CN105549724A - User identification method and air conditioning equipment - Google Patents

Abstract

The present application provides a user identification method and air-conditioning equipment, which are used to solve the technical problem that the air-conditioning equipment has low work efficiency when identifying and processing images collected by an infrared camera. The method includes: scanning the first environment where the air conditioner is located by using an infrared sensor array in the air conditioner to obtain a first image corresponding to the first environment; performing median filtering processing on the first image , obtaining a second image corresponding to the first image; determining relevant information of the user in the first environment according to the first image and the second image.

Description

A user identification method and air conditioning equipment

technical field

The invention relates to the field of electronic technology, in particular to a user identification method and an air conditioner.

Background technique

With the rapid development of science and technology, the consumer electronics industry is undergoing great innovations. Among them, air-conditioning equipment has become an indispensable household equipment in people's daily life. It provides users with many services and is increasingly sought after by people.

At present, in order to obtain a better adjustment effect when users use air-conditioning equipment to adjust the air, it is usually necessary for the air-conditioning equipment to obtain information about users in the environment, such as the location of the users in the environment, the number of users, and so on. In practical applications, air-conditioning equipment mainly uses infrared cameras to collect images of the environment, and then determines the user's information through human body recognition on the images, so as to adjust the air-conditioning equipment according to the acquired information, such as switching working modes, etc., so that the air-conditioning equipment Smarter.

However, when the image collected by the infrared camera is recognized and processed, the algorithm is more complicated and the processing time is longer, which makes the working efficiency of the air conditioner lower.

Contents of the invention

The present application provides a user identification method and air-conditioning equipment, which are used to solve the technical problem that the air-conditioning equipment has low work efficiency when identifying and processing images collected by an infrared camera.

On the one hand, the present application provides a user identification method, comprising the following steps:

Scanning a first environment where the air conditioner is located by using an infrared sensor array in the air conditioner to obtain a first image corresponding to the first environment;

performing median filtering processing on the first image to obtain a second image corresponding to the first image;

Relevant information of users in the first environment is determined according to the first image and the second image.

On the other hand, the present application provides an air conditioner, comprising:

An acquisition module, configured to scan a first environment where the air conditioner is located through an infrared sensor array in the air conditioner, and obtain a first image corresponding to the first environment;

A processing module, configured to perform median filtering processing on the first image to obtain a second image corresponding to the first image;

A determining module, configured to determine relevant information of users in the first environment according to the first image and the second image.

The above-mentioned one or more technical solutions in this application have at least one or more of the following technical effects:

In this application, the first image is processed using a relatively simple and quick median filter method, which shortens the processing time for the image and effectively improves the processing efficiency of the air conditioner, so that the first image can be determined through the first image and the second image. The relevant information of the user in the environment, for example, determines the relative information of the user according to the changes of the pixels in the first image and the second image before and after filtering, so the implementation process is relatively simple.

In addition, since the low-priced infrared sensor array is used in the present application to collect images and data, the cost of air-conditioning equipment is reduced.

Description of drawings

Fig. 1 is the schematic diagram of the infrared sensor array in the air conditioner in the embodiment of the present invention;

Fig. 2 is the flowchart of the user identification method in the embodiment of the present invention;

Fig. 3 is a schematic diagram of the arrangement of data collected in one cycle in an embodiment of the present invention;

4 is a schematic diagram of performing median filtering on pixels in an embodiment of the present invention;

FIG. 5 is a schematic diagram of determining pixel points related to a user in an embodiment of the present invention;

Fig. 6 is a structural block diagram of an air conditioner in an embodiment of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

The technical solutions provided by the embodiments of the present invention can be used in but not limited to air conditioners. The air conditioners can refer to smart air conditioners in smart homes. In practical applications, the air conditioners can be set in the first environment, such as the first environment any position. For example, the first environment may be a living room, a bedroom, an office, etc., which is not specifically limited in this embodiment of the present invention.

Optionally, an infrared sensor array for data collection can be provided in the air conditioner, and the infrared sensor array is connected with a motor (such as a stepping motor) in the air conditioner, so that when the motor driver controls the motor to run, the motor can drive The infrared sensor array is rotated so that different areas in the first environment are scanned by the infrared sensor array.

Generally speaking, the infrared sensor array can be a 16*4, 24*32 or 1*32 infrared sensor array, which can be set by those of ordinary skill in the field of the present invention according to the actual situation, and the embodiment of the present invention makes no specific limitation. In the embodiment of the present invention, an infrared sensor array of 16*4 is taken as an example for illustration, and the infrared sensor used may be a low-pixel uncooled infrared sensor.

As shown in FIG. 1 , it is a possible infrared sensor array in the air conditioner in the embodiment of the present invention.

Certainly, the air conditioner may also include other working components, such as a processor, a memory, a communication module, etc., which are not specifically limited in this embodiment of the present invention.

The method provided by the present invention will be described below in conjunction with the accompanying drawings.

As shown in FIG. 2 , an embodiment of the present invention provides a user identification method, and the process of the method is described as follows.

S11: Scan the first environment where the air conditioner is located by using the infrared sensor array in the air conditioner to obtain a first image corresponding to the first environment;

S12: Perform median filtering processing on the first image to obtain a second image corresponding to the first image;

S13: Determine relevant information of the user in the first environment according to the first image and the second image.

Generally speaking, the scanning range of the infrared sensor array is limited, such as 12°, 16°, 20°, etc. Therefore, when scanning the first environment, the infrared sensor array can perform multiple scans. Generally speaking, the scanning range of an infrared sensor in the horizontal direction can be 4°, and the scanning range in the vertical direction can be 3.75°, so the scanning range of a 16*4 infrared sensor array is 16°. Then, when using the 16*4 infrared sensor array to scan the first area in the first environment, if the angle between the two edge lines of the first area relative to the air conditioner is 112° (this angle is usually defined by the user relative to The angle of the active area of the air conditioner), the infrared sensor array needs to scan 7 cycles to complete the data collection of the first area.

Optionally, driven by the motor, the infrared sensor array in the air conditioner can periodically scan the first environment. For example, in each cycle, the infrared sensor array can scan at an angle of 1°, 1°, 1°, 13°, etc. are rotated and scanned one by one, and the temperature value corresponding to each scanning angle is obtained. That is, within one cycle, the infrared sensor array rotates 1°, 1°, 1°, and 13° sequentially from the initial position along the first direction (clockwise or counterclockwise), wherein, after each rotation, the infrared sensor array Data collection will be carried out (in the embodiment of the present invention, the collected data is a temperature value as an example), and the temperature value corresponding to each scanning angle can be obtained, and 4 groups of temperature values can be obtained in one cycle. After one cycle of scanning is completed, the next cycle is entered until the scanning of the first environment (or the first area in the first environment) is completed.

Optionally, after obtaining 4 sets of temperature values corresponding to one cycle, the temperature values can be arranged according to a preset method, as shown in Figure 3, the numbers 1, 2, 3, and 4 marked in the horizontal direction respectively represent the temperature values located in the infrared sensor array There are 4 columns of infrared sensors in the system, and each column of infrared sensors collects 4 columns of temperature values in one cycle.

Optionally, the n pixels included in the first image are the pixels corresponding to the infrared sensor array. If the infrared sensor array is a 16*4 infrared sensor array, that is, the infrared sensor array contains 64 infrared sensors, and these infrared sensors are arranged in 16 rows and 4 columns, then the scanned image obtained by scanning the infrared sensor array once will be It includes 64 pixels corresponding to the infrared sensor array, and the arrangement of the 64 pixels may be the same as that of the infrared sensor array. In the embodiment of the present invention, the temperature value obtained by scanning the infrared sensor array is the initial temperature value corresponding to the corresponding pixel.

Optionally, after the first image is obtained, median filtering may be performed on the first image to obtain a processed second image.

For example, performing median filtering processing on the first image may be performing median filtering processing on each pixel in the first image. Median filtering is a nonlinear signal processing technology that can effectively suppress noise based on sorting statistics theory. Its basic principle is to use the value of a point in a digital image or digital sequence as the median value of each point in a neighborhood of the point. Instead, let the surrounding pixel values close to the true value, thereby eliminating isolated noise points. In the embodiment of the present invention, because the pixels in the first image are relatively few in the vertical direction, the effect of its processing is not obvious enough, so in the present invention, the data can be filtered in a horizontal manner to improve the performance of the air conditioner. Processing efficiency.

Optionally, the process of S12 may be: perform median filter processing on the n pixels contained in the first image according to the filter template to obtain the second image; wherein, each pixel in the n pixels contained in the first image The point corresponds to the initial temperature value (that is, the temperature value collected by the infrared sensor array), and each pixel point in the n pixels contained in the second image corresponds to the filtered temperature value.

When performing median filtering, the filter template used can be a changing one-dimensional sliding template, and the length range of the filter window corresponding to the filter template can be the length of the area occupied by [3, 21] pixels, and the width is The width of the area occupied by 1 pixel, that is, in the process of filtering the pixel, the filter template can be 1*3 (that is, the width of the filter window corresponding to the filter template is the width of the area occupied by a pixel, and the length is the length of the area occupied by 3 pixels, which is expressed in the following similar expressions in this paper) gradually changes to a one-dimensional sliding template of 1*21, and the change is that every time a pixel is processed, the length of the corresponding filtering window will be Increase the length of the area occupied by two pixels, that is, when calculating the median value for the first time, use a 1*3 filter module; when calculating the median value for the second time, use a filter module of 1*5; When calculating the median, use the filter template of 1*7, ..., and so on.

For example, for a group of pixels with a size of 4*16 (that is, 4 rows and 16 columns) in the first image, the filter temperature value corresponding to the j-th pixel in the i-th row of the 4 rows is the i-th The initial temperature value of the pixel in the middle position in the filter window formed by the 1st pixel to the 2j+1th pixel in the row, that is, in the above algorithm, the j+1th pixel in the i-th row The initial temperature value corresponding to the point is determined as the filtered temperature value of the jth pixel point after filtering, i takes an integer from 1 to 4 in turn, and j takes an integer from 1 to 16 in turn.

As shown in Figure 4, it is a schematic diagram of performing median filtering on a row of pixels in the image according to the filter template. In the figure, the filter template of pixel 1 at the first position of the row is 1*3, and its corresponding filter The resulting temperature value is the temperature value corresponding to the pixel located in the middle of the filter template, that is, 27.86. Similarly, the filter template of pixel 2 located in the second position is 1*5, and the corresponding filtered temperature value is is the temperature value of the pixel at the middle position in the filtering template, that is, 27.93. Similarly, the filtered temperature value corresponding to pixel 3 at the third position is 27.96.

It should be noted that in practical applications, the first image corresponds to many pixels. When performing median filtering on the first image according to the above method, the filtering process is performed from both sides of the first image to the middle. For In terms of pixels, that is, the two pixels located at the end points of each row (that is, the pixel at the first position and the pixel at the last position of the row) are respectively used as the starting point, and the pixels at the middle position are moved one by one Median filtering is performed in an efficient manner. Of course, the length of the filtering window corresponding to the corresponding filtering template is also gradually extended from both sides to the middle.

Since the maximum range of the filter template is 1*21, that is, the pixel points 10 arranged at the tenth position in each row will reach the maximum length of the corresponding filter window, that is, the length of the area occupied by 21 pixel points, then, in the pair arranged in When the pixel point 11 at the eleventh position is subjected to median filtering, it is still processed according to the filter template of 1*21. At this time, although the size of the filter template of pixel point 11 is the same as that of pixel point 10, the The positions are different, the starting point of the filter template of pixel 11 is pixel 2 located in the second position in the corresponding row, the end point is pixel 22, and the corresponding filter templates of pixel 10 and pixels before pixel 10 are respectively The starting point of is pixel 1. Therefore, in the embodiment of the present invention, it can be considered that when the length of the filter window of the filter template corresponding to the processed pixel reaches the maximum length, the length of the filter window corresponding to other pixels after the pixel remains unchanged , but its position will be shifted, that is, every time a pixel is processed later, the starting position of the filter window will be moved back by one position from the first position of the row, thus completing the processing of n pixels.

Therefore, each of the n pixel points contained in the second image obtained by performing median filtering on the n pixel points contained in the first image may correspond to a filtered temperature value.

Optionally, the process of S13 may include: according to the corresponding relationship between the pixels in the first image and the second image, respectively obtain each of the n initial temperature values and the corresponding filter temperature among the n filter temperature values value, and determine the relevant information of the user in the first environment according to the r difference values greater than or equal to the preset threshold among the obtained n difference values.

Wherein, the preset threshold may be set in the air conditioner at the factory. In the embodiment of the present invention, the preset threshold may be 1°, 1.5°, or the like.

Since the user's body temperature is usually higher than the ambient temperature, the initial temperature values corresponding to the n pixels in the first image include the temperature values corresponding to the human body and the temperature values corresponding to the environment, and the first image obtained through median filtering The filtered temperature values corresponding to n pixels in the two images are relatively similar, so the difference corresponding to each pixel can be determined according to the temperature value of each pixel before and after median filtering. For example, for a certain pixel, its corresponding initial temperature value in the first image (ie before median filtering) is 28.26, and in the second image (ie after median filtering) the corresponding initial temperature is 28.37, then , and the corresponding difference is 28.26-28.37=-0.11.

After obtaining n difference values corresponding to n pixels, r difference values greater than a preset threshold can be determined, and the r pixels corresponding to the r difference values are the pixels corresponding to the user.

Optionally, after obtaining the r differences, the positions of the r pixels corresponding to the r temperature differences in the first image or the second image can also be determined, and the position of the r pixels in the first environment can be determined according to the positions of the r pixels. The number of users and the distance between users, and/or, according to the correspondence between temperature and distance and the r initial temperature values corresponding to r pixel points, determine the distance between the user and the air conditioner.

As shown in FIG. 5 , it is the pixel corresponding to the first image. " " in the figure represents a pixel whose median difference is less than a preset threshold, and "-" represents a pixel whose difference is greater than a preset threshold. Then the area where "-" is located is the area where the user is located in the first environment. It can be seen from FIG. 5 that the first environment includes 2 users, and the distance between the 2 users can also be determined according to the pixel points.

Further, the distance between the user and the air conditioner can be calculated according to the correspondence between temperature and distance, and the temperature values corresponding to r pixels. The specific calculation method is the same as the existing method, and will not be repeated here.

In the embodiment of the present invention, in the process of performing median filtering on the first image, a changed filtering template is used to avoid the need to add additional pixels to match the median filtering in the original median filtering method, and the calculation time is reduced. It only takes 0.5 seconds, which greatly speeds up the calculation speed, so that the pixels related to the user can be quickly distinguished, which makes the air-conditioning equipment more efficient, realizes the intelligence of the air-conditioning equipment, and improves the user experience.

As shown in FIG. 6 , the embodiment of the present invention also discloses an air conditioner, which includes: an acquisition module 301 , a processing module 302 and a determination module 303 .

The acquisition module 301 may be configured to scan a first environment where the air conditioner is located through an infrared sensor array in the air conditioner, and obtain a first image corresponding to the first environment;

The processing module 302 may be configured to perform median filtering processing on the first image to obtain a second image corresponding to the first image;

The determining module 303 may be configured to determine relevant information of users in the first environment according to the first image and the second image.

Optionally, the length of the filtering window corresponding to the filtering template used in the median filtering process is the length of the area occupied by [3, 21] pixels, and the width is the width of the area occupied by 1 pixel.

Optionally, the processing module 302 may also be configured to: perform median filtering processing on the n pixels contained in the first image according to the filtering template to obtain the second image; wherein, the first Each of the n pixels included in the image corresponds to an initial temperature value, and each of the n pixels included in the second image corresponds to a filtered temperature value.

Optionally, the determining module 303 may be used to:

According to the corresponding relationship between the pixel points in the first image and the second image, the relationship between each initial temperature value in the n initial temperature values and the corresponding filtered temperature value in the n filtered temperature values is respectively obtained. difference;

Determine the relevant information of the user in the first environment according to r difference values greater than or equal to a preset threshold among the obtained n difference values.

Optionally, the determining module 303 may be configured to: determine the positions of r pixels corresponding to the r temperature differences in the first image or the second image, according to the position of the r pixels Determine the number of users in the first environment and the distance between users, and/or, according to the correspondence between temperature and distance and the r initial temperature values corresponding to the r pixel points, determine the The distance between the user and the air conditioner.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and equivalent technologies thereof, the present invention also intends to include these modifications and variations.

Claims (10)

1. A user identification method, characterized in that the method comprises: Scanning a first environment where the air conditioner is located by using an infrared sensor array in the air conditioner to obtain a first image corresponding to the first environment; performing median filtering processing on the first image to obtain a second image corresponding to the first image; Relevant information of users in the first environment is determined according to the first image and the second image. 2. The method according to claim 1, wherein the length range of the filter window corresponding to the filter template used in the median filtering process is the length of the area occupied by [3, 21] pixels, and the width is The width of the area occupied by 1 pixel. 3. The method according to claim 2, wherein performing median filtering on the first image to obtain a second image corresponding to the first image comprises: Perform median filter processing on the n pixels included in the first image according to the filter template to obtain the second image; wherein, each pixel in the n pixels included in the first image The point corresponds to the initial temperature value, and each pixel point in the n pixel points included in the second image corresponds to the filtered temperature value. 4. The method according to claim 3, wherein determining relevant information of users in the first environment according to the first image and the second image comprises: According to the corresponding relationship between the pixel points in the first image and the second image, the relationship between each initial temperature value in the n initial temperature values and the corresponding filtered temperature value in the n filtered temperature values is respectively obtained. difference; Determine the relevant information of the user in the first environment according to r difference values greater than or equal to a preset threshold among the obtained n difference values. 5. The method according to claim 4, characterized in that determining the relevant information of the user in the first environment according to the r difference values greater than or equal to a preset threshold among the obtained n difference values comprises: determining the positions of r pixels corresponding to the r temperature differences in the first image or the second image, and determining the number and number of users in the first environment according to the positions of the r pixels distance between users; and/or The distance between the user and the air conditioner is determined according to the correspondence between the temperature and the distance and the r initial temperature values corresponding to the r pixel points. 6. An air conditioner, characterized in that the air conditioner comprises: An acquisition module, configured to scan a first environment where the air conditioner is located through an infrared sensor array in the air conditioner, and obtain a first image corresponding to the first environment; A processing module, configured to perform median filtering processing on the first image to obtain a second image corresponding to the first image; A determining module, configured to determine relevant information of users in the first environment according to the first image and the second image. 7. The air conditioner according to claim 6, wherein the length range of the filter window corresponding to the filter template used in the median filter process is the length and width of the area occupied by [3, 21] pixels. It is the width of the area occupied by 1 pixel. 8. The air conditioner according to claim 7, wherein the processing module is used for: Perform median filter processing on the n pixels included in the first image according to the filter template to obtain the second image; wherein, each pixel in the n pixels included in the first image The point corresponds to the initial temperature value, and each pixel point in the n pixel points included in the second image corresponds to the filtered temperature value. 9. The air conditioner according to claim 8, wherein the determination module is used for: According to the corresponding relationship between the pixel points in the first image and the second image, the relationship between each initial temperature value in the n initial temperature values and the corresponding filtered temperature value in the n filtered temperature values is respectively obtained. difference; Determine the relevant information of the user in the first environment according to r difference values greater than or equal to a preset threshold among the obtained n difference values. 10. The air conditioner according to claim 9, wherein the determination module is used for: determining the positions of r pixels corresponding to the r temperature differences in the first image or the second image, and determining the number and number of users in the first environment according to the positions of the r pixels distance between users; and/or The distance between the user and the air conditioner is determined according to the correspondence between the temperature and the distance and the r initial temperature values corresponding to the r pixel points.