CN110084177B - Positioning system, method, control system, air conditioner and storage medium - Google Patents
Positioning system, method, control system, air conditioner and storage medium Download PDFInfo
- Publication number
- CN110084177B CN110084177B CN201910332972.3A CN201910332972A CN110084177B CN 110084177 B CN110084177 B CN 110084177B CN 201910332972 A CN201910332972 A CN 201910332972A CN 110084177 B CN110084177 B CN 110084177B
- Authority
- CN
- China
- Prior art keywords
- image
- contour
- position information
- target
- communication unit
- 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.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
- F24F2120/12—Position of occupants
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a positioning system, a method, a control system, an air conditioner and a storage medium, and relates to the technical field of equipment, wherein the positioning system comprises: the image acquisition device is used for shooting the target area under the overlooking visual angle to obtain a target area image; and the information processing device is used for acquiring the position information of the human body according to the target area image and sending the position information to the main control device of the equipment so that the main control device can correspondingly control and operate based on the position information. The positioning system, the positioning method, the control system, the air conditioner and the storage medium can obtain the target area image under the overlooking visual angle and obtain the position information of the user based on the image identification result, and can control the air conditioner based on the position information; the acquired image data volume is small and the positioning precision is high; the volume is small, and the cost is low; the user experience can be improved.
Description
Technical Field
The invention relates to the technical field of equipment, in particular to a positioning system, a positioning method, a control system, an air conditioner and a storage medium.
Background
With the development of economy and the continuous improvement of living standard of people, higher requirements are put forward on the comfort level and the energy consumption of equipment. For example, in the case of an air conditioner having an intelligent adjustment function, such as a central air conditioner, when intelligently adjusting wind power, wind direction, and the like, it is necessary to acquire position information of a user in a room and intelligently adjust the wind direction and the wind power based on the position information. Currently, an infrared sensor and the like can be used for positioning a user, but the indoor position of the user cannot be accurately determined by the method; the computer vision technology can also be adopted to position the user, but the current computer vision positioning scheme has the problems of high cost, redundant acquired information, complex processing, exposure of user privacy and the like, and influences the user experience.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a positioning system, a positioning method, a control system, an air conditioner, and a storage medium, which can obtain a target area image of a target area in a top view and obtain position information of a human body from the target area image.
According to an aspect of the present invention, there is provided a positioning system comprising: the image acquisition device is used for shooting the target area under the overlooking visual angle to obtain a target area image; and the information processing device is used for obtaining the position information of the human body according to the target area image and sending the position information to a main control device of the equipment so that the main control device carries out corresponding control operation based on the position information.
Optionally, the information processing apparatus includes: the receiving module is used for receiving the target area image sent by the image acquisition device through a first communication unit; the processing module is used for identifying the human body in the target area image and obtaining the position information corresponding to the human body; and the sending module is used for sending the position information to the main control device through a second communication unit.
Optionally, the processing module includes: the ashing unit is used for carrying out image ashing processing on the target area image to obtain a gray level image corresponding to the target area image; a binarization unit, configured to perform image binarization processing on the grayscale image to obtain a binary image corresponding to the grayscale image; the background determining unit is used for processing the binary image based on a preset background separation algorithm to determine a static background; and the target positioning unit is used for acquiring a human body contour according to the static background and acquiring the position information corresponding to the human body contour.
Optionally, the ashing unit is further configured to perform filtering processing on the grayscale image after the grayscale image is obtained; wherein the filtering process includes: and (5) median filtering processing.
Optionally, the binarization unit is further configured to determine a grayscale threshold, and perform image binarization processing on the grayscale image based on the grayscale threshold; wherein the grayscale threshold includes: a grayscale value corresponding to ground in the grayscale image.
Optionally, the binarization unit is further configured to sequentially perform erosion and expansion processing on the binary image, and sequentially perform expansion and erosion processing on the binary image after the erosion and expansion processing is performed.
Optionally, the background separation algorithm comprises: an interframe difference method; the background determination unit is specifically configured to obtain a plurality of image frames based on the binary image in each detection period; acquiring the value of each pixel point of the image frame, calculating the difference value between the value of each pixel point of each image frame and the value of the corresponding pixel point in the previous image frame, and acquiring the mean square error of all the pixel points based on the difference value; and acquiring a set of pixel points with the mean square error lower than a preset mean square error threshold, and determining image areas corresponding to all the pixel points in the set as the static background.
Optionally, the background determining unit is further configured to increase the mean square error threshold if a proportion of an area occupied by the static background in the binary image is smaller than a first proportional threshold; and if the proportion of the area occupied by the static background in the binary image is within a preset proportion interval, reducing the mean square error threshold.
Optionally, the target positioning unit is specifically configured to remove the static background from the two-phase image to obtain a local image; extracting a target contour in the local image by utilizing an edge detection operator; obtaining the perimeter of the target contour and the area surrounded by the target contour, and determining the circularity of the target contour based on the perimeter and the area; judging whether the target contour is the human body contour according to the circularity and a preset contour judgment rule;
optionally, the target location unit is specifically configured to obtain pixel coordinate information corresponding to pixels constituting the human body contour, obtain average coordinate information according to the pixel coordinate information, and determine the position information according to the average coordinate information.
Optionally, the first communication unit comprises: a bus communication unit, a serial communication unit or a wireless communication unit; the second communication unit includes: a bus communication unit, a serial communication unit or a wireless communication unit.
Optionally, the first communication unit is a USB communication unit, and the second communication unit is an SPI bus communication unit.
Optionally, the image acquiring apparatus includes: a monocular image capturing device; the information processing apparatus includes: an information processing device based on raspberry pi;
optionally, the apparatus comprises: an air conditioner; wherein, the control operation that the master control unit of air conditioner carries out includes: control operations for wind direction and/or wind force.
Optionally, the image acquisition device is arranged on a panel of the air conditioner, and the information processing device is arranged in a host of the air conditioner; wherein, the air conditioner includes: raise-hole machine air-conditioner, air-duct machine air-conditioner.
According to another aspect of the present invention, there is provided an air conditioning control system including: a positioning system as described above.
According to still another aspect of the present invention, there is provided an air conditioner including: the air conditioner control system is as above.
According to still another aspect of the present invention, there is provided a positioning method, including: receiving a target area image obtained by shooting a target area by an image acquisition device under a top view angle; and obtaining the position information of the human body according to the target area image, and sending the position information to a main control device of the equipment so that the main control device carries out corresponding control operation based on the position information.
Optionally, the target area image sent by the image acquisition device is received through a first communication unit; identifying the human body in the target area image, and obtaining the position information corresponding to the human body; and sending the position information to the main control device through a second communication unit.
Optionally, the identifying the human body in the target area image, and the obtaining the position information corresponding to the human body includes: performing image ashing processing on the target area image to obtain a gray level image corresponding to the target area image; carrying out image binarization processing on the gray level image to obtain a binary image corresponding to the gray level image; processing the binary image based on a preset background separation algorithm to determine a static background; and acquiring a human body contour according to the static background, and acquiring the position information corresponding to the human body contour.
Optionally, after obtaining the grayscale image, performing filtering processing on the grayscale image; wherein the filtering process includes: and (5) median filtering processing.
Optionally, the performing image binarization processing on the grayscale image includes: determining a gray threshold value, and performing image binarization processing on the gray image based on the gray threshold value; wherein the grayscale threshold includes: a grayscale value corresponding to ground in the grayscale image.
Optionally, sequentially performing erosion and expansion treatment on the binary image; and sequentially performing expansion and corrosion treatment on the binary image subjected to corrosion and expansion treatment.
Optionally, the background separation algorithm comprises: an interframe difference method; the processing of the binary image based on a preset background separation algorithm comprises: obtaining a plurality of image frames based on the binary image in each detection period; acquiring the value of each pixel point of the image frame, calculating the difference value between the value of each pixel point of each image frame and the value of the corresponding pixel point in the previous image frame, and acquiring the mean square error of all the pixel points based on the difference value; and acquiring a set of pixel points with the mean square error lower than a preset mean square error threshold, and determining image areas corresponding to all the pixel points in the set as the static background.
Optionally, if the proportion of the area occupied by the static background in the binary image is smaller than a first proportion threshold, increasing the mean square error threshold; and if the proportion of the area occupied by the static background in the binary image is within a preset proportion interval, reducing the mean square error threshold.
Optionally, the obtaining a human body contour according to the static background includes: removing the static background from the two-phase image to obtain a local image; extracting a target contour in the local image by utilizing an edge detection operator; obtaining the perimeter of the target contour and the area surrounded by the target contour, and determining the circularity of the target contour based on the perimeter and the area; and judging whether the target contour is the human body contour according to the circularity and a preset contour judgment rule.
Optionally, the obtaining the position information corresponding to the human body contour includes: obtaining pixel point coordinate information corresponding to pixel points forming the human body contour, obtaining average coordinate information according to the pixel point coordinate information, and determining the position information according to the average coordinate information.
According to yet another aspect of the present invention, there is provided a computer readable storage medium having stored thereon computer instructions for execution by a processor to perform the method as described above.
According to the positioning system, the positioning method, the control system, the air conditioner and the storage medium, the target area image of the target area under the overlooking visual angle is obtained, the position information of a human body is obtained according to the target area image, and the position information is sent to the main control device of the equipment to carry out corresponding control operation; the target area image under the overlooking visual angle can be obtained, the position information of the user is obtained based on the image recognition result, and the control of the air conditioner based on the position information can be realized; the acquired image data volume is small and the positioning precision is high; the volume is small, and the cost is low; the user experience 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 needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of one embodiment of a positioning system according to the present invention;
FIG. 2 is a schematic view of the installation of the image capture device and its capture from a top view;
FIG. 3 is a block diagram of an information processing device in an embodiment of a positioning system according to the invention;
FIG. 4 is a block diagram of a processing module of an information processing device in an embodiment of a positioning system according to the invention;
FIG. 5 is a schematic view of the connection of the positioning system according to the present invention to the various components of the raise boring machine;
FIG. 6 is a schematic flow chart diagram illustrating one embodiment of a position determination method in accordance with the present invention;
fig. 7 is a schematic flow chart of obtaining location information in an embodiment of a positioning method according to the present invention;
fig. 8 is a schematic flow chart of determining a static background in an embodiment of the positioning method according to the present invention.
Detailed Description
The present invention now will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the invention are shown. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. The technical solution of the present invention is described in various aspects below with reference to various figures and embodiments.
Hereinafter, "first", "second", etc. are only descriptive differences and have no other special meanings.
As shown in fig. 1, the present invention provides a positioning system comprising: an image acquisition apparatus 1 and an information processing apparatus 2. The image capturing apparatus 1 is configured to capture an image of a target area in a top view, where the target area may be an air conditioning operation area set indoors or the like, and obtain an image of the target area. The information processing device 2 obtains the position information of the human body according to the target area image, and sends the position information to the main control device 3 of the equipment, so that the main control device 3 carries out corresponding control operation based on the position information. The device may be an air conditioner or the like, and the control operation performed by the main control apparatus 3 may be a control operation for wind direction, wind power, or the like.
The image acquiring apparatus 1 includes a camera device, and may be a monocular camera device or the like, for example, the monocular camera device is a monocular camera, the cost of the monocular camera is low, and the amount of acquired image data is small. The information processing apparatus 2 includes an information processing apparatus based on raspberry pi, and the like. Raspberry type Raspberry Pi is an open-source hardware, is a card type computer, is internally provided with software such as Broadcom video core IV, OpenGL ES 2.0 and the like, can realize the modularized splicing and control of the open-source hardware, can realize the operation such as digital signal processing and the like, and has the characteristics of small size, low cost and the like. The information processing apparatus 2 may be a variety of card computers.
The air conditioner comprises a courtyard machine air conditioner, an air duct machine air conditioner and the like. For example, the air conditioner is a patio air conditioner, and the image acquisition device 1 is disposed on a panel of the patio air conditioner, and may be embedded in the center of the surface of the panel of the patio air conditioner, facing vertically downward into the room. The information processing device 2 is provided in the main unit of the patio air conditioner, and is located inside the panel. The information processing device 2 can be a card computer, which is low in price and small in size and is convenient to be embedded into the courtyard machine. As shown in fig. 2, the patio air conditioner is installed on the ceiling in the center of the room, at a certain height from the ground. The camera device is installed at the center of the surface of the panel of the air conditioner of the courtyard unit, and the camera device shoots under the overlooking visual angle, so that indoor image information can be more comprehensively collected.
In one embodiment, as shown in fig. 3, the information processing apparatus 2 includes: a receiving module 21, a processing module 22 and a transmitting module 23. The receiving module 21 receives the target area image transmitted by the image capturing apparatus through the first communication unit. The processing module 22 identifies a human body in the target area image, and obtains position information corresponding to the human body. The transmitting module 23 transmits the position information to the main control apparatus through the second communication unit. The first communication unit and the second communication unit can be various, and can be a bus communication unit, a serial communication unit, a wireless communication unit or the like.
For example, the first communication unit is a USB (Universal Serial Bus) communication unit, and the second communication unit is an SPI (Serial Peripheral Interface) Bus communication unit. The image acquisition device may be a monocular camera with 720P, 300W pixels. The receiving module 21 is connected to the image capturing device through a USB communication unit, and receives the target area image transmitted by the image capturing device. The sending module 23 is connected with a main control device of the air conditioner through an SPI bus communication unit, communicates in an SPI bus manner, and sends the position information to the main control device.
In one embodiment, as shown in FIG. 4, the processing module 22 includes: an ashing unit 221, a binarization unit 222, a background determination unit 223, and a target positioning unit 224. The ashing unit 221 performs image ashing processing on the target area image to obtain a grayscale image corresponding to the target area image. The ashing unit 221 performs filter processing including median filter processing and the like on the grayscale image after obtaining the grayscale image. The ashing unit 221 performs filtering processing on the grayscale image to obtain a clearer and better-featured image.
The binarization unit 222 performs image binarization processing on the grayscale image, and obtains a binary image corresponding to the grayscale image. The binarization unit 222 determines a grayscale threshold value, and performs image binarization processing on the grayscale image based on the grayscale threshold value. The image binarization processing is to set the gray value of the pixel point of the gray image to be 0 or 255 based on the comparison result of the gray threshold value and the gray value of the pixel point of the gray image, so that the whole image presents obvious black and white effect. The grayscale threshold includes a grayscale value corresponding to the ground in the grayscale image.
The binarization unit 222 sequentially performs erosion and expansion processing on the binary image, and sequentially performs expansion and erosion processing on the binary image after the erosion and expansion processing. The background determination unit 223 processes the binary image based on a preset background separation algorithm to determine a static background. The target positioning unit 224 obtains the human body contour according to the static background, and obtains the position information corresponding to the human body contour.
The target area image acquired by the image acquisition device is subjected to image graying and binarization processing, so that the data volume can be compressed, and the real-time performance of image processing by the information processing device is improved. According to the position difference of the indoor target area, different gray threshold values (binarization threshold values) can be set, and the active area and the non-active area of the human body are preliminarily divided, so that the binarized image is more targeted, and the outline of the target can be highlighted.
For example, in a home environment, a grayscale threshold is set based on a ground color, and image binarization processing is performed, so that a region in which a human body acts and a region occupied by furniture can be roughly outlined. The gray value corresponding to the ground in the gray image is used as the gray threshold value to distinguish the ground from the non-ground part, so that the subsequent calculation amount can be reduced.
And performing opening operation (corrosion first and then expansion) on the binary image to eliminate isolated small points and burrs in the human body contour image so as to realize noise reduction, and performing closing operation (corrosion first and then expansion) to close cracks of the human body contour image so as to realize complete shape. The expansion and corrosion processing can be carried out by adopting the existing expansion operation and corrosion operation methods with various morphologies, and isolated small points and burrs can be removed while the overall shape of the image is not changed.
In one embodiment, the binary image may be processed to determine a static background based on a variety of background separation algorithms. The background separation algorithm may be an interframe difference method, an average background method, or the like. For example, the background separation algorithm is an inter-frame difference method. The background determination unit 223 is configured to obtain a plurality of image frames based on the binary image in each detection period. The background determination unit 223 obtains a value of each pixel point of the image frame, calculates a difference between the value of each pixel point of each image frame and a value of a corresponding pixel point in the previous image frame, and obtains a mean square error of all the pixel points based on the difference. The value of the pixel point can be the gray value of the pixel point, etc.
The background determining unit 223 obtains a set of pixel points having a mean square error lower than a preset mean square error threshold, and determines an image area corresponding to all the pixel points in the set as a static background, where the image area corresponding to all the pixel points in the set is regarded as an image portion that is not changed for a long time and is identified as the static background.
Each detection period is a time period for performing one round of image sampling and performing position information calculation, and the time duration of 3 minutes and the like can be set as one detection period. The static background is extracted by using the background separation algorithm, so that the operation amount can be further reduced. And (3) adopting an adaptive inter-frame difference method, and carrying out identification processing on a static background on an image frame part which is kept unchanged for a long time in each detection period.
For example, an image frame is first acquired, and pixel data of the image frame is stored. Continuously collecting a plurality of image frames, carrying out difference operation on the value of each pixel point in the plurality of continuous image frames and the value of the corresponding pixel point in the previous image frame, and obtaining the mean square error of all the pixel points based on the difference value. For example, 10 image frames are obtained based on the binary image, and a value of each pixel point of the image frames is obtained. Calculating the difference between the value of the pixel point A of each image frame and the value of the corresponding pixel point A in the previous image frame, so as to obtain nine difference values, and obtaining the mean square error of the pixel point A based on the nine difference values. The mean square error of all the pixel points can be obtained based on the same method.
Because the image acquisition device is static relative to the static background, the static background has no or only small displacement under continuous multi-frame images, and the mean square error value reflected on the pixel point is small. Therefore, a mean square error threshold is set, a set of pixels with a mean square error exceeding the mean square error threshold is determined as a dynamic image, such as a user and a pet, and a set of pixels with a mean square error below the mean square error threshold is determined as a static background, such as furniture and household appliances.
In one embodiment, the background determination unit 233 increases the mean square error threshold if the proportion of the area occupied by the static background in the binary image is less than a first proportion threshold, which may be 10%, 15%, or the like. If the proportion of the area occupied by the static background in the binary image is within a preset proportion interval, the background determination unit 233 reduces the mean square error threshold, and the proportion interval may be 90% -95%, and the like.
An improved interframe difference method aiming at the practical application scene of the air conditioner is provided, and the value of the mean square error threshold is self-adapted. In the use process of the air conditioner, the relative static relation between the image acquisition device and the indoor environment is influenced due to the fact that different degrees of vibration exist in the air supply amount change and the opening and closing of the air sweeping panel. At this time, the background stripping effect is poor, and the threshold of the mean square error used for judging the static background needs to be adaptively adjusted. For example, when the proportion of the area occupied by the peeled static background in the binary image is less than 10%, the setting of the mean square error threshold value is increased. And when the proportion of the area occupied by the stripped static background in the binary image is between 90 and 95 percent, reducing the setting of the mean square error threshold.
In one embodiment, the object localization unit 224 removes the static background from the two-phase image, obtaining a local image. The calculation range of the image processing is separated from the static background area, so that the calculation amount can be reduced, and the misjudgment of the contour of the static background (such as furniture) on the extraction of the human body contour can be reduced. The object locating unit 224 extracts the human body contour based on the static background in the local image by using the edge detection operator.
The target positioning unit 224 may extract a target contour in the local image by using an edge detection operator, where the target contour includes contours of moving objects (e.g., sweeping robots, pets, etc.) of human bodies and non-human bodies. Obtaining the perimeter of the target contour and the area surrounded by the target contour, and determining the circularity of the target contour based on the perimeter and the area, wherein the circularity is C:
wherein L is the perimeter of the target contour, and the perimeter of the target contour can be obtained by using various methods, for example, the perimeter of the target contour is calculated by using a cvArclength function of an openCV open-source computer vision library; s is the area surrounded by the target contour, and the area surrounded by the target contour can be obtained by using various methods, for example, the proportion of the number of pixels included in the region surrounded by the target contour to the pixels of the full picture is calculated, and the area surrounded by the target contour can be calculated according to the proportion obtained by calculation and the area corresponding to the full picture.
And judging whether the target contour is a human body contour according to the circularity and a preset contour judgment rule, wherein the contour judgment rule can be various. For example, if C is equal to 1, the target contour is a circle, the first circularity threshold K1 and the second circularity threshold K2 are set, the target corresponding to the target contour conforming to K1< C < K2 is regarded as the sweeping robot, the target corresponding to the target contour conforming to K2< C is regarded as a human body, and the target corresponding to the target contour conforming to C < K1 is regarded as an animal (pet, etc.).
The target positioning unit 224 obtains pixel point coordinate information corresponding to pixel points constituting the human body contour, obtains average coordinate information according to the pixel point coordinate information, and takes the average coordinate information as position information.
In one embodiment, the object-locating unit 224 may invoke the CvFindContours, CvRectangle functions in the open-source computer vision library to perform the extraction and cutting of the human body contour. The object locating unit 224 may also extract a human body contour based on a static background (which may also include a contour of a non-human moving object, etc.) in the local image by using an edge detection operator. A variety of edge detection operators can be used, including Roberts, Canny, Sobel, etc.
The existing edge detection algorithms corresponding to the edge detection operators can be adopted to extract the human body contour (including the contour of a non-human body moving object and the like) based on the static background. For example, the static background is removed according to an inter-frame difference method, a local image from which the static background is removed is used as an input signal to calculate a Canny algorithm, and a Canny operator is used for extracting a human body contour based on the static background from the local image.
In one embodiment, the image coordinate system and the actual environment coordinate system may be predefined, and a coordinate mapping relationship between the image coordinate system and the actual environment coordinate system may be established. The image coordinate system and the actual environment coordinate system may be set in various ways. The human body contour is a set of continuous pixels connected end to end, and pixel coordinate information of the continuous pixels is obtained, and the pixel coordinate information can be the abscissa and the ordinate of the pixel in an image coordinate system.
The average coordinate information may be an average value of the abscissa and the ordinate of the continuous pixels, and the average coordinate information is used as the position information. The average coordinate information may be used as the position information of the human body, or an abscissa and an ordinate corresponding to the average coordinate information in the actual environment coordinate system may be obtained based on the coordinate mapping relationship, and the abscissa and the ordinate are used as the position information of the human body.
As shown in fig. 5, the image capturing apparatus 1 captures images in a top view, and the image capturing apparatus 1 may be a monocular image capturing apparatus or the like. The information processing device 2 is connected with the image acquisition device 1 through a USB communication unit, and the information processing device 2 is connected with the courtyard machine inner unit 4 through an SPI communication unit, namely is connected with a main control device in the courtyard machine inner unit 4. The 220V power supply 9 is used for supplying power to the 3.3V voltage stabilizing module 7, the 12V voltage stabilizing module 8 and the raise machine inner machine 4. The master control device in the raise machine inner machine 4 can control the fan 5 and the wind sweeping motor 6.
The main control device in the courtyard machine indoor unit 4 controls wind power, air volume and the like according to the position information of the human body sent by the information processing device 2. For example, the control of the wind sweeping panel is used for avoiding blowing air to the position of the user and avoiding blowing the user directly; the wind power is adjusted in a self-adaptive mode based on the number of indoor human bodies. The fan 5 is used for controlling the air outlet volume of the inner machine 4 of the courtyard machine, such as medium-grade air volume, low-grade air volume and high-grade air volume. The wind sweeping motor 6 is a stepping motor for controlling the wind sweeping panel to run, and controls the rotation displacement of the wind sweeping panel in the processes of left wind sweeping, right wind sweeping and up-down wind sweeping.
For example, when the shaft machine internal unit 4 needs to increase the amount of air blown, the main control device in the shaft machine internal unit 4 outputs PWM waves with wider pulse width to the fan 5, the rotating speed of the fan 5 is increased, and the amount of air blown is increased. When the raise-hole machine indoor unit 4 needs to sweep wind to the left side, the wind sweeping motor 6 needs to be driven to move forward in the reverse direction, and a main control device in the raise-hole machine indoor unit 4 outputs four-phase eight-beat driving signals to the wind sweeping motor 6.
In one embodiment, the invention provides an air conditioner control system comprising the positioning system as in any one of the above embodiments.
In one embodiment, the invention provides an air conditioner, which comprises the air conditioner control system in any one of the above embodiments. The air conditioner can be a courtyard machine air conditioner, an air duct machine air conditioner and the like.
Fig. 6 is a schematic flowchart of an embodiment of a positioning method according to the present invention, as shown in fig. 6:
The target area image sent by the image acquisition device can be received through the first communication unit, the human body in the target area image is identified, the position information corresponding to the human body is obtained, and the position information is sent to the main control device through the second communication unit.
In an embodiment, fig. 7 is a schematic flowchart of a process of obtaining location information in an embodiment of a positioning method according to the present invention, as shown in fig. 7:
in step 701, the image of the target area is subjected to image ashing processing to obtain a gray image corresponding to the image of the target area.
And step 702, performing image binarization processing on the gray level image to obtain a binary image corresponding to the gray level image.
And 703, processing the binary image based on a preset background separation algorithm to determine a static background.
After obtaining the gray level image, performing filtering processing on the gray level image, wherein the filtering processing comprises the following steps: median filtering, etc. Determining a gray threshold value, and performing image binarization processing on a gray image based on the gray threshold value, wherein the gray threshold value comprises: gray values corresponding to the ground in the gray scale image, etc. And sequentially carrying out corrosion and expansion treatment on the binary image, and sequentially carrying out expansion and corrosion treatment on the binary image subjected to corrosion and expansion treatment.
In an embodiment, fig. 8 is a schematic flowchart of determining a static background in an embodiment of the positioning method according to the present invention, and the background separation algorithm is an inter-frame difference method, as shown in fig. 8:
in step 801, in each detection period, a plurality of image frames are obtained based on the binary image.
And if the proportion of the area occupied by the static background in the binary image is smaller than a first proportional threshold, increasing the mean square error threshold, and if the proportion of the area occupied by the static background in the binary image is within a preset proportional interval, decreasing the mean square error threshold.
In one embodiment, the static background is removed from the two-phase image, and a local image is obtained. And extracting the human body contour based on the static background in the local image by using an edge detection operator. For example, an edge detection operator is used for extracting a target contour from a local image, the perimeter of the target contour and the area surrounded by the target contour are obtained, the circularity of the target contour is determined based on the perimeter and the area, and whether the target contour is a human body contour is judged according to the circularity and a preset contour judgment rule.
Obtaining pixel point coordinate information corresponding to pixel points forming the human body outline, obtaining average coordinate information according to the pixel point coordinate information, and determining the position information of the human body according to the average coordinate information.
In one embodiment, the present disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a positioning method as in any of the above embodiments.
In the positioning system, the positioning method, the control system, the air conditioner and the storage medium in the embodiments, the target area image of the target area under the overlooking visual angle of the image acquisition device is obtained, the position information of the human body is obtained according to the target area image, and the position information is sent to the main control device of the air conditioner to perform corresponding control operation; the method comprises the steps of obtaining a target area image under a overlooking visual angle, obtaining position information of a user based on an image recognition result, and controlling the air conditioner based on the position information; the acquired image data volume is small, and the positioning accuracy of the used positioning algorithm is higher; the requirement of air conditioner control can be met, and the privacy of a user is not invaded for off-line operation; the image is shot under the overlooking visual angle by utilizing the model characteristics of the courtyard machine without independently installing an image acquisition device; the volume is small, the cost is low, the price advantage is achieved, the product competitiveness is improved, and the use experience of a user can be improved.
The method and system of the present invention may be implemented in a number of ways. For example, the methods and systems of the present invention may be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically indicated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as a program recorded in a recording medium, the program including machine-readable instructions for implementing a method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (22)
1. A positioning system, comprising:
the image acquisition device is used for shooting the target area under the overlooking visual angle to obtain a target area image;
the information processing device is used for obtaining the position information of the human body according to the target area image and sending the position information to a main control device of the equipment so that the main control device can correspondingly control and operate based on the position information;
wherein the information processing apparatus includes:
a processing module, comprising:
a background determination unit configured to obtain a plurality of image frames based on a binary image corresponding to the target area image in each detection period; acquiring the value of each pixel point of the image frame, calculating the difference value between the value of each pixel point of each image frame and the value of the corresponding pixel point in the previous image frame, and acquiring the mean square error of all the pixel points based on the difference value; acquiring a set of pixel points with mean square errors lower than a preset mean square error threshold, and determining image areas corresponding to all the pixel points in the set as static backgrounds;
the background determination unit is further configured to increase the mean square error threshold if the proportion of the area occupied by the static background in the binary image is smaller than a first proportional threshold; if the proportion of the area occupied by the static background in the binary image is within a preset proportion interval, reducing the mean square error threshold;
the target positioning unit is used for acquiring a human body contour according to the static background and acquiring the position information corresponding to the human body contour;
the target positioning unit is specifically configured to obtain pixel coordinate information corresponding to pixels constituting the human body contour, obtain average coordinate information according to the pixel coordinate information, and determine the position information according to the average coordinate information.
2. The system of claim 1, wherein,
the information processing apparatus further includes:
a receiving module, configured to receive, through a first communication unit, the target area image sent by the image obtaining apparatus;
and the sending module is used for sending the position information to the main control device through a second communication unit.
3. The system of claim 2, wherein,
the processing module further comprises:
the ashing unit is used for carrying out image ashing processing on the target area image to obtain a gray level image corresponding to the target area image;
and the binarization unit is used for carrying out image binarization processing on the gray level image to obtain a binary image corresponding to the gray level image.
4. The system of claim 3, wherein,
the ashing unit is further used for performing filtering processing on the gray level image after the gray level image is obtained; wherein the filtering process includes: and (5) median filtering processing.
5. The system of claim 3, wherein,
the binarization unit is also used for determining a gray threshold value and carrying out image binarization processing on the gray image based on the gray threshold value; wherein the grayscale threshold includes: a grayscale value corresponding to ground in the grayscale image.
6. The system of claim 5, wherein,
and the binarization unit is also used for sequentially carrying out corrosion and expansion treatment on the binary image, and sequentially carrying out expansion and corrosion treatment on the binary image after the corrosion and expansion treatment.
7. The system of claim 3, wherein,
the target positioning unit is specifically configured to remove the static background from the binary image to obtain a local image; extracting a target contour in the local image by utilizing an edge detection operator; obtaining the perimeter of the target contour and the area surrounded by the target contour, and determining the circularity of the target contour based on the perimeter and the area; and judging whether the target contour is the human body contour according to the circularity and a preset contour judgment rule.
8. The system of claim 2, wherein,
the first communication unit includes: a bus communication unit, a serial communication unit or a wireless communication unit; the second communication unit includes: a bus communication unit, a serial communication unit or a wireless communication unit.
9. The system of claim 8, wherein,
the first communication unit is a USB communication unit, and the second communication unit is an SPI bus communication unit.
10. The system of claim 1, wherein,
the image acquisition apparatus includes: a monocular camera device;
the information processing apparatus includes: an information processing apparatus based on raspberry pi.
11. The system of claim 1, wherein,
the apparatus comprises: an air conditioner; wherein, the control operation that the master control unit of air conditioner carries out includes: control operations for wind direction and/or wind force.
12. The system of claim 11, wherein,
the image acquisition device is arranged on a panel of the air conditioner, and the information processing device is arranged in a host of the air conditioner;
wherein, the air conditioner includes: raise-hole machine air-conditioner, air-duct machine air-conditioner.
13. An air conditioning control system comprising:
the positioning system of any one of claims 1 to 12.
14. An air conditioner, comprising:
the air conditioning control system of claim 13.
15. A method of positioning, comprising:
receiving a target area image obtained by shooting a target area by an image acquisition device under a top view angle;
obtaining position information of a human body according to the target area image, and sending the position information to a main control device of equipment so that the main control device performs corresponding control operation based on the position information;
wherein, in each detection period, a plurality of image frames are obtained based on a binary image corresponding to the target area image; acquiring the value of each pixel point of the image frame, calculating the difference value between the value of each pixel point of each image frame and the value of the corresponding pixel point in the previous image frame, and acquiring the mean square error of all the pixel points based on the difference value; acquiring a set of pixel points with mean square errors lower than a preset mean square error threshold, and determining image areas corresponding to all the pixel points in the set as static backgrounds;
if the proportion of the area occupied by the static background in the binary image is smaller than a first proportional threshold, increasing the mean square error threshold; if the proportion of the area occupied by the static background in the binary image is within a preset proportion interval, reducing the mean square error threshold;
obtaining a human body contour according to the static background, and obtaining the position information corresponding to the human body contour; obtaining pixel point coordinate information corresponding to pixel points forming the human body contour, obtaining average coordinate information according to the pixel point coordinate information, and determining the position information according to the average coordinate information.
16. The method of claim 15, further comprising:
receiving the target area image sent by the image acquisition device through a first communication unit;
and sending the position information to the main control device through a second communication unit.
17. The method of claim 16, further comprising:
performing image ashing processing on the target area image to obtain a gray level image corresponding to the target area image;
and carrying out image binarization processing on the gray level image to obtain a binary image corresponding to the gray level image.
18. The method of claim 17, further comprising:
after the gray level image is obtained, filtering the gray level image;
wherein the filtering process includes: and (5) median filtering processing.
19. The method of claim 17, said image binarization processing of said grayscale image comprising:
determining a gray threshold value, and performing image binarization processing on the gray image based on the gray threshold value;
wherein the grayscale threshold includes: a grayscale value corresponding to ground in the grayscale image.
20. The method of claim 19, further comprising:
sequentially carrying out corrosion and expansion treatment on the binary image;
and sequentially performing expansion and corrosion treatment on the binary image subjected to corrosion and expansion treatment.
21. The method of claim 17, the obtaining a human body contour from the static background comprising:
removing the static background from the binary image to obtain a local image;
extracting a target contour in the local image by utilizing an edge detection operator;
obtaining the perimeter of the target contour and the area surrounded by the target contour, and determining the circularity of the target contour based on the perimeter and the area;
and judging whether the target contour is the human body contour according to the circularity and a preset contour judgment rule.
22. A computer readable storage medium having stored thereon computer instructions for execution by a processor to perform the method of any one of claims 15 to 21.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910332972.3A CN110084177B (en) | 2019-04-24 | 2019-04-24 | Positioning system, method, control system, air conditioner and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910332972.3A CN110084177B (en) | 2019-04-24 | 2019-04-24 | Positioning system, method, control system, air conditioner and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110084177A CN110084177A (en) | 2019-08-02 |
| CN110084177B true CN110084177B (en) | 2020-10-20 |
Family
ID=67416486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910332972.3A Active CN110084177B (en) | 2019-04-24 | 2019-04-24 | Positioning system, method, control system, air conditioner and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084177B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733571B (en) * | 2019-10-14 | 2024-05-17 | 杭州萤石软件有限公司 | Control method, device and storage medium for robot |
| CN114120354A (en) * | 2021-10-14 | 2022-03-01 | 武汉高德智感科技有限公司 | Human body detection and positioning method and device applied to air conditioner and intelligent sensing system |
| CN116967846B (en) * | 2023-09-25 | 2023-12-12 | 深圳市磐锋精密技术有限公司 | Intelligent robot vision positioning system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780526A (en) * | 2016-11-21 | 2017-05-31 | 浙江工业大学 | A kind of ferrite wafer alligatoring recognition methods |
| CN107514745A (en) * | 2017-08-03 | 2017-12-26 | 上海斐讯数据通信技术有限公司 | A kind of method and system of intelligent air condition stereoscopic vision positioning |
| CN109063602A (en) * | 2018-07-13 | 2018-12-21 | 北京理工大学 | Method for tracking target and device under Celestial Background based on path continuity function |
-
2019
- 2019-04-24 CN CN201910332972.3A patent/CN110084177B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110084177A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084177B (en) | Positioning system, method, control system, air conditioner and storage medium | |
| CN110866903B (en) | Ping-pong ball identification method based on Hough circle transformation technology | |
| Malima et al. | A fast algorithm for vision-based hand gesture recognition for robot control | |
| US9124812B2 (en) | Object image capture apparatus and method | |
| CN107908195B (en) | Target tracking method, target tracking device, tracker and computer-readable storage medium | |
| CN109654676B (en) | Adjusting method, device and system of air supply device, computer equipment and storage medium | |
| CN113761970B (en) | Method, system, robot and storage medium for identifying working position based on image | |
| EP3043289B1 (en) | Control system for an autonomous vehicle and a method for generating a control signal and autonomous vehicle equipped with such control system | |
| JP5127531B2 (en) | Image monitoring device | |
| CN108280386B (en) | Monitoring scene detection method and device | |
| CN112949347B (en) | Fan adjusting method based on human body posture, fan and storage medium | |
| CN113822094B (en) | Method, system, robot and storage medium for identifying working position based on image | |
| CN113822095B (en) | Method, system, robot and storage medium for identifying working position based on image | |
| CN113538358A (en) | Robot walking deviation rectifying method and device, intelligent robot and storage medium | |
| US8059153B1 (en) | Three-dimensional object tracking using distributed thin-client cameras | |
| JP2002282210A (en) | Method and apparatus for detecting visual axis | |
| CN113689365B (en) | Target tracking and positioning method based on Azure Kinect | |
| CN111339906A (en) | Image processing device and image processing system | |
| KR101333459B1 (en) | Lane detecting method and apparatus thereof | |
| CN112696372A (en) | Fan adjusting method, fan and storage medium | |
| CN110738689B (en) | Method, system and device for automatically following and avoiding targets by trolley | |
| CN110674751A (en) | Device and method for detecting head posture based on monocular camera | |
| CN113836722B (en) | Assembly state perception method based on wearable device, scene and digital-analog registration | |
| CN109951687B (en) | Machine vision implementation system for underground coal mine environment | |
| CN111062229B (en) | Method and device for identifying outer rotor of wind generating set |
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 |