matrix, determines a human body motion track matched with the first human body position information according to the optimal solution of the cost matrix, updates the human body motion track according to the first human body position information matched with the human body motion track, and controlling the air supply strategy of the air conditioner according to the updated motion tracks of the human bodies. This scheme can improve the accuracy of air conditioner control.

Description

Air conditioner control method and device based on infrared human body tracking
Technical Field
The invention relates to the technical field of air conditioners, in particular to an air conditioner control method and device based on infrared human body tracking.
Background
The household air conditioner achieves the purpose of human body comfort by adjusting the parameters of the air in the room, such as temperature, humidity, air flow rate and the like. With the continuous development of intelligent technology, the requirements of users on the functions and the performances of the air conditioner are not only simple refrigeration and heating, but also include the requirements of health, comfort, intelligence, environmental protection and the like. At present, relevant functions of the air conditioner in the market are added, for example, a certain fresh air exchange function is used for improving indoor air quality, a unique air supply direction is used for achieving a more comfortable body sensing effect, a voice recognition function can be detected and achieved so as to achieve a more convenient man-machine interaction mode, and the like.
Chinese patent No. CN110822662A discloses an air conditioner control method, device, air conditioner and storage medium. According to the invention, the infrared detection device arranged on the air conditioner is controlled to emit the infrared scanning lines to different directions, and the operation parameters of the air conditioner are controlled according to the detection results of the infrared scanning lines in the first direction and the second direction, so that the air conditioner is more accurately controlled.
However, the infrared detection device is used for emitting different infrared scanning lines, and then the purpose of controlling the air conditioner is achieved according to infrared detection results in different directions, and the problem that the air conditioner control accuracy is poor still exists.
Disclosure of Invention
The embodiment of the invention provides an air conditioner control method and device based on infrared human body tracking, which can improve the accuracy of air conditioner control.
In a first aspect, an embodiment of the present invention provides an air conditioner control method based on infrared human body tracking, including:
every time a preset image acquisition period passes, carrying out image acquisition on a preset image acquisition area by using an infrared detector to obtain an infrared image;
identifying human body images from first infrared images acquired at the current moment, and respectively determining first human body position information of corresponding users according to the positions of the human body images in the first infrared images, wherein different human body images correspond to different users, and the first human body position information is used for representing the positions of the corresponding users in the image acquisition area at the current moment;
acquiring at least one piece of second human body position information, wherein the second human body position information is acquired according to a second infrared image acquired at the last moment, and the second human body position information is used for representing a predictive result of the position of a corresponding user in the image acquisition area at the current moment;
generating a cost matrix according to each piece of first human body position information and each piece of second human body position information, wherein the number of rows and the number of columns of the cost matrix are respectively equal to the number of the first human body position information and the number of the second human body position information, and elements in the cost matrix are distances between positions represented by the corresponding first human body position information and the second human body position information;
solving the cost matrix by using a Hungarian algorithm to obtain an optimal solution of the cost matrix;
determining a human body motion track matched with each piece of first human body position information according to the optimal solution of the cost matrix, wherein the human body motion track is used for representing the motion track of a corresponding user in the image acquisition area;
aiming at each human body motion track, updating the human body motion track according to the first human body position information matched with the human body motion track;
and controlling an air supply strategy of the air conditioner according to each updated human body motion track, wherein the air supply strategy comprises air supply quantity, air supply angle and air supply temperature.
Optionally, the identifying a human body image from the infrared image acquired at the current moment, and determining first human body position information of the corresponding user according to the position of each human body image in the infrared image respectively includes:
converting an infrared image acquired at the current moment into a binary image;
determining a connected region of each binary image for representing a human body as one human body image;
and aiming at each human body image, acquiring the mean value of the horizontal coordinates of all pixel points in the human body image and the mean value of the vertical coordinates of all pixel points, and sequentially combining the acquired mean values of the horizontal coordinates and the mean values of the vertical coordinates to be used as the first human body position information of the user corresponding to the human body image.
Optionally, the acquiring at least one second human body position information includes:
determining third human body position information of each user according to the second infrared image, wherein the third human body position information is used for representing the position of the corresponding user in the image acquisition area at the last moment;
respectively determining the movement speed and the movement acceleration of the corresponding user between the last moment and the current moment according to each piece of third human body position information;
for each piece of third human body position information, calculating second human body position information corresponding to the third human body position information by a first formula according to the third human body position information and the movement speed and the movement acceleration corresponding to the third human body position information;
the first formula is:
Figure BDA0002606577780000021
wherein x (k) is used for representing the abscissa included in the second human body position information, y (k) is used for representing the ordinate included in the second human body position information, x (k-1) is used for representing the abscissa included in the third human body position information, and y (k-1) is used for representing the abscissa included in the third human body position informationThe v is a vertical coordinate included in the third body position informationx(k-1) the abscissa used to characterize the motion velocity corresponding to the third human body position information, the vy(k-1) for characterizing a ordinate included in the movement velocity corresponding to the third human body position information, the k being for characterizing a current time, and the (k-1) being for characterizing a previous time.
Optionally, the solving the cost matrix by using the hungarian algorithm to obtain an optimal solution of the cost matrix includes:
s1: subtracting the minimum element in each line of the cost square matrix;
s2: subtracting the smallest element in each column of the cost square matrix;
s3: covering all 0 s in the cost square matrix with the fewest horizontal lines and the fewest vertical lines;
s4: determining whether the sum of the numbers of horizontal lines and vertical lines is equal to the sum of the numbers of the first human body position information and the second human body position information, if so, performing S5, otherwise, performing S6;
s5: determining the matrix at the moment as the optimal solution of the cost matrix, and ending the current process;
s6: determining the smallest element in the matrix that is not covered by any horizontal and vertical lines;
s7: s3 is performed after subtracting the minimum element from each row in the matrix that is not covered by a horizontal line and adding the minimum element to each column of the matrix that is covered by a vertical line.
Optionally, the updating, for each human motion trajectory, the human motion trajectory according to the first human position information matched with the human motion trajectory includes:
for each human motion track, executing:
if the first human body position information matched with the human body motion track exists, storing the first human body position information matched with the human body motion track to the tail end of a coordinate sequence corresponding to the human body motion track;
if the first human body position information matched with the human body motion track does not exist, determining that the human body motion track acquired by the image is invisible;
if the number of times that the human motion track is continuously invisible in the periodic image acquisition process is larger than a preset number threshold, deleting the human motion track;
and for each piece of first human body position information, if the human body motion track matched with the human body position information does not exist, creating the human body motion track matched with the first human body position information, and storing the first human body position information into a coordinate sequence corresponding to the created human body motion track.
Optionally, the infrared detector is an array infrared thermopile detector with a large view field, and an acute angle is formed between an optical axis of the infrared detector and the horizontal direction, and the acute angle is downward, wherein the infrared detector is used for detecting a user in a current scene and acquiring human body information in the scene, and the human body information includes a distance between the human body of the user at the current moment and the infrared detector.
Optionally, the updating, for each human motion trajectory, the human motion trajectory according to the first human position information matched with the human motion trajectory includes:
for each human body image in the first infrared image, acquiring the human body temperature of a corresponding user from the first infrared image, and updating the acquired human body temperature into temperature information included in the human body motion track;
for each piece of first human body position information, acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as a human body distance, and updating the human body distance into the distance information included in the human body motion track;
for each piece of human body position information, calculating the movement speed of the corresponding user at the current moment through a second formula, and updating the calculated movement speed into the speed information included in the human body movement track;
the second formula includes:
Figure BDA0002606577780000041
wherein, v isx(k) An abscissa for characterizing the motion speed corresponding to the first human body position information, the vy(k) A vertical coordinate included for characterizing the movement velocity corresponding to the first human body position information, the vx(k-1) the abscissa used to characterize the motion velocity corresponding to the third human body position information, the vy(k-1) a ordinate included in the movement velocity corresponding to the third human body position information, the k being used to represent a current time, and the (k-1) being used to represent a previous time;
optionally, the controlling an air supply strategy of the air conditioner according to the updated motion trajectory of each human body includes:
aiming at each updated human body motion track, calculating the air supply weight corresponding to the human body motion track by using the following third formula;
the third formula is:
Figure BDA0002606577780000042
wherein T isjThe body temperature, v, stored for the jth of the body motion trajectoryxjRepresenting said body velocity in x-direction of a body stored for the jth said body motion trajectory, djRepresenting the human body distance stored in the jth human body motion track;
and determining the human body motion track with the largest corresponding air supply weight as a target human body motion track, and controlling an air supply strategy of the air conditioner according to the target human body motion track.
In a second aspect, an embodiment of the present invention further provides an air conditioner control device based on infrared human body tracking, including: the device comprises an acquisition module, an identification determination module, an acquisition module, a generation module, a solving module, a matching determination module, an updating module and a control module;
the acquisition module is used for acquiring an image once in a preset image acquisition area by using an infrared detector every time a preset image acquisition period passes to obtain an infrared image;
the identification determination module is configured to identify a human body image from the first infrared image acquired by the acquisition module at the current time, and determine first human body position information of a corresponding user according to a position of each human body image in the first infrared image, where different human body images correspond to different users, and the first human body position information is used to represent positions of the corresponding users in the image acquisition area at the current time;
the acquisition module is used for acquiring at least one piece of second human body position information, wherein the second human body position information is acquired according to a second infrared image acquired from the acquisition module at the last moment, and the second human body position information is used for representing a predictive result of the position of the corresponding user in the image acquisition area at the current moment;
the generating module is configured to generate a cost matrix according to first human body position information identified and determined by each identification determining module and second human body position information acquired by each acquiring module, where the number of rows and the number of columns of the cost matrix are respectively equal to the number of the first human body position information and the number of the second human body position information, and an element in the cost matrix is a distance between positions represented by the corresponding first human body position information and the corresponding second human body position information;
the solving module is used for solving the cost matrix generated by the generating module by using a Hungarian algorithm to obtain an optimal solution of the cost matrix;
the matching determination module is configured to determine a human body motion trajectory matched with each piece of first human body position information according to the optimal solution of the cost matrix obtained by the solving module, where the human body motion trajectory is used to represent a motion trajectory of a corresponding user in the image acquisition area;
the updating module is used for updating the human body motion track determined by each matching determination module according to the first human body position information matched with the human body motion track;
and the control module is used for controlling an air supply strategy of the air conditioner according to each human body motion track after the updating module updates, wherein the air supply strategy comprises air supply quantity, an air supply angle and air supply temperature.
Optionally, the identification determination module includes: the device comprises a conversion unit, a determination unit and an acquisition unit;
the conversion unit is used for converting the infrared image acquired at the current moment into a binary image;
the first determining unit is configured to determine a connected region, which is used for representing a human body, in each of the binary images converted by the converting unit as one human body image;
the acquiring unit is configured to acquire, for each human body image determined by the first determining unit, a mean value of abscissa of all pixel points and a mean value of ordinate of all pixel points in the human body image, and use a sequential combination of the acquired mean values of the abscissa and the mean values of the ordinate as the first human body position information of the user corresponding to the human body image.
Optionally, the obtaining module includes: a second determining unit, a third determining unit and a calculating unit;
the second determining unit is configured to determine third human body position information of each user according to the second infrared image, where the third human body position information is used to represent a position of a corresponding user in the image acquisition area at a previous time;
the third determining unit is configured to determine a movement velocity and a movement acceleration of the corresponding user between the previous time and the current time according to the third human body position information determined by each of the second determining units;
the calculating unit is configured to calculate, for each piece of third human body position information determined by the second determining unit, the second human body position information corresponding to the third human body position information according to the third human body position information and the movement velocity and the movement acceleration determined by the third determining unit corresponding to the third human body position information by using a first formula;
the first formula is:
Figure BDA0002606577780000051
optionally, the solving module includes: the device comprises a first subtracting unit, a second subtracting unit, a covering unit, a judging unit, an optimal solution determining unit, a minimum element determining unit and an adding and subtracting unit;
the first subtracting unit is used for subtracting the minimum element in each line of the cost square matrix;
the second subtracting unit is used for subtracting the smallest element in each column of the cost square matrix;
the covering unit is used for covering all 0 s in the cost square matrix after the subtraction of the first subtracting unit and the second subtracting unit with the least horizontal lines and the least vertical lines;
the judging unit is used for judging whether the sum of the number of the horizontal lines and the number of the vertical lines of the covering unit is equal to the sum of the number of the first human body position information and the number of the second human body position information, if so, the covering unit turns to an optimal solution determining unit, and if not, the covering unit turns to a minimum element determining unit;
the optimal solution determining unit is used for determining that the matrix judged by the judging unit is the optimal solution of the cost matrix and stopping the operation work of the solving module;
the minimum element determining unit is configured to determine a minimum element in the matrix that is not covered by any horizontal line and vertical line when the determining unit determines that the matrix is not the optimal solution of the cost matrix;
the addition and subtraction unit is used for subtracting the minimum element determined by the minimum element determining unit from each row which is not covered by the horizontal line in the matrix, and turning to the covering unit after adding the minimum element to each column which is covered by the vertical line in the matrix.
Optionally, the update module includes: matched unit, unmatched unit, deleting unit and creating unit;
the matched unit is used for storing the first human body position information matched with the human body motion track to the tail end of the coordinate sequence corresponding to the human body motion track for the first human body position information matched with the human body motion track existing in each human body motion track;
the unmatched unit is used for determining that the human body motion track acquired by the image acquisition is invisible for the situation that the first human body position information matched with the human body motion track does not exist in the human body motion track;
the deleting unit is used for deleting the human body motion track when the continuous invisible times of the human body motion track in the unmatched unit are larger than a preset time threshold in the periodic image acquisition process aiming at each human body motion track;
the creating unit is configured to, for each piece of the first human body position information, create a human body movement trajectory matched with the first human body position information if the human body movement trajectory matched with the human body position information does not exist, and store the first human body position information in a coordinate sequence corresponding to the created human body movement trajectory.
Optionally, the update module includes: a human body temperature updating unit, a human body distance updating unit and a human body speed updating unit;
the human body temperature updating unit is used for acquiring the human body temperature of a corresponding user from the first infrared image aiming at each human body image in the first infrared image, and updating the acquired human body temperature into the temperature information included in the human body motion trail;
the human body distance updating unit is used for acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as the human body distance according to each piece of first human body position information, and updating the human body distance to the distance information included in the human body motion track;
the human body speed updating unit is used for calculating the movement speed of the corresponding user at the current moment according to the following second formula aiming at each piece of human body position information and updating the calculated movement speed into the speed information included in the human body movement track;
the second formula includes:
Figure BDA0002606577780000071
optionally, the control module comprises: an air supply weight calculation unit and an air conditioner control unit;
the air supply weight calculation unit is used for calculating the air supply weight corresponding to each updated human body motion track by using the following third formula;
the third formula is:
Figure BDA0002606577780000072
and the air conditioner control unit is used for determining the human body motion track with the maximum air supply weight calculated by the air supply weight calculation unit as a target human body motion track and controlling the air supply strategy of the air conditioner according to the target human body motion track.
The air conditioner control method and device based on infrared human body tracking, provided by the embodiment of the invention, firstly utilize an infrared detector to acquire an infrared image for a preset image acquisition area at one time, identify a human body image from the infrared image acquired at the current moment, respectively determine first human body position information of a corresponding user according to the position of each human body image in the infrared image, then obtain a second human body position of the corresponding user at the current moment predicted at the previous moment, then generate a cost matrix according to each first human body position information and each second human body position information, utilize a Hungarian algorithm to solve the cost matrix to obtain an optimal solution of the cost matrix, determine a human body motion track matched with each first human body position information according to the optimal solution of the cost matrix, and aim at each human body motion track, and updating the human body movement track according to the first human body position information matched with the human body movement track, and finally controlling an air supply strategy of the air conditioner according to each updated human body movement track. According to the scheme, the human body target is obtained through infrared image detection, statistical analysis is carried out to extract relevant information, the feasibility of maintaining human body information is guaranteed by tracking and establishing the human body motion track, the air supply strategy of the air conditioner is adjusted in real time according to the corresponding human body motion track, and the accuracy of air conditioner control can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an air conditioner control method based on infrared human body tracking according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an apparatus where an air conditioning control device based on infrared human body tracking according to an embodiment of the present invention is located;
fig. 3 is a schematic diagram of an air conditioning control device based on infrared human body tracking according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an infrared human body tracking-based air conditioning control device including a conversion unit according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an infrared human body tracking based air conditioning control device including a second determination unit according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an infrared human body tracking-based air conditioning control device including a first subtracting unit according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an infrared human body tracking-based air conditioning control device including a matched unit according to an embodiment of the present invention;
fig. 8 is a schematic diagram of an infrared human body tracking-based air conditioning control device including a human body temperature updating unit according to an embodiment of the present invention;
fig. 9 is a schematic diagram of an infrared human body tracking-based air conditioning control apparatus including an air supply weight calculation unit according to an embodiment of the present invention;
fig. 10 is a flowchart of another air conditioning control device based on infrared human body tracking according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides an air conditioner control method based on infrared human body tracking, including the following steps:
step 101: every time a preset image acquisition period passes, carrying out image acquisition on a preset image acquisition area by using an infrared detector to obtain an infrared image;
step 102: identifying human body images from first infrared images acquired at the current moment, and determining first human body position information of a corresponding user according to the position of each human body image in the first infrared images;
step 103: acquiring at least one second human body position information;
step 104: generating a cost matrix according to the first human body position information and the second human body position information;
step 105: solving the cost matrix by using a Hungarian algorithm to obtain an optimal solution of the cost matrix;
step 106: determining a human body motion track matched with each piece of first human body position information according to the optimal solution of the cost matrix;
step 107: aiming at each human body motion track, updating the human body motion track according to first human body position information matched with the human body motion track;
step 108: and controlling the air supply strategy of the air conditioner according to the updated motion tracks of the human bodies.
The air conditioner control method based on infrared human body tracking provided by the embodiment of the invention comprises the steps of firstly carrying out image acquisition on a preset image acquisition area by using an infrared detector to obtain an infrared image, identifying the human body image from the infrared image acquired at the current moment, respectively determining first human body position information of a corresponding user according to the position of each human body image in the infrared image, then obtaining a second human body position of the corresponding user at the current moment predicted at the previous moment, then generating a cost matrix according to each first human body position information and each second human body position information, solving the cost matrix by using a Hungarian algorithm to obtain the optimal solution of the cost matrix, determining a human body motion track matched with each first human body position information according to the optimal solution of the cost matrix, aiming at each human body motion track, according to the first human body position information matched with the human body motion track, and updating the human body motion trail, and finally controlling an air supply strategy of the air conditioner according to each updated human body motion trail. According to the scheme, the human body target is obtained through infrared image detection, statistical analysis is carried out to extract relevant information, the feasibility of maintaining human body information is guaranteed by tracking and establishing the human body motion track, the air supply strategy of the air conditioner is adjusted in real time according to the corresponding human body motion track, and the accuracy of air conditioner control can be improved.
Optionally, in the air-conditioning control method based on infrared human body tracking shown in fig. 1, the step 102 of identifying human body images from the infrared images collected at the current time, and determining first human body position information of a corresponding user according to a position of each human body image in the infrared image includes:
the infrared detector is arranged on the ground and has a certain distance height, an optical axis of the detector forms an acute angle with the horizontal ground, the infrared detector is used for obtaining the distance information of the human body at the current moment, the infrared image collected at the current moment is converted into a binary image, the relevant information of the human body is counted, the detected binary image of the human body is made to be I (x, y), and each connected region used for representing the human body in the binary image is determined to be a human body image BW.
The coordinates of the human body can be obtained by the following formula:
Figure BDA0002606577780000091
wherein x is the abscissa mean value corresponding to all the pixels marked as i in the human body image, and y is the ordinate mean value corresponding to all the pixels marked as i in the human body image.
And combining the obtained horizontal coordinate mean value and the obtained vertical coordinate mean value in sequence to serve as the first human body position information of the user corresponding to the human body image.
In the embodiment of the invention, the infrared detector is set at a certain height, and the optical axis of the infrared detector forms an acute angle with the horizontal ground, so that the infrared detector can detect infrared images of all users in the current scene, the detected infrared images are converted into binary images, and the region including the human body in the current scene is conveniently communicated and determined as the human body image, so that the abscissa and the ordinate of all pixel points marked as i of corresponding users in the human body image are averaged, and the first human body position information of the user corresponding to the human body image is obtained.
Optionally, step 103 obtains at least one piece of second human body position information, specifically as follows:
determining third human body position information of each user according to the second infrared image, wherein the third human body position information is used for representing the position of the corresponding user in the image acquisition area at the last moment, determining the movement speed and the movement acceleration of the corresponding user between the last moment and the current moment according to each piece of third human body position information, and calculating second human body position information corresponding to the third human body position information according to the third human body position information and the movement speed and the movement acceleration corresponding to the third human body position information by using a first formula as follows aiming at each piece of third human body position information, wherein the first formula is as follows:
Figure BDA0002606577780000101
wherein, x (k) is used for representing the horizontal coordinate included by the second human body position information, y (k) is used for representing the vertical coordinate included by the second human body position information, x (k-1) is used for representing the horizontal coordinate included by the third human body position information, y (k-1) is used for representing the vertical coordinate included by the third human body position information, vx(k-1) abscissa, v, included for characterizing a moving velocity corresponding to the third human body position informationy(k-1) for characterizing the ordinate included in the movement velocity corresponding to the third body position information, k for characterizing the current time, and (k-1) for characterizing the previous time.
According to a first formula, the state X of the current time is orderedkComprises the following steps:
Xk=[x(k) vx(k) y(k) vy(k)]T
the equation of state can be found as:
Xk=AXk-1+k-1Wk-1
the state matrix can be represented as:
Figure BDA0002606577780000102
the state noise input matrix can be expressed as:
Figure BDA0002606577780000103
process noise Wk-1Can be expressed as:
Wk-1=[x(k-1)y(k-1)]T
for the predicted current time state X obtained due to the presence of interference information during the observationkAnd obtaining the real current time state information after optimization processing, wherein a measurement equation is as follows:
let Zk=HXK+Vk
Wherein, VkTo measure noise, the measurement of the current time state is:
Zk=[zx(k) zy(k)]T=[x(k) y(k)]T
the measurement state matrix can be expressed as:
Figure BDA0002606577780000104
the covariance matrices of the process noise and the observed noise may be taken as:
Figure BDA0002606577780000105
wherein the content of the first and second substances,
Figure BDA0002606577780000106
and
Figure BDA0002606577780000107
represents the variance of the acceleration of the corresponding user in the x and y directions, respectively, namely:
Figure BDA0002606577780000111
Figure BDA0002606577780000112
and
Figure BDA0002606577780000113
represents the variance of the position measurement of the corresponding user in x and y directions, respectively, i.e.:
Figure BDA0002606577780000114
and denoising the obtained first formula result through the first formula to obtain second human body position information.
In the embodiment of the invention, the infrared detector is used for collecting the infrared image at the previous moment, the third human body position information of each user is further determined according to the infrared image, the third human body position information and the second human body position information corresponding to the third human body position information are utilized, the second human body position information is calculated through a first formula, the second human body position information is the predicted human body position information of the current moment at the previous moment, and the corresponding user human body position information is predicted specifically through a Kalman filtering algorithm.
Optionally, in step 105, solving the cost matrix by using the hungarian algorithm to obtain an optimal solution of the cost matrix, where the specific process is as follows:
s1: subtracting the minimum element in each row of the cost square matrix;
s2: subtracting the minimum element in each column of the cost square matrix;
s3: covering all 0 s in the cost square matrix with the minimum horizontal line and the minimum vertical line;
s4: judging whether the sum of the numbers of the horizontal lines and the vertical lines is equal to the sum of the numbers of the first human body position information and the second human body position information, if so, executing S5, otherwise, executing S6;
s5: determining the matrix at the moment as the optimal solution of the cost matrix, and ending the current process;
s6: determining the smallest element in the matrix that is not covered by any horizontal and vertical lines;
s7: s3 is performed after subtracting the minimum element from each row in the matrix that is not covered by a horizontal line and adding the minimum element to each column of the matrix that is covered by a vertical line.
In the embodiment of the invention, the cost matrix generated by each piece of first human body position information and each piece of second human body position information is solved through the Hungarian algorithm, and because the elements in the cost matrix are the distances between the positions represented by the corresponding first human body position information and the corresponding second human body position information, the cost matrix with the optimal solution obtained through the Hungarian algorithm is a matrix with each row and each column only comprising one element, and the human body position monitored at the current moment can be matched with the corresponding human body motion trajectory through Hungarian matching according to the matrix with the optimal solution.
Optionally, in step 107, for each human motion trajectory, updating the human motion trajectory according to the first human position information matched with the human motion trajectory, where the method specifically includes the following steps:
if the first human body position information matched with the human body motion track exists, the first human body position information matched with the human body motion track is stored to the tail end of a coordinate sequence corresponding to the human body motion track, specifically, if Num continuous multi-frame coordinates of a human body are not filled, the current coordinates are filled into a first vacant position of the continuous coordinates, if Num continuous coordinates of the human body are filled, the first continuous coordinates are deleted, other continuous coordinates are sequentially moved forward by one position, the last vacant position is filled into a new coordinate position, and the first human body position information is updated.
And if the first human body position information matched with the human body motion track does not exist, determining that the human body motion track acquired by the image acquisition is invisible, and recording the continuous invisible times of the human body motion track.
And if the continuous invisible times of the human body motion track in the periodic image acquisition process are larger than a preset time threshold value, deleting the human body motion track.
And for each piece of first human body position information, if the human body motion track matched with the human body position information does not exist, creating the human body motion track matched with the first human body position information, and storing the first human body position information into a coordinate sequence corresponding to the created human body motion track.
In the embodiment of the invention, after each first human body position is successfully matched with the corresponding human body motion track, each human body motion track is updated, the method mainly comprises the steps of updating the matched human body motion track information, updating the unmatched human body motion track information, deleting the lost human body motion track and creating a new human body motion track, and the human body motion tracks of all users in the current scene can be corrected in real time by updating the human body motion tracks.
Optionally, in step 107, for each human motion trajectory, updating the human motion trajectory according to the first human position information matched with the human motion trajectory, further including the following steps:
for each human body image in the first infrared image, acquiring the human body temperature of the corresponding user from the first infrared image, updating the acquired human body temperature into temperature information included in a human body movement track, for each piece of first human body position information, acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as a human body distance, updating the human body distance into distance information included in the human body movement track, for each piece of human body position information, calculating the movement speed of the corresponding user at the current moment by using a second formula, and updating the calculated movement speed into speed information included in the human body movement track, wherein the second formula is as follows:
Figure BDA0002606577780000121
wherein v isx(k) For characterizing the abscissa, v, included in the movement speed corresponding to the first human body position informationy(k) For characterizing the ordinate, v, included in the movement speed corresponding to the first human body position informationx(k-1) abscissa, v, included for characterizing a moving velocity corresponding to the third human body position informationy(k-1) for characterizing the ordinate included in the movement velocity corresponding to the third body position information, k for characterizing the current time, and (k-1) for characterizing the previous time.
In the embodiment of the invention, the human body temperature of the corresponding user is obtained from the human body image at the current moment, the distance between the position of the corresponding user at the current moment and the infrared detector is obtained as the human body distance, the human body temperature and the human body distance are updated into the information included in the human body motion track, meanwhile, the human body speed of the corresponding user at the current moment is calculated through the second formula, and the calculated human body speed is updated into the information included in the human body motion track, so that the information included in the human body motion track of the corresponding user at the current moment can be updated in time.
Optionally, step 108 of controlling the air supply strategy of the air conditioner according to the updated respective human body motion trajectories and controlling the air supply strategy of the air conditioner according to the updated respective human body motion trajectories specifically includes the following processes:
and aiming at each updated human body motion track, calculating the air supply weight corresponding to the human body motion track by using the following third formula:
Figure BDA0002606577780000122
wherein T isjBody temperature, v, stored for jth individual's body motion trajectoryxjThe human body speed in the x direction of the human body stored in the jth human body motion trail is shown,djand representing the human body distance stored in the jth human body motion track, determining the human body motion track with the maximum corresponding air supply weight as a target human body motion track, and controlling the air supply strategy of the air conditioner according to the target human body motion track.
Acquiring the human body coordinates and the motion speed in the human body motion track, and when the human body motion speed vxWhen the human body state information is more than 0.5, the human body state information acquired by the infrared detector at each moment has a system error, so that the human body can be judged to move leftwards or rightwards through Num continuous x coordinate information stored in the human body motion track of a corresponding user, and the method specifically comprises the following steps:
Figure BDA0002606577780000131
in the embodiment of the invention, the air supply angle of the air conditioner is controlled by judging the motion state of a corresponding user, the air supply intensity of the air conditioner is controlled by judging the distance between a human body and the air conditioner, when a plurality of users exist in the current scene, the air supply weight is calculated for each human body motion track corresponding to the corresponding user, the larger the air supply weight is, the larger the air supply weight represents that the human body needs larger air supply quantity at present, therefore, the user corresponding to the human body with the largest air supply weight is taken as the user with the highest air supply priority to supply air to the user, and meanwhile, the human body state information is continuously stored and updated in the tracking process, so that the abundant human body state information can be used for an intelligent air supply control strategy.
As shown in fig. 2 and 3, an embodiment of the present invention provides an air conditioning control device based on infrared human body tracking. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware level, as shown in fig. 2, a hardware structure diagram of an infrared human body tracking based air conditioner control device according to an embodiment of the present invention is provided, where in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 2, a device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing a packet. Taking a software implementation as an example, as shown in fig. 3, as a logical apparatus, the apparatus is formed by reading, by a CPU of a device in which the apparatus is located, corresponding computer program instructions in a non-volatile memory into a memory for execution. The air conditioner controlling means based on infrared human tracking that this embodiment provided includes: the system comprises an acquisition module 301, an identification determination module 302, an acquisition module 303, a generation module 304, a solving module 305, a matching determination module 306, an updating module 307 and a control module 308;
the acquisition module 301 is configured to acquire an infrared image once in a preset image acquisition area by using an infrared detector every time a preset image acquisition cycle passes;
an identification determining module 302, configured to identify a human body image from the first infrared image acquired by the current time acquiring module 301, and determine first human body position information of a corresponding user according to a position of each human body image in the first infrared image;
an obtaining module 303, configured to obtain at least one piece of second human body position information;
a generating module 304, configured to generate a cost matrix according to the first human body position information identified and determined by each identification determining module 302 and the second human body position information acquired by each acquiring module 303;
a solving module 305, configured to solve the cost matrix generated by the generating module 304 by using the hungarian algorithm, and obtain an optimal solution of the cost matrix;
a matching determination module 306, configured to determine a human motion trajectory matched with each piece of first human position information according to the optimal solution of the cost matrix obtained by the solving module 305;
an updating module 307, configured to update the human motion trajectory determined by each matching determining module 306 according to the first human position information matched with the human motion trajectory;
and the control module 308 is configured to control an air supply strategy of the air conditioner according to each human body motion trajectory updated by the updating module 307.
Alternatively, on the basis of the air conditioning control device based on infrared human body tracking shown in fig. 3, as shown in fig. 4, the recognition determination module 302 includes a conversion unit 3021, a determination unit 3022, and an acquisition unit 3023;
the conversion unit 3021 is configured to convert an infrared image acquired at the current time into a binary image;
a first determining unit 3022 configured to determine a connected region representing a human body in each of the binary images converted by the converting unit 3021 as one human body image;
an obtaining unit 3023, configured to determine 3022 each human body image for the first determining unit, obtain a mean abscissa value of all pixel points in the human body image and a mean ordinate value of all pixel points, and use a sequential combination of the obtained mean abscissa values and mean ordinate values as first human body position information of a user corresponding to the human body image.
Optionally, on the basis of the air conditioning control device based on infrared human body tracking shown in fig. 3, as shown in fig. 5, the obtaining module 303 includes a second determining unit 3031, a third determining unit 3032 and a calculating unit 3033;
a second determining unit 3031, configured to determine third human body position information of each user according to the second infrared image, where the third human body position information is used to represent a position of a corresponding user in the image acquisition area at the last time;
a third determining unit 3032, configured to determine a movement velocity and a movement acceleration of the corresponding user between the previous time and the current time according to the third human body position information determined by each of the second determining units 3031;
a calculating unit 3033, configured to calculate, for the third human body position information determined by each of the second determining units 3031, second human body position information corresponding to the third human body position information according to the third human body position information and the movement velocity and the movement acceleration determined by the third determining unit 3032 corresponding to the third human body position information by using the following first formula;
the first formula is:
Figure BDA0002606577780000141
wherein, x (k) is used for representing the horizontal coordinate included by the second human body position information, y (k) is used for representing the vertical coordinate included by the second human body position information, x (k-1) is used for representing the horizontal coordinate included by the third human body position information, y (k-1) is used for representing the vertical coordinate included by the third human body position information, vx(k-1) abscissa, v, included for characterizing a moving velocity corresponding to the third human body position informationy(k-1) for characterizing the ordinate included in the movement velocity corresponding to the third body position information, k for characterizing the current time, and (k-1) for characterizing the previous time.
Alternatively, on the basis of the air conditioning control device based on infrared human body tracking shown in fig. 3, as shown in fig. 6, the solving module 305 includes: the system comprises a first subtracting unit 3051, a second subtracting unit 3052, a covering unit 3053, a judging unit 3054, an optimal solution determining unit 3055, a minimum element determining unit 3056 and an adding and subtracting unit 3057;
a first subtracting unit 3051, configured to subtract a minimum element in each row of the cost square matrix;
a second subtracting unit 3052, configured to subtract the smallest element in each column of the cost square matrix;
the covering unit 3053 is configured to cover all 0 s in the cost square matrix subtracted by the first and second subtracting units 3051 and 3052 with the fewest horizontal lines and the fewest vertical lines;
a judging unit 3054 for judging whether the sum of the numbers of horizontal lines and vertical lines of the covering unit 3053 is equal to the sum of the numbers of the first human body position information and the second human body position information, if yes, steering to an optimal solution determining unit 3055, otherwise, steering to a minimum element determining unit 3056;
the optimal solution determining unit 3055 is configured to determine that the matrix determined by the determining unit 3054 is an optimal solution of the cost matrix, and stop operation of the solving module 305;
the minimum element determining unit 3056, configured to determine, when the determining unit 3054 determines that the matrix is not the optimal solution of the cost matrix, a minimum element in the matrix that is not covered by any horizontal line and vertical line;
an add/subtract unit 3057 for subtracting the minimum element determined by the minimum element determination unit 3056 from each row not covered by the horizontal line in the matrix and, after adding the minimum element to each column covered by the vertical line in the matrix, turning to the covering unit 3053.
Alternatively, on the basis of the infrared human body tracking based air conditioning control apparatus shown in fig. 3, as shown in fig. 7, the updating module 307 includes a matched unit 3071, an unmatched unit 3072, a deletion unit 3073, and a creation unit 3074;
the matched unit 3071, configured to, for each human body motion trajectory, store, to the end of the coordinate sequence corresponding to the human body motion trajectory, first human body position information that matches the human body motion trajectory;
the unmatched unit 3072 is used for determining that the human body motion track acquired by the image acquisition is invisible for each human body motion track if first human body position information matched with the human body motion track does not exist;
the deleting unit 3073 is used for deleting the human body motion track when the continuous invisible times of the human body motion track in the unmatched unit are larger than a preset time threshold value in the periodic image acquisition process aiming at each human body motion track;
a creating unit 3074 for creating a human body movement trajectory matching the first human body position information if there is no human body movement trajectory matching the human body position information for each first human body position information, and storing the first human body position information to a coordinate sequence corresponding to the created human body movement trajectory.
Optionally, on the basis of the air conditioning control device based on infrared human body tracking shown in fig. 3, as shown in fig. 8, the updating module 307 further includes a human body temperature updating unit 3075, a human body distance updating unit 3076 and a human body speed updating unit 3077;
the human body temperature updating unit 3075 is configured to, for each human body image in the first infrared image, obtain a human body temperature of the corresponding user from the first infrared image, and update the obtained human body temperature to temperature information included in the human body motion trajectory;
the human body distance updating unit 3076 is used for acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as the human body distance according to each piece of first human body position information, and updating the human body distance to the distance information included in the human body motion track;
the human body velocity updating unit 3077 is configured to calculate, for each piece of personal location information, a motion velocity of the corresponding user at the current time according to a second formula, and update the calculated motion velocity into velocity information included in the human body motion trajectory, where the second formula includes the following:
Figure BDA0002606577780000161
wherein v isx(k) For characterizing the abscissa, v, included in the movement speed corresponding to the first human body position informationy(k) For characterizing the ordinate, v, included in the movement speed corresponding to the first human body position informationx(k-1) abscissa, v, included for characterizing a moving velocity corresponding to the third human body position informationy(k-1) for characterizing the ordinate included in the movement velocity corresponding to the third body position information, k for characterizing the current time, and (k-1) for characterizing the previous time.
Alternatively, on the basis of the air conditioning control device based on infrared human body tracking shown in fig. 3, as shown in fig. 9, the control module 308 includes: an air supply weight calculation unit 3081 and an air conditioner control unit 3082;
an air supply weight calculation unit 3081, configured to calculate, for each updated human body motion trajectory, an air supply weight corresponding to the human body motion trajectory by using a third formula, where the third formula includes:
Figure BDA0002606577780000162
wherein T isjBody temperature, v, stored for jth individual's body motion trajectoryxjRepresenting the body velocity in the x-direction of the body stored in the jth body motion trajectory, djAnd representing the human body distance stored in the jth human body motion track, determining the human body motion track with the maximum corresponding air supply weight as a target human body motion track, and controlling the air supply strategy of the air conditioner according to the target human body motion track.
And an air conditioner control unit 3082, configured to determine, as a target human body motion trajectory, one human body motion trajectory with the largest air supply weight calculated by the corresponding air supply weight calculation unit 3081, and control an air supply strategy of the air conditioner according to the target human body motion trajectory.
It should be noted that, because the contents of information interaction, execution process, and the like between the units in the apparatus are based on the same concept as the method embodiment of the present invention, specific contents may refer to the description in the method embodiment of the present invention, and are not described herein again.
The method for controlling an air conditioner based on infrared human body tracking according to an embodiment of the present invention is further described in detail with reference to the following specific examples, as shown in fig. 10, the method may include the following steps:
step 1001: and acquiring the image of the preset image acquisition area once by using the infrared detector every time a preset image acquisition period passes to obtain an infrared image.
In the embodiment of the invention, image acquisition is carried out once in each preset image acquisition period, the time interval of each image acquisition is ensured to be equal, the time of each image acquisition period can be set according to actual requirements, meanwhile, the infrared detector is arranged at a position which has a certain distance with the ground, the infrared detector is an array infrared thermopile detector with a large field of view, the optical axis of the infrared detector and the horizontal direction form an acute angle downward for detecting users in a scene, and more human body information in the scene can be acquired.
For example, the infrared detector is installed at a position where the height of the current scene from the ground is 2 meters, so that the field range of the infrared detector can cover all users in the current scene, and the image acquisition period is set to 1 second, that is, the infrared detector performs infrared image acquisition every second.
Step 1002: and identifying human body images from the first infrared images acquired at the current moment, and determining first human body position information of the corresponding user according to the position of each human body image in the first infrared image.
In the embodiment of the invention, the infrared image acquired by the infrared detector at the current moment consists of at least one pixel point, the binary image of the corresponding user is obtained through a detection algorithm, the statistical analysis is carried out on the binary image, the human body position information of the corresponding user at the current moment can be determined according to the binary image information, the human body position in the current scene can be detected in real time, the air supply direction is changed according to the human body position, and the use experience of the air conditioner of the user can be improved.
For example, after statistical analysis is performed on the binary image of the user corresponding to the current time, temperature information, area information, position information, continuous multi-frame coordinate information, distance information, an air supply weight coefficient, a movement speed, whether the user is still or not, and information on the number of people in the scene can be obtained, and the air supply strategy of the air conditioner can be adjusted in real time for the user in the current scene according to the information.
Step 1003: at least one second human body position information is acquired.
In the embodiment of the invention, according to the infrared image acquired by the infrared detector at the previous moment, the infrared image is processed to obtain the human body position information, the human body position is predicted through a Kalman filtering algorithm according to the human body position information to obtain the predicted target position at the current moment, and the predicted human body position information is subjected to data filtering to obtain more real human body position information, namely, the second human body position information is the predictive result of the position of the corresponding user in the image acquisition area at the current moment.
For example, the coordinate of the location where the user was located at the previous time is [15, 18], and the state matrix is:
Figure BDA0002606577780000171
the measurement state matrix is:
Figure BDA0002606577780000172
then the current state matrix can be obtained as:
X=[17.9754 22.9553]T
step 1004: and generating a cost matrix according to the first human body position information and the second human body position information.
In the embodiment of the invention, a cost matrix is generated according to the first human body position information at the current moment and the second human body position information at the current moment predicted at the last moment, the line number of the cost matrix is the number of the first human body position information, the column number of the cost matrix is the number of the second human body position information, and the element in the cost matrix is the distance between the positions represented by the corresponding first human body position information and the corresponding second human body position information, so that the current-moment human body position of the corresponding user and the current-moment human body position predicted at the last moment can be reflected in real time.
For example, there are 3 users in the current scene, the first human body position coordinate of each user at the current time is [2,5], [1,4] and [3,6], and the second human body position coordinate of the current time predicted at the previous time is [1,5], [2,4] and [3,6], respectively, then the cost matrix generated according to the first human body position information and the second human body position information is:
Figure BDA0002606577780000181
step 1005: solving the cost matrix by using a Hungarian algorithm to obtain an optimal solution of the cost matrix, and determining the human motion trajectory matched with each piece of first human body position information according to the optimal solution of the cost matrix.
In the embodiment of the invention, the Hungarian algorithm is utilized to match the human body position acquired at the current moment with the existing human body motion trail, the matching result is distributed to different human body motion trails, the successful matching of each human body position and the corresponding human body motion trail is ensured, the real human body motion trail of the corresponding user in the current scene is identified, the air supply of the air conditioner is controlled according to the actual position information of the current scene, and the accuracy of the air conditioner is ensured.
Specifically, S1: subtracting the smallest element in each row of the cost matrix, S2: subtracting the smallest element in each column of the cost matrix, S3: covering all 0S in the cost square matrix with the least horizontal lines and the least vertical lines, S4: determining whether the sum of the numbers of horizontal lines and vertical lines is equal to the sum of the numbers of first human body position information and second human body position information, if so, performing S5, otherwise performing S6, S5: determining the matrix at this time as the optimal solution of the cost matrix, and ending the current process, S6: determining the smallest element in the matrix that is not covered by any horizontal and vertical lines, S7: s3 is performed after subtracting the minimum element from each row in the matrix that is not covered by a horizontal line and adding the minimum element to each column of the matrix that is covered by a vertical line. After the optimal solution of the cost matrix is obtained in the steps, matching each person position information with the human motion track according to the optimal solution result of the cost matrix.
For example, solving the cost matrix to obtain the optimal solution of the cost matrix is as follows:
Figure BDA0002606577780000182
and matching each first human body position with the corresponding human body motion track according to the optimal solution result.
Step 1006: and aiming at each human body motion track, updating the human body motion track according to the first human body position information matched with the human body motion track.
In the embodiment of the invention, each human body motion trail is updated according to the Hungarian matching result, the human body motion trail is continuously matched with the human body motion trail according to the target information obtained by statistics in the human body motion trail tracking process, finally, the human body motion trail information is updated, and then the air supply quantity, the air supply angle and the air supply temperature of the air conditioner are automatically controlled by using the human body trail motion information, so that the accuracy of air conditioner control on corresponding users according to the current scene is improved.
Specifically, for each human motion trajectory, the following is performed: if the first human body position information matched with the human body motion track exists, the first human body position information matched with the human body motion track is stored at the tail end of the coordinate sequence corresponding to the human body motion track, if the first human body position information matched with the human body motion track does not exist, determining that the human body motion track acquired by the image acquisition is invisible, if the number of times that the human body motion track is continuously invisible in the periodic image acquisition process is larger than a preset number threshold, deleting the human body motion track, and aiming at each piece of first human body position information, if there is no human body movement trajectory matching the human body position information, a human body movement trajectory matching the first human body position information is created, and storing the first human body position information into a coordinate sequence corresponding to the created human body motion track.
For example, for the first human body position information matched with the human body motion track, the number of times of visibility of the human body motion track is added with 1, namely age1=age1+1 if the Num consecutive multiframe coordinates of the human body are not filled, e.g., [ (x)1,y1)......(x5,y5)(null1)(null2)(null3)]Then the current coordinate (x)t,yt) Filling in the first empty spaces of continuous coordinates, e.g., [ (x)1,y1)......(x5,y5)(xt,yt)(null2)(null3)]If Num consecutive coordinates of the body have been filled, e.g., [ (x)1,y1)(x2,y2)......(xn,yn)]Then delete the continuous sittingThe first, other consecutive coordinates of the target are sequentially shifted forward by one bit, and the last empty bit is filled into the new coordinate position, e.g., [ (x)2,y2)......(xn,yn)(xt,yt)](ii) a If the detection result is not matched with the human body movement track, the number of times that the human body movement track is visible is not matched0=age0+ 1; if the number of times of continuous invisibility of the human motion track in the periodic image acquisition process is larger than a preset number threshold, if the number threshold is set to be 8, and if the number of times of continuous invisibility is set to be 9, deleting the human motion track; and if a certain detection result is not matched with the track, creating a new human motion track by taking the position of the detection result as a starting point.
Step 1007: and updating the temperature information, the distance information and the speed information included in the human body movement track according to the first human body position information matched with the human body movement track aiming at each human body movement track.
In the embodiment of the invention, aiming at each human body image and the first human body position information, the human body temperature of the corresponding user is obtained from the human body image, the human body temperature of the corresponding user is obtained from the first human body position information, the human body distance is obtained from the distance between the current position and the last position, and the human body information is updated to the human body motion track matched with the first human body position information, so that the accuracy of the human body information included in the current human body motion track is ensured, and the accuracy of air conditioning control is further improved.
Specifically, for each human body image in the first infrared image, the human body temperature of the corresponding user is obtained from the first infrared image, and the obtained human body temperature is updated into the temperature information included in the human body movement track, for each piece of first human body position information, the distance between the position of the corresponding user at the current time and the infrared detector is obtained as the human body distance, and the human body distance is updated into the distance information included in the human body movement track, for each piece of human body position information, the movement speed of the corresponding user at the current time is calculated by the following second formula, and the calculated movement speed is updated into the speed information included in the human body movement track, and the second formula includes the following:
Figure BDA0002606577780000191
wherein v isx(k) For characterizing the abscissa, v, included in the movement speed corresponding to the first human body position informationy(k) For characterizing the ordinate, v, included in the movement speed corresponding to the first human body position informationx(k-1) abscissa, v, included for characterizing a moving velocity corresponding to the third human body position informationy(k-1) for characterizing the ordinate included in the movement velocity corresponding to the third body position information, k for characterizing the current time, and (k-1) for characterizing the previous time.
Step 1008: and controlling the air supply strategy of the air conditioner according to the updated motion tracks of the human bodies.
In the embodiment of the invention, when a plurality of users appear in a scene, the air supply weight needs to be calculated for each human body motion track, and the corresponding user with the largest human body air supply weight is taken as the user with the highest air supply priority to supply air to the user according to the air supply weight value.
Specifically, for each updated human body motion trajectory, the following third formula is used to calculate the air supply weight corresponding to the human body motion trajectory, and the third formula includes the following:
Figure BDA0002606577780000201
wherein T isjBody temperature, v, stored for jth individual's body motion trajectoryxjRepresenting the body velocity in the x-direction of the body stored in the jth body motion trajectory, djThe human body distance stored in the jth human body motion track is shown and correspondingly sentAnd determining the human body motion track with the largest wind weight as a target human body motion track, and controlling an air supply strategy of the air conditioner according to the target human body motion track.
Step 1009: and judging whether a user exists in the current scene or not, and if the user does not exist in the preset time length in the current scene, closing the air conditioner.
In the embodiment of the invention, whether the user exists in the current scene is judged through the real-time detection of the infrared detector, and if the user does not exist in the current scene within the preset time, the air conditioner is closed, so that the air conditioner can be closed in time, and resources are saved.
Specifically, the preset time period is 20 minutes, and if it is detected that there is no user for 20 minutes continuously in the current scene, the air conditioner may be turned off by controlling an air conditioner switch.
In summary, the air conditioner control method and device based on infrared human body tracking provided by the embodiments of the present invention at least have the following beneficial effects:
1. in the embodiment of the invention, firstly, an infrared detector is utilized to acquire an infrared image for a preset image acquisition area once, a human body image is identified from the infrared image acquired at the current moment, first human body position information of a corresponding user is determined according to the position of each human body image in the infrared image, then, a second human body position of the corresponding user at the current moment predicted at the previous moment is acquired, then, a cost matrix is generated according to each first human body position information and each second human body position information, the cost matrix is solved by utilizing a Hungarian algorithm to obtain the optimal solution of the cost matrix, a human body motion track matched with each first human body position information is determined according to the optimal solution of the cost matrix, and according to each human body motion track, first human body position information matched with the human body motion track is obtained, and updating the human body motion trail, and finally controlling an air supply strategy of the air conditioner according to each updated human body motion trail. According to the scheme, the human body target is obtained through infrared image detection, statistical analysis is carried out to extract relevant information, the feasibility of maintaining human body information is guaranteed by tracking and establishing the human body motion track, the air supply strategy of the air conditioner is adjusted in real time according to the corresponding human body motion track, and the accuracy of air conditioner control can be improved.
2. In the embodiment of the invention, image acquisition is carried out once in each preset image acquisition period, the time interval of each image acquisition is ensured to be equal, the time of each image acquisition period can be set according to actual requirements, meanwhile, the infrared detector is arranged at a position which has a certain distance with the ground, the infrared detector is an array infrared thermopile detector with a large field of view, the optical axis of the infrared detector and the horizontal direction form an acute angle downward for detecting users in a scene, and more human body information in the scene can be acquired.
3. In the embodiment of the invention, the infrared image acquired by the infrared detector at the current moment consists of at least one pixel point, the binary image of the corresponding user is obtained through a detection algorithm, the statistical analysis is carried out on the binary image, the human body position information of the corresponding user at the current moment can be determined according to the binary image information, the human body position in the current scene can be detected in real time, the air supply direction is changed according to the human body position, and the use experience of the air conditioner of the user can be improved.
4. In the embodiment of the invention, according to the infrared image acquired by the infrared detector at the previous moment, the infrared image is processed to obtain the human body position information, the human body position is predicted through a Kalman filtering algorithm according to the human body position information to obtain the predicted target position at the current moment, and the predicted human body position information is subjected to data filtering to obtain more real human body position information, namely, the second human body position information is the predictive result of the position of the corresponding user in the image acquisition area at the current moment.
5. In the embodiment of the invention, the Hungarian algorithm is utilized to match the human body position acquired at the current moment with the existing human body motion trail, the matching result is distributed to different human body motion trails, the successful matching of each human body position and the corresponding human body motion trail is ensured, the real human body motion trail of the corresponding user in the current scene is identified, the air supply of the air conditioner is controlled according to the actual position information of the current scene, and the accuracy of the air conditioner is ensured.
6. In the embodiment of the invention, each human body motion trail is updated according to the Hungarian matching result, the human body motion trail is continuously matched with the human body motion trail according to the target information obtained by statistics in the human body motion trail tracking process, finally, the human body motion trail information is updated, and then the air supply quantity, the air supply angle and the air supply temperature of the air conditioner are automatically controlled by using the human body trail motion information, so that the accuracy of air conditioner control on corresponding users according to the current scene is improved.
7. In the embodiment of the invention, aiming at each human body image and the first human body position information, the human body temperature of the corresponding user is obtained from the human body image, the human body temperature of the corresponding user is obtained from the first human body position information, the human body distance is obtained from the distance between the current position and the last position, and the human body information is updated to the human body motion track matched with the first human body position information, so that the accuracy of the human body information included in the current human body motion track is ensured, and the accuracy of air conditioning control is further improved.
8. In the embodiment of the invention, when a plurality of users appear in a scene, the air supply weight needs to be calculated for each human body motion track, and the corresponding user with the largest human body air supply weight is taken as the user with the highest air supply priority to supply air to the user according to the air supply weight value.
9. In the embodiment of the invention, whether the user exists in the current scene is judged through the real-time detection of the infrared detector, and if the user does not exist in the current scene within the preset time, the air conditioner is closed, so that the air conditioner can be closed in time, and resources are saved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other similar elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it is to be noted that: the above description is only a preferred embodiment of the present invention, and is only used to illustrate the technical solutions of the present invention, and not to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (10)

1. An air conditioner control method based on infrared human body tracking is characterized by comprising the following steps:
every time a preset image acquisition period passes, carrying out image acquisition on a preset image acquisition area by using an infrared detector to obtain an infrared image;
identifying human body images from first infrared images acquired at the current moment, and respectively determining first human body position information of corresponding users according to the positions of the human body images in the first infrared images, wherein different human body images correspond to different users, and the first human body position information is used for representing the positions of the corresponding users in the image acquisition area at the current moment;
acquiring at least one piece of second human body position information, wherein the second human body position information is acquired according to a second infrared image acquired at the last moment, and the second human body position information is used for representing a predictive result of the position of a corresponding user in the image acquisition area at the current moment;
generating a cost matrix according to each piece of first human body position information and each piece of second human body position information, wherein the number of rows and the number of columns of the cost matrix are respectively equal to the number of the first human body position information and the number of the second human body position information, and elements in the cost matrix are distances between positions represented by the corresponding first human body position information and the second human body position information;
solving the cost matrix by using a Hungarian algorithm to obtain an optimal solution of the cost matrix;
determining a human body motion track matched with each piece of first human body position information according to the optimal solution of the cost matrix, wherein the human body motion track is used for representing the motion track of a corresponding user in the image acquisition area;
aiming at each human body motion track, updating the human body motion track according to the first human body position information matched with the human body motion track;
and controlling an air supply strategy of the air conditioner according to each updated human body motion track, wherein the air supply strategy comprises air supply quantity, air supply angle and air supply temperature.
2. The method according to claim 1, wherein the identifying human body images from the infrared images acquired at the current moment and determining the first human body position information of the corresponding user according to the position of each human body image in the infrared images respectively comprises:
converting an infrared image acquired at the current moment into a binary image;
determining a connected region of each binary image for representing a human body as one human body image;
and aiming at each human body image, acquiring the mean value of the horizontal coordinates of all pixel points in the human body image and the mean value of the vertical coordinates of all pixel points, and sequentially combining the acquired mean values of the horizontal coordinates and the mean values of the vertical coordinates to be used as the first human body position information of the user corresponding to the human body image.
3. The method of claim 1, wherein the obtaining at least one second body position information comprises:
determining third human body position information of each user according to the second infrared image, wherein the third human body position information is used for representing the position of the corresponding user in the image acquisition area at the last moment;
respectively determining the movement speed and the movement acceleration of the corresponding user between the last moment and the current moment according to each piece of third human body position information;
for each piece of third human body position information, calculating second human body position information corresponding to the third human body position information by a first formula according to the third human body position information and the movement speed and the movement acceleration corresponding to the third human body position information;
the first formula is:
Figure FDA0002606577770000021
wherein x (k) is used for representing the abscissa included in the second body position information, y (k) is used for representing the ordinate included in the second body position information, x (k-1) is used for representing the abscissa included in the third body position information, y (k-1) is used for representing the ordinate included in the third body position information, and v (k-1) is used for representing the abscissa included in the third body position informationx(k-1) the step of characterizing the motion speed corresponding to the third body position information includesThe abscissa of (a), the vy(k-1) for characterizing a ordinate included in the movement velocity corresponding to the third human body position information, the k being for characterizing a current time, and the (k-1) being for characterizing a previous time.
4. The method as claimed in claim 1, wherein the solving the cost matrix by using the hungarian algorithm to obtain the optimal solution of the cost matrix comprises:
s1: subtracting the minimum element in each line of the cost square matrix;
s2: subtracting the smallest element in each column of the cost square matrix;
s3: covering all 0 s in the cost square matrix with the fewest horizontal lines and the fewest vertical lines;
s4: determining whether the sum of the numbers of horizontal lines and vertical lines is equal to the sum of the numbers of the first human body position information and the second human body position information, if so, performing S5, otherwise, performing S6;
s5: determining the matrix at the moment as the optimal solution of the cost matrix, and ending the current process;
s6: determining the smallest element in the matrix that is not covered by any horizontal and vertical lines;
s7: subtracting the minimum element from each row in the matrix not covered by the horizontal lines and performing S3 after adding the minimum element to each column of the matrix covered by the vertical lines;
and/or the presence of a gas in the gas,
the updating of the human motion trajectory according to the first human position information matched with the human motion trajectory for each human motion trajectory includes:
for each human motion track, executing:
if the first human body position information matched with the human body motion track exists, storing the first human body position information matched with the human body motion track to the tail end of a coordinate sequence corresponding to the human body motion track;
if the first human body position information matched with the human body motion track does not exist, determining that the human body motion track acquired by the image is invisible;
if the number of times that the human motion track is continuously invisible in the periodic image acquisition process is larger than a preset number threshold, deleting the human motion track;
and for each piece of first human body position information, if the human body motion track matched with the human body position information does not exist, creating the human body motion track matched with the first human body position information, and storing the first human body position information into a coordinate sequence corresponding to the created human body motion track.
5. The method according to any one of claims 1 to 4,
the infrared detector is an array type infrared thermopile detector with a large view field, and an acute angle is formed between the optical axis of the infrared detector and the horizontal direction, wherein the infrared detector is used for detecting a user in a current scene and acquiring human body information in the scene, and the human body information comprises the distance between the human body of the user at the current moment and the infrared detector;
and/or the presence of a gas in the gas,
the updating of the human motion trajectory according to the first human position information matched with the human motion trajectory for each human motion trajectory includes:
for each human body image in the first infrared image, acquiring the human body temperature of a corresponding user from the first infrared image, and updating the acquired human body temperature into temperature information included in the human body motion track;
for each piece of first human body position information, acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as a human body distance, and updating the human body distance into the distance information included in the human body motion track;
for each piece of human body position information, calculating the movement speed of the corresponding user at the current moment through a second formula, and updating the calculated movement speed into the speed information included in the human body movement track;
the second formula includes:
Figure FDA0002606577770000041
wherein, v isx(k) An abscissa for characterizing the motion speed corresponding to the first human body position information, the vy(k) A vertical coordinate included for characterizing the movement velocity corresponding to the first human body position information, the vx(k-1) the abscissa used to characterize the motion velocity corresponding to the third human body position information, the vy(k-1) a ordinate included in the movement velocity corresponding to the third human body position information, the k being used to represent a current time, and the (k-1) being used to represent a previous time;
the air supply strategy for controlling the air conditioner according to the updated motion trail of the human body comprises the following steps:
aiming at each updated human body motion track, calculating the air supply weight corresponding to the human body motion track by using the following third formula;
the third formula is:
Figure FDA0002606577770000051
wherein T isjThe body temperature, v, stored for the jth of the body motion trajectoryxjRepresenting said body velocity in x-direction of a body stored for the jth said body motion trajectory, djRepresenting the human body distance stored in the jth human body motion track;
and determining the human body motion track with the largest corresponding air supply weight as a target human body motion track, and controlling an air supply strategy of the air conditioner according to the target human body motion track.
6. Air conditioner controlling means based on infrared human tracking, its characterized in that includes: the device comprises an acquisition module, an identification determination module, an acquisition module, a generation module, a solving module, a matching determination module, an updating module and a control module;
the acquisition module is used for acquiring an image once in a preset image acquisition area by using an infrared detector every time a preset image acquisition period passes to obtain an infrared image;
the identification determination module is configured to identify a human body image from the first infrared image acquired by the acquisition module at the current time, and determine first human body position information of a corresponding user according to a position of each human body image in the first infrared image, where different human body images correspond to different users, and the first human body position information is used to represent positions of the corresponding users in the image acquisition area at the current time;
the acquisition module is used for acquiring at least one piece of second human body position information, wherein the second human body position information is acquired according to a second infrared image acquired from the acquisition module at the last moment, and the second human body position information is used for representing a predictive result of the position of the corresponding user in the image acquisition area at the current moment;
the generating module is configured to generate a cost matrix according to first human body position information identified and determined by each identification determining module and second human body position information acquired by each acquiring module, where the number of rows and the number of columns of the cost matrix are respectively equal to the number of the first human body position information and the number of the second human body position information, and an element in the cost matrix is a distance between positions represented by the corresponding first human body position information and the corresponding second human body position information;
the solving module is used for solving the cost matrix generated by the generating module by using a Hungarian algorithm to obtain an optimal solution of the cost matrix;
the matching determination module is configured to determine a human body motion trajectory matched with each piece of first human body position information according to the optimal solution of the cost matrix obtained by the solving module, where the human body motion trajectory is used to represent a motion trajectory of a corresponding user in the image acquisition area;
the updating module is used for updating the human body motion track determined by each matching determination module according to the first human body position information matched with the human body motion track;
and the control module is used for controlling an air supply strategy of the air conditioner according to each human body motion track updated by the updating module, wherein the air supply strategy comprises air supply amount, air supply angle and air supply temperature.
7. The apparatus of claim 6, wherein the identification determination module comprises: the device comprises a conversion unit, a determination unit and an acquisition unit;
the conversion unit is used for converting the infrared image acquired at the current moment into a binary image;
the first determining unit is configured to determine a connected region, which is used for representing a human body, in each of the binary images converted by the converting unit as one human body image;
the acquiring unit is configured to acquire, for each human body image determined by the first determining unit, a mean value of abscissa of all pixel points and a mean value of ordinate of all pixel points in the human body image, and use a sequential combination of the acquired mean values of the abscissa and the mean values of the ordinate as the first human body position information of the user corresponding to the human body image.
8. The apparatus of claim 6, wherein the obtaining module comprises: a second determining unit, a third determining unit and a calculating unit;
the second determining unit is configured to determine third human body position information of each user according to the second infrared image, where the third human body position information is used to represent a position of a corresponding user in the image acquisition area at a previous time;
the third determining unit is configured to determine a movement velocity and a movement acceleration of the corresponding user between the previous time and the current time according to the third human body position information determined by each of the second determining units;
the calculating unit is configured to calculate, for each piece of third human body position information determined by the second determining unit, the second human body position information corresponding to the third human body position information according to the third human body position information and the movement velocity and the movement acceleration determined by the third determining unit corresponding to the third human body position information by using a first formula;
the first formula is:
Figure FDA0002606577770000071
wherein x (k) is used for representing the abscissa included in the second body position information, y (k) is used for representing the ordinate included in the second body position information, x (k-1) is used for representing the abscissa included in the third body position information, y (k-1) is used for representing the ordinate included in the third body position information, and v (k-1) is used for representing the abscissa included in the third body position informationx(k-1) the abscissa used to characterize the motion velocity corresponding to the third human body position information, the vy(k-1) for characterizing a ordinate included in the movement velocity corresponding to the third human body position information, the k being for characterizing a current time, and the (k-1) being for characterizing a previous time.
9. The apparatus of claim 6, wherein the solving module comprises: the device comprises a first subtracting unit, a second subtracting unit, a covering unit, a judging unit, an optimal solution determining unit, a minimum element determining unit and an adding and subtracting unit;
the first subtracting unit is used for subtracting the minimum element in each line of the cost square matrix;
the second subtracting unit is used for subtracting the smallest element in each column of the cost square matrix;
the covering unit is used for covering all 0 s in the cost square matrix after the subtraction of the first subtracting unit and the second subtracting unit with the least horizontal lines and the least vertical lines;
the judging unit is used for judging whether the sum of the number of the horizontal lines and the number of the vertical lines of the covering unit is equal to the sum of the number of the first human body position information and the number of the second human body position information, if so, the covering unit turns to an optimal solution determining unit, and if not, the covering unit turns to a minimum element determining unit;
the optimal solution determining unit is used for determining that the matrix judged by the judging unit is the optimal solution of the cost matrix and stopping the operation work of the solving module;
the minimum element determining unit is configured to determine a minimum element in the matrix that is not covered by any horizontal line and vertical line when it is determined that the matrix determined by the determining unit is not the optimal solution of the cost matrix;
the addition and subtraction unit is used for subtracting the minimum element determined by the minimum element determining unit from each row which is not covered by the horizontal line in the matrix, and turning to the covering unit after adding the minimum element to each column which is covered by the vertical line in the matrix;
and/or the presence of a gas in the gas,
the update module includes: matched unit, unmatched unit, deleting unit and creating unit;
the matched unit is used for storing the first human body position information matched with the human body motion track to the tail end of the coordinate sequence corresponding to the human body motion track for the first human body position information matched with the human body motion track existing in each human body motion track;
the unmatched unit is used for determining that the human body motion track acquired by the image acquisition is invisible for the situation that the first human body position information matched with the human body motion track does not exist in the human body motion track;
the deleting unit is used for deleting the human body motion track when the continuous invisible times of the human body motion track in the unmatched unit are larger than a preset time threshold in the periodic image acquisition process aiming at each human body motion track;
the creating unit is configured to, for each piece of the first human body position information, create a human body movement trajectory matched with the first human body position information if the human body movement trajectory matched with the human body position information does not exist, and store the first human body position information in a coordinate sequence corresponding to the created human body movement trajectory.
10. The apparatus according to any one of claims 6 to 9,
the update module includes: a human body temperature updating unit, a human body distance updating unit and a human body speed updating unit;
the human body temperature updating unit is used for acquiring the human body temperature of a corresponding user from the first infrared image aiming at each human body image in the first infrared image, and updating the acquired human body temperature into the temperature information included in the human body motion trail;
the human body distance updating unit is used for acquiring the distance between the position of the corresponding user at the current moment and the infrared detector as the human body distance according to each piece of first human body position information, and updating the human body distance to the distance information included in the human body motion track;
the human body speed updating unit is used for calculating the movement speed of the corresponding user at the current moment according to the following second formula aiming at each piece of human body position information and updating the calculated movement speed into the speed information included in the human body movement track;
the second formula includes:
Figure FDA0002606577770000091
wherein, v isx(k) An abscissa for characterizing the motion speed corresponding to the first human body position information, the vy(k) A vertical coordinate included for characterizing the movement velocity corresponding to the first human body position information, the vx(k-1) the abscissa used to characterize the motion velocity corresponding to the third human body position information, the vy(k-1) a ordinate included in the movement velocity corresponding to the third human body position information, the k being used to represent a current time, and the (k-1) being used to represent a previous time;
the control module includes: an air supply weight calculation unit and an air conditioner control unit;
the air supply weight calculation unit is used for calculating the air supply weight corresponding to each updated human body motion track by using the following third formula;
the third formula is:
Figure FDA0002606577770000092
wherein T isjThe human body temperature, v, updated by the human body temperature updating unit stored for the jth human body motion trajectoryxjThe human body speed updated by the human body speed updating unit in the x direction of the human body stored in the jth human body motion track is represented, djThe human body distance updated by the human body distance updating unit and stored in the jth human body motion track is represented;
and the air conditioner control unit is used for determining the human body motion track with the maximum air supply weight calculated by the air supply weight calculation unit as a target human body motion track and controlling the air supply strategy of the air conditioner according to the target human body motion track.
CN202010740565.9A 2020-07-28 2020-07-28 Air conditioner control method and device based on infrared human body tracking Active CN112032987B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010740565.9A CN112032987B (en) 2020-07-28 2020-07-28 Air conditioner control method and device based on infrared human body tracking

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010740565.9A CN112032987B (en) 2020-07-28 2020-07-28 Air conditioner control method and device based on infrared human body tracking

Publications (2)

Publication Number Publication Date
CN112032987A true CN112032987A (en) 2020-12-04
CN112032987B CN112032987B (en) 2022-04-08

Family

ID=73583421

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010740565.9A Active CN112032987B (en) 2020-07-28 2020-07-28 Air conditioner control method and device based on infrared human body tracking

Country Status (1)

Country Link
CN (1) CN112032987B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112984718A (en) * 2020-12-18 2021-06-18 四川虹美智能科技有限公司 Intelligent air conditioner control method, device and system based on human body tracking
CN113611012A (en) * 2021-06-16 2021-11-05 南京邮电大学 Non-invasive people number detection method, device and system based on infrared array sensor
CN114576822A (en) * 2022-03-10 2022-06-03 深圳美智华科智能科技研究中心有限公司 Air conditioner control method based on millimeter wave radar, air conditioner and storage medium
WO2022217998A1 (en) * 2021-04-12 2022-10-20 青岛海尔空调器有限总公司 Method and apparatus for air supply control of air conditioner, and air conditioner

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06117836A (en) * 1992-08-21 1994-04-28 Matsushita Electric Ind Co Ltd Image processing apparatus, controller of air conditioner, and applied equipment using the apparatus
JP2000172827A (en) * 1998-12-03 2000-06-23 Sharp Corp Human body detector and air conditioner using it
CN101807245A (en) * 2010-03-02 2010-08-18 天津大学 Artificial neural network-based multi-source gait feature extraction and identification method
JP2010276324A (en) * 2009-06-01 2010-12-09 Mitsubishi Electric Corp Air conditioner
CN103673089A (en) * 2012-09-03 2014-03-26 日立空调·家用电器株式会社 Air-conditioning machine
CN105526682A (en) * 2016-02-04 2016-04-27 四川长虹电器股份有限公司 Air conditioning system capable of intelligently recognizing number of persons and image processing method
CN105526671A (en) * 2015-12-11 2016-04-27 四川长虹电器股份有限公司 User identification method and air conditioning equipment
US20160320085A1 (en) * 2014-05-27 2016-11-03 Panasonic Intellectual Property Corporation Of America Sensor control method executed by air-conditioning apparatus
CN108253596A (en) * 2018-01-31 2018-07-06 广东美的制冷设备有限公司 Air-conditioning method, air conditioner and computer readable storage medium
CN108826594A (en) * 2018-05-11 2018-11-16 奥克斯空调股份有限公司 Air-conditioning draught fan control method and air conditioner
CN110517292A (en) * 2019-08-29 2019-11-29 京东方科技集团股份有限公司 Method for tracking target, device, system and computer readable storage medium
CN110925970A (en) * 2019-11-04 2020-03-27 佛山市云米电器科技有限公司 Target character wind power intelligent air-out system under multi-person scene

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06117836A (en) * 1992-08-21 1994-04-28 Matsushita Electric Ind Co Ltd Image processing apparatus, controller of air conditioner, and applied equipment using the apparatus
JP2000172827A (en) * 1998-12-03 2000-06-23 Sharp Corp Human body detector and air conditioner using it
JP2010276324A (en) * 2009-06-01 2010-12-09 Mitsubishi Electric Corp Air conditioner
CN101807245A (en) * 2010-03-02 2010-08-18 天津大学 Artificial neural network-based multi-source gait feature extraction and identification method
CN103673089A (en) * 2012-09-03 2014-03-26 日立空调·家用电器株式会社 Air-conditioning machine
US20160320085A1 (en) * 2014-05-27 2016-11-03 Panasonic Intellectual Property Corporation Of America Sensor control method executed by air-conditioning apparatus
CN105526671A (en) * 2015-12-11 2016-04-27 四川长虹电器股份有限公司 User identification method and air conditioning equipment
CN105526682A (en) * 2016-02-04 2016-04-27 四川长虹电器股份有限公司 Air conditioning system capable of intelligently recognizing number of persons and image processing method
CN108253596A (en) * 2018-01-31 2018-07-06 广东美的制冷设备有限公司 Air-conditioning method, air conditioner and computer readable storage medium
CN108826594A (en) * 2018-05-11 2018-11-16 奥克斯空调股份有限公司 Air-conditioning draught fan control method and air conditioner
CN110517292A (en) * 2019-08-29 2019-11-29 京东方科技集团股份有限公司 Method for tracking target, device, system and computer readable storage medium
CN110925970A (en) * 2019-11-04 2020-03-27 佛山市云米电器科技有限公司 Target character wind power intelligent air-out system under multi-person scene

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112984718A (en) * 2020-12-18 2021-06-18 四川虹美智能科技有限公司 Intelligent air conditioner control method, device and system based on human body tracking
WO2022217998A1 (en) * 2021-04-12 2022-10-20 青岛海尔空调器有限总公司 Method and apparatus for air supply control of air conditioner, and air conditioner
CN113611012A (en) * 2021-06-16 2021-11-05 南京邮电大学 Non-invasive people number detection method, device and system based on infrared array sensor
CN114576822A (en) * 2022-03-10 2022-06-03 深圳美智华科智能科技研究中心有限公司 Air conditioner control method based on millimeter wave radar, air conditioner and storage medium

Also Published As

Publication number Publication date
CN112032987B (en) 2022-04-08

Similar Documents

Publication Publication Date Title
CN112032987B (en) Air conditioner control method and device based on infrared human body tracking
CN109934121B (en) Orchard pedestrian detection method based on YOLOv3 algorithm
Jiang et al. FLYOLOv3 deep learning for key parts of dairy cow body detection
CN114299417A (en) Multi-target tracking method based on radar-vision fusion
CN112308881B (en) Ship multi-target tracking method based on remote sensing image
CN108154098A (en) A kind of target identification method of robot, device and robot
CN104766320B (en) Many Bernoulli Jacob under thresholding is measured filter Faint target detection and tracking
CN111780763A (en) Visual positioning method and device based on visual map
CN105868707B (en) A kind of falling from bed behavior real-time detection method based on deep image information
CN106169188A (en) A kind of method for tracing object based on the search of Monte Carlo tree
CN105279483A (en) Fall-down behavior real-time detection method based on depth image
CN112183153A (en) Object behavior detection method and device based on video analysis
CN109141395B (en) Sweeper positioning method and device based on visual loopback calibration gyroscope
CN102184551A (en) Automatic target tracking method and system by combining multi-characteristic matching and particle filtering
CN113642361B (en) Fall behavior detection method and equipment
CN107564035B (en) Video tracking method based on important area identification and matching
CN109791615A (en) For detecting and tracking the method, target object tracking equipment and computer program product of target object
CN106981075A (en) The skeleton point parameter acquisition devices of apery motion mimicry and its recognition methods
Ong et al. Effective moving object tracking using modified flower pollination algorithm for visible image sequences under complicated background
CN104951055B (en) The method and apparatus and air-conditioning equipment of the operation mode of equipment are set
CN113781519A (en) Target tracking method and target tracking device
CN115335872A (en) Training method of target detection network, target detection method and device
CN113688734B (en) FPGA heterogeneous acceleration-based old people falling detection method
CN114299050A (en) Infrared image tumble detection method based on improved Alphapos
CN108564063A (en) Centre of the palm localization method based on depth information and system

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
GR01 Patent grant
GR01 Patent grant