Self-adaptive proximity sensing method, full-screen building terminal and storage medium

Abstract

The invention relates to a self-adaptive proximity sensing method, a full-screen building terminal and a storage medium, and the method comprises the following steps: under the condition that no object approaches, the following steps are executed at set intervals: obtaining external environment parameters, analyzing the external environment parameters, dynamically generating parameters in a smoothing algorithm according to the analysis result of the external environment parameters, and outputting the parameters in the smoothing algorithm; a dynamically adjusted smoothing algorithm is obtained; predicting a preset number of ADC values at a future moment; smoothing a preset number of ADC values through the dynamically adjusted smoothing algorithm to obtain a smoothed ADC value array, and dynamically generating an induction trigger threshold through the smoothed ADC value array; and performing infrared induction monitoring according to the dynamically generated induction triggering threshold.

Description

Technical Field

[0001] The present invention relates to the field of adaptive proximity sensing, and in particular to an adaptive proximity sensing method, a full-screen building terminal, and a storage medium. Background Art

[0002] With the continuous development of science and technology, the use of smart home devices is becoming more and more widespread. Infrared proximity sensors are common devices in smart control panels, which are used to wake up the device when an object approaches. For example, when a person approaches the smart control panel, the smart control panel automatically wakes up and starts face recognition. The working principle of infrared proximity sensing is that an infrared transmitter emits infrared light pulses, which are reflected back to the proximity sensing receiver after encountering an object. The proximity sensing converts the received energy into an ADC value. The device sets the ADC trigger threshold and reads the ADC value collected by the proximity sensing to judge the approach (greater than the threshold) and distance (less than the threshold) events. However, in the actual use test process, it was found that due to different PCB plate making and material batches, or during the use of the equipment, or changes in the equipment use environment, the ADC values ​​collected by the proximity sensing are quite different, which leads to the failure of the proximity sensing function or inaccurate triggering.

[0003] In order to dynamically adjust the sensing trigger threshold of the infrared distance sensor, the prior art dynamically adjusts the sensing trigger threshold of the next moment through the changes in the ADC value corresponding to the infrared signal received by the infrared distance sensor in one or more sensing cycles. For example, the prior application with the publication number CN114296146A adjusts the sensing trigger threshold through the action that has occurred, and assumes that the surrounding environment is basically unchanged; or the prior art adjusts the sensitivity of the infrared distance sensor through temperature, dust, etc., so as to obtain a dynamic trigger threshold. However, the infrared distance sensor is not only simply affected by environmental factors such as temperature and dust, and human movements, but also by the refraction, reflection, diffuse reflection, etc. of the infrared signal emitted by the infrared distance sensor by the external environment. At the same time, there are also complex interference factors in the external environment, which ultimately leads to the prior art's setting of the dynamic trigger threshold being prone to misjudgment.

[0004] The purpose of the present invention is to design an adaptive proximity sensing method, a full-screen building terminal, and a storage medium in view of the problems existing in the above-mentioned prior art. Summary of the invention

[0005] In view of the problems existing in the above-mentioned prior art, the present invention provides an adaptive proximity sensing method, a full-screen building terminal, and a storage medium, which can effectively solve at least one problem existing in the above-mentioned prior art.

[0006] The technical solution of the present invention is: An adaptive proximity sensing method comprises the following steps: performing at intervals when no object is approaching: Acquiring external environment parameters, analyzing the external environment parameters, dynamically generating parameters in a smoothing algorithm according to the analysis results of the external environment parameters, and obtaining a dynamically adjusted smoothing algorithm; Predict a preset number of ADC values ​​at future moments; Smoothing a preset number of ADC values ​​by using the dynamically adjusted smoothing algorithm to obtain a smoothed ADC value array, and dynamically generating a sensing trigger threshold by using the smoothed ADC value array; Infrared sensing monitoring is performed based on dynamically generated sensing trigger thresholds.

[0007] Furthermore, the external environment parameters include the temperature of the infrared ranging unit, obstacle parameters around the infrared ranging unit, and light parameters.

[0008] Further, analyzing the external environment parameters includes: Analyze the size, color, position, and dynamic change interval of obstacles around the infrared ranging unit; Analyze the illumination angle and illumination intensity of the light around the infrared ranging unit.

[0009] Furthermore, image data is obtained by a camera mechanism, and image analysis is performed on the image data to obtain the size, color, position, dynamic change interval, and illumination angle and illumination intensity of the obstacle.

[0010] Furthermore, the smoothing algorithm is X[i]=a*V+(1-a)*X[i-1], wherein X[i] represents the i-th value in the smoothed infrared signal group, a is the weight, and V is the ADC value corresponding to the infrared signal currently returned.

[0011] Furthermore, the parameters in the smoothing algorithm are dynamically generated according to the analysis results of the external environment parameters, and the dynamically adjusted smoothing algorithm includes: Collect the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the illumination angle, light intensity, and the ADC value generated by the infrared ranging unit when no object is approaching, build a sample training set, use the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the light angle, and light intensity as inputs of the prediction model, use the ADC value generated by the infrared ranging unit when no object is approaching as output of the prediction model, and train the prediction model to obtain an ADC value prediction model; Predicting several ADC values ​​in a future time period by using the ADC value prediction model according to the current external environment parameters; The variance of several ADC values ​​in a future time period is calculated, and the weight a in the smoothing algorithm is adjusted according to the variance.

[0012] Furthermore, the variance and the weight a are negatively correlated.

[0013] Furthermore, dynamically generating the sensing trigger threshold of the infrared ranging unit through the smoothed ADC value array includes: The sensing trigger threshold T is generated by T=(S / N)+D, where S is the sum of the ADC values ​​of the smoothed ADC value array, N is the number of values ​​in the smoothed ADC value array, and D is the ADC value corresponding to the preset proximity sensing trigger distance.

[0014] A full-screen building terminal is further provided, which implements the adaptive proximity sensing method when in operation.

[0015] A computer-readable storage medium is further provided, storing a computer program, wherein the computer program implements the adaptive proximity sensing method when executed by a processor.

[0016] Therefore, the present invention provides the following effects and / or advantages: The present application changes the prior art method of performing sensing trigger threshold based on the past moment, and optimizes it to predict the ADC value at the future moment according to the environmental parameters, so that the parameters of the smoothing algorithm can be output according to the ADC value array at the future moment, and then the statistics of the ADC value array at the future moment, and finally the smoothed ADC value array is used to calculate the sensing trigger threshold. The sensing trigger threshold obtained can be dynamically adjusted according to the changing trend of the environment, which greatly improves the recognition accuracy of proximity sensing.

[0017] The external environmental parameters of the present application include the temperature of the infrared ranging unit, the size, color, position, and dynamic change interval of the obstacles around the infrared ranging unit; the illumination angle and light intensity of the light around the infrared ranging unit are analyzed, and a training set is constructed by different changes of these parameters, so as to train the prediction algorithm to obtain an ADC value prediction model, which can output the ADC value in the future period of time according to the changes in the current environment.

[0018] This application dynamically outputs the weight parameters of the smoothing algorithm according to the ADC value in the future, so as to match the smoothing effect of the corresponding effect according to different situations.

[0019] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0020] It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart diagram of one embodiment of the present invention is provided.

[0022] Figure 2 This is a graph showing several ADC values ​​predicted by the method at future moments, the ADC values ​​calculated by the smoothing algorithm, and the calculated induction trigger threshold. DETAILED DESCRIPTION

[0023] In order to facilitate understanding by those skilled in the art, the present invention is now described in further detail by way of examples: refer to Figure 1 , an adaptive proximity sensing method, comprising the following steps: when no object is approaching, performing at intervals: S1, obtaining external environment parameters, analyzing the external environment parameters, dynamically generating parameters in a smoothing algorithm according to the analysis results of the external environment parameters, and obtaining a dynamically adjusted smoothing algorithm; S2, predicting the ADC value of a preset number of future moments; S3, smoothing a preset number of ADC values ​​by using the dynamically adjusted smoothing algorithm to obtain a smoothed ADC value array, and dynamically generating a sensing trigger threshold by using the smoothed ADC value array; S4, performing infrared sensing monitoring according to the dynamically generated sensing trigger threshold.

[0024] The ADC value is a prior art and can be calculated from the returned infrared signal obtained by the infrared ranging sensor. The larger the ADC value, the stronger the returned infrared signal. When an object or a person gradually approaches the infrared ranging unit, the ADC value will gradually increase. When the ADC value is greater than a preset threshold, the control system can determine that there is an object or a person in front of the infrared ranging unit.

[0025] In this embodiment, the ADC value used to calculate the sensing trigger threshold is the ADC value at a future moment. Therefore, when used for infrared sensing monitoring, it is possible to predict in advance the impact of future external changes on the ADC value and generate a corresponding sensing trigger threshold based on the future situation.

[0026] When there is no object approaching, after the infrared ranging unit sends out an infrared signal, obstacles in front of or around the infrared ranging unit (such as buildings, trees, grass, cars, doors, etc.) will reflect and scatter the infrared signal, and eventually a small amount of infrared signal will return to the infrared ranging unit, thereby calculating the corresponding ADC value. When the external environment changes, it will interfere with the infrared signal returning to the infrared ranging unit, generate noise, etc., and will also interfere with the detection sensitivity of the infrared ranging unit, or when the external environment fluctuates (such as wind blowing trees, grass, etc.), it will cause large fluctuations in the returned infrared signal. When an object or a human body approaches the infrared ranging unit, the infrared signal received by the infrared ranging unit is a superposition of the infrared signal reflected by the human body and the infrared signal reflected and scattered by the environment, which will cause the infrared signal received by the infrared ranging unit to fluctuate over a large range when the position of the human body or object in front of the infrared ranging unit is fixed.

[0027] If a fixed ADC trigger threshold is set, the trigger threshold may not be reached when a person or object approaches the infrared ranging unit, or the trigger threshold may be reached before the person or object approaches the infrared ranging unit, resulting in misjudgment. To avoid this, most of the existing technologies for adjusting the induction trigger threshold are based on the influence of external temperature, dust, etc., which are not suitable for the above complex situations.

[0028] The present application obtains and analyzes the external environment parameters to obtain the complex situation in the external environment. The complex situation can simply predict the impact of the external environment on the returned infrared signal, thereby inferring the change of the infrared signal returned by the external environment in the future, and dynamically generating the parameters in the smoothing algorithm according to the analysis results of the external environment parameters. Correspondingly, when the external environment will cause a large change in the returned infrared signal, the smoothing effect in the smoothing algorithm can be enhanced to reduce the fluctuation of the infrared signal. Conversely, the smoothing effect in the smoothing algorithm can be reduced to make the fluctuation of the infrared signal more obvious.

[0029] Therefore, the sensing trigger threshold of the infrared ranging unit can be dynamically generated through the smoothed ADC value array, and the sensing trigger threshold and the smoothed infrared signal can be more closely matched.

[0030] Furthermore, the external environment parameters include the temperature of the infrared ranging unit, obstacle parameters around the infrared ranging unit, and light parameters.

[0031] Further, analyzing the external environment parameters includes: Analyze the size, color, position, and dynamic change interval of obstacles around the infrared ranging unit; Analyze the illumination angle and illumination intensity of the light around the infrared ranging unit.

[0032] In this embodiment, the temperature change on the surface of an object will affect the intensity of its infrared radiation. As the temperature rises, the infrared signal radiated by the object increases, which may cause the ADC value to increase. The larger the obstacle, the more infrared signals reflected by the object, which may cause the ADC value to increase. The lighter the color of the obstacle, the more infrared signals reflected by the object, which may cause the ADC value to increase. The closer the obstacle is to the infrared ranging unit, the more infrared signals it reflects, which may cause the ADC value to increase. The larger the dynamic change range of the object, such as the swaying of trees, the more violent the swaying, the greater the fluctuation of the reflected infrared signal, which may cause the ADC value to fluctuate greatly. The greater the external light intensity, the different illumination angles for the sensor, and the sensor may be affected by the ambient light intensity. Strong light, especially light sources containing infrared bands, may interfere with the sensor's detection of the target. Therefore, this embodiment obtains these environmental data for subsequent calculations.

[0033] Furthermore, image data is obtained by a camera mechanism, and image analysis is performed on the image data to obtain the size, color, position, dynamic change interval, and illumination angle and illumination intensity of the obstacle.

[0034] In this embodiment, for example, building access control systems, most of which are equipped with infrared ranging units and camera mechanisms. Therefore, in this embodiment, without adding other sensors, the camera mechanism obtains image data for calculating the size, color, position, dynamic change interval of the obstacle and the angle of illumination and light intensity. Specifically, various objects in the image can be identified through computer vision and image processing, and then the size and position of other objects can be estimated based on the parameters such as the contour area and contour perimeter of the object in the image and the size of the known reference object. Then, according to the size and position of the obstacle, the position of the object in the continuous frames is tracked by using the optical flow method, Kalman filtering, Hungarian algorithm (for multi-target tracking), etc. for the obstacles in multiple images, and then the difference between the images is calculated by frame difference to determine whether the object is moving, as well as the direction and amplitude of the movement, so as to obtain the change interval of the obstacle. The angle of illumination of the light can be obtained from the light and shadow changes in multiple images, and the light intensity can be obtained by calculating the evaluation brightness of the image.

[0035] Furthermore, the smoothing algorithm is X[i]=a*V+(1-a)*X[i-1], wherein X[i] represents the i-th value in the smoothed infrared signal group, a is the weight, and V is the ADC value corresponding to the infrared signal currently returned.

[0036] In this embodiment, X[i-1] is the ADC value after smoothing at the last moment. For example, the ADC value after smoothing at the last moment is 401, the ADC value corresponding to the infrared signal currently returned is 415, and the weight a is set to 0.3, then X[i]=405.2.

[0037] Through this algorithm, ADC data can be smoothed, and the smaller the value of the weight a is, the better the smoothing effect of the smoothing algorithm is.

[0038] Furthermore, the parameters in the smoothing algorithm are dynamically generated according to the analysis results of the external environment parameters, and the dynamically adjusted smoothing algorithm includes: Collect the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the illumination angle, light intensity, and the ADC value generated by the infrared ranging unit when no object is approaching, build a sample training set, use the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the light angle, and light intensity as inputs of the prediction model, use the ADC value generated by the infrared ranging unit when no object is approaching as output of the prediction model, and train the prediction model to obtain an ADC value prediction model; Predicting several ADC values ​​in a future time period by using the ADC value prediction model according to the current external environment parameters; The variance of several ADC values ​​in a future time period is calculated, and the weight a in the smoothing algorithm is adjusted according to the variance.

[0039] In this embodiment, the prediction model can be an existing neural network model. By training it, the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of obstacles, as well as the light angle, light intensity, and the potential relationship between the ADC value can be extracted, so as to calculate the ADC value in the future period according to the specific external environmental parameters in the current situation. Then, through the variance of several ADC values ​​at future moments, the variance can reflect the fluctuation of the ADC value at future moments. The greater the magnification, the greater the fluctuation of the ADC value. At this time, the smoothing algorithm is required to calculate these ADC values ​​more smoothly to prevent the ADC value from fluctuating violently so that the calculated induction trigger threshold cannot match the situation.

[0040] Furthermore, the variance and the weight a are negatively correlated.

[0041] The formula of the smoothing algorithm is introduced above, where the smaller the weight a is, the smaller the change of the smoothed ADC value array is, which is suitable for the case of large fluctuations in ADC values. In this embodiment, the weight a can be a value between 0.01 and 0.3, and the weight can be calculated according to the following formula: Weight a = maximum weight - (current variance / preset maximum variance) * maximum weight.

[0042] Furthermore, dynamically generating the sensing trigger threshold of the infrared ranging unit through the smoothed ADC value array includes: The sensing trigger threshold T is generated by T=(S / N)+D, where S is the sum of the ADC values ​​of the smoothed ADC value array, N is the number of values ​​in the smoothed ADC value array, and D is the ADC value corresponding to the preset proximity sensing trigger distance.

[0043] In the above calculation, the smoothed ADC value array is obtained. At this time, the average value of the smoothed ADC value array is calculated. The average value can be considered as the average ADC value of the infrared signal received by the infrared ranging sensor in the future period of time when no object or human body is close to or standing in front of the infrared ranging sensor. After superimposing the ADC value corresponding to the preset proximity sensing trigger distance, it can be used as the sensing trigger threshold.

[0044] refer to Figure 2 , under certain external environment conditions, predict the ADC value at the future time as follows Figure 2 As shown in the blue curve with the horizontal axis of 1-100, the variance of these data is 259.29. The preset maximum variance is set to 600, and the weight a=0.3-(current variance / preset maximum variance)*0.3=0.17. The smoothed ADC value calculated based on the weight a=0.17 is as follows Figure 2 As shown in the red curve with the horizontal axis of 1-100, the calculated S / N=395, D is set to 60, and the induction trigger threshold is 455. Next, at the next moment, the ADC value of the future moment is predicted according to a certain external environment. Figure 2 As shown in the blue curve with the horizontal axis of 101-199, the variance of these data is 384.6. It can be seen that the fluctuation of these ADC values ​​is more obvious and the values ​​are larger. Therefore, a smoother smoothing algorithm is needed. The preset maximum variance is set to 600, and the weight a=0.3-(current variance / preset maximum variance)*0.3=0.11. The smoothed ADC value calculated according to the weight a=0.11 is as follows Figure 2 As shown in the red curve with the horizontal axis of 101-199, the calculated S / N=418, D is set to 60, and the induction trigger threshold is 478.

[0045] Through the method provided in this embodiment, infrared sensing monitoring is performed according to the dynamically generated sensing trigger threshold, and the detection rate of judging the approach of a human body under different external environments reaches more than 99.3%.

[0046] A full-screen building terminal is further provided, which implements the adaptive proximity sensing method when in operation.

[0047] In this embodiment, the full-screen building terminal is provided with a camera and an infrared ranging sensor.

[0048] A computer-readable storage medium is further provided, storing a computer program, wherein the computer program implements the adaptive proximity sensing method when executed by a processor.

[0049] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0051] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0052] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0053] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms should not be understood as necessarily being directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

Claims

1. An adaptive proximity sensing method, characterized in that: The following steps are involved: When no object is approaching, execute the following at regular intervals: Acquiring external environment parameters, analyzing the external environment parameters, dynamically generating parameters in a smoothing algorithm according to the analysis results of the external environment parameters, and obtaining a dynamically adjusted smoothing algorithm; Predict a preset number of ADC values ​​at future moments; Smoothing a preset number of ADC values ​​by using the dynamically adjusted smoothing algorithm to obtain a smoothed ADC value array, and dynamically generating a sensing trigger threshold by using the smoothed ADC value array; Infrared sensing monitoring is performed based on dynamically generated sensing trigger thresholds.

2. The adaptive proximity sensing method according to claim 1, characterized in that: The external environment parameters include the temperature of the infrared ranging unit, obstacle parameters around the infrared ranging unit, and light parameters.

3. The adaptive proximity sensing method according to claim 2, characterized in that: Analyzing the external environment parameters includes: Analyze the size, color, position, and dynamic change interval of obstacles around the infrared ranging unit; Analyze the illumination angle and illumination intensity of the light around the infrared ranging unit.

4. The adaptive proximity sensing method according to claim 3, characterized in that: The image data is obtained by a camera mechanism, and image analysis is performed on the image data to obtain the size, color, position, dynamic change range, and illumination angle and illumination intensity of the obstacle.

5. The adaptive proximity sensing method according to claim 3, characterized in that: The smoothing algorithm is X[i]=a*V+(1-a)*X[i-1], where X[i] represents the i-th value in the smoothed infrared signal group, a is the weight, and V is the ADC value corresponding to the infrared signal currently returned.

6. The adaptive proximity sensing method according to claim 5, characterized in that: Dynamically generating parameters in the smoothing algorithm according to the analysis results of the external environment parameters, and obtaining the dynamically adjusted smoothing algorithm includes: Collect the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the illumination angle, light intensity, and the ADC value generated by the infrared ranging unit when no object is approaching, build a sample training set, use the temperature under different conditions, as well as the size, color, position, dynamic change interval and light of the obstacle, as well as the light angle, and light intensity as inputs of the prediction model, use the ADC value generated by the infrared ranging unit when no object is approaching as output of the prediction model, and train the prediction model to obtain an ADC value prediction model; Predicting several ADC values ​​in a future time period by using the ADC value prediction model according to the current external environment parameters; The variance of several ADC values ​​in a future time period is calculated, and the weight a in the smoothing algorithm is adjusted according to the variance.

7. The adaptive proximity sensing method according to claim 6, characterized in that: The variance and the weight a are negatively correlated.

8. The adaptive proximity sensing method according to claim 1, characterized in that: Dynamically generating the sensing trigger threshold of the infrared ranging unit by using the smoothed ADC value array includes: The sensing trigger threshold T is generated by T=(S / N)+D, where S is the sum of the ADC values ​​of the smoothed ADC value array, N is the number of values ​​in the smoothed ADC value array, and D is the ADC value corresponding to the preset proximity sensing trigger distance.

9. A full-screen building terminal, characterized in that: When working, an adaptive proximity sensing method as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, an adaptive proximity sensing method according to any one of claims 1 to 8 is implemented.

Images