Air conditioner and air conditioner infrared target detection result stability enhancement method

Abstract

The application discloses an air conditioner and an air conditioner infrared target detection result stability enhancement method. The air conditioner comprises a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter and a controller. The controller is configured to: when the infrared image is detected as having a target, performing weighting processing on the cache frame weight based on a first count value, and outputting a target detection result and a target position coordinate. The first count value is the cumulative number of continuous detected frames of the infrared image. When the infrared image is detected as having no target and the infrared image is previously detected as having a target, outputting the target detection result and the target position coordinate based on a second counter. The second count value is the cumulative number of continuous undetected frames of the infrared image. The method realizes correction of the detected target according to the cache frame weight, improves the accuracy and stability of the detected target result, and improves the user experience.

Description

Technical Field

[0001] This application relates to the field of air conditioner technology, and more specifically, to an air conditioner and a method for enhancing the stability of infrared target detection results of an air conditioner. Background Technology

[0002] Object detection is a popular area in computer vision and digital image processing. It involves finding all objects of interest in an image, encompassing two sub-tasks: object localization and object classification, while simultaneously determining the object's category and location. Infrared thermopile sensors are frequently used in various electronic devices and home appliances to perform product applications in object detection, such as acquiring temperature data, protecting user privacy, and detecting relevant human heat source areas, facial regions, and other body parts.

[0003] Currently, infrared thermopile sensors generally produce thermal image arrays with low resolution and poor image contrast. They are also highly susceptible to interference from hot air and other heat sources, resulting in low frame rates for image acquisition. Due to these inherent limitations of infrared thermopile sensors and the generally limited processing power of processors within home appliances, their target detection rates are low, failing to achieve the high-quality results of high-definition devices like cameras. Consequently, when displaying real-time frames, issues such as intermittent target marking, inaccurate target marking positions, and marking delays occur, severely impacting the user's visual experience. Furthermore, the controller at the product's main control unit processes infrared images with instability, hindering software logic design and leading to poor product performance.

[0004] Therefore, how to provide a method to enhance the stability of air conditioner and infrared target detection results to improve the stability of target detection results is a technical problem that needs to be solved. Summary of the Invention

[0005] This invention provides an air conditioner to solve the technical problem of unstable and inaccurate target detection results in existing air conditioners.

[0006] The air conditioner includes:

[0007] The refrigerant circulation loop allows the refrigerant to circulate within a loop consisting of the compressor, condenser, expansion valve, and evaporator.

[0008] An outdoor heat exchanger and an indoor heat exchanger, one of which functions as a condenser and the other as an evaporator;

[0009] An infrared thermopile sensor is used to acquire infrared lumen value data and to acquire infrared images based on the lumen value data;

[0010] A detection frame counter is used to acquire a first count value, wherein the first count value is the cumulative number of consecutively detected frames of the infrared image;

[0011] A non-detected frame counter is used to obtain a second count value, which is the cumulative number of consecutive non-detected frames in the infrared image;

[0012] The controller is configured as follows:

[0013] When the infrared image detects a target, the weight of the cached frame is weighted based on the first count value, and the target detection result and target position coordinates are output.

[0014] When the infrared image detects no target and the infrared image previously showed a target, the target detection result and target location coordinates are output based on the second count value.

[0015] In some embodiments of this application, the controller is specifically configured as follows:

[0016] When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold.

[0017] If so, output the target detection result as "detected" and output the target's location coordinates;

[0018] If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

[0019] In some embodiments of this application, the controller is specifically configured as follows:

[0020] When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold.

[0021] If so, the output result will be "None", and the target position coordinates will be set to 0.

[0022] In some embodiments of this application, the controller is specifically configured as follows:

[0023] When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:1.

[0024] When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

[0025] In some embodiments of this application, the detection result of the current frame is specifically determined by the following formula:

[0026] The detection result obtained from the current frame = current frame * current frame weight + cached frame * cached frame weight.

[0027] Accordingly, this invention also proposes a method for enhancing the stability of infrared target detection results in air conditioners, applicable to air conditioners including a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter, and a controller. The method includes:

[0028] When the infrared image detects a target, the weight of the cached frames is weighted based on the first count value, and the target detection result and target position coordinates are output. The first count value is the cumulative number of consecutively detected frames of the infrared image.

[0029] When the infrared image detects no target and the infrared image previously showed a target, the target detection result and target location coordinates are output based on the second count value, where the second count value is the cumulative number of consecutive undetected frames in the infrared image.

[0030] In some embodiments of this application, the weights of the cached frames are weighted based on the first count value, and the target detection result and target location coordinates are output, specifically as follows:

[0031] When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold.

[0032] If so, output the target detection result as "detected" and output the target's location coordinates;

[0033] If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

[0034] In some embodiments of this application, the target detection result and target position coordinates are output based on the second count value, specifically as follows:

[0035] When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold.

[0036] If so, the output result will be "None", and the target position coordinates will be set to 0.

[0037] In some embodiments of this application, the weights of the cached frames are weighted, specifically as follows:

[0038] When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:1.

[0039] When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

[0040] In some embodiments of this application, the detection result of the current frame is specifically determined by the following formula:

[0041] The detection result obtained from the current frame = current frame * current frame weight + cached frame * cached frame weight.

[0042] By applying the above technical solutions, in an air conditioner including a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter, and a controller, the controller is configured to: when the infrared image detects a target, perform weighted processing on the cached frame weights based on a first count value, and output the target detection result and target position coordinates, where the first count value is the cumulative number of consecutive detected frames of the infrared image; when the infrared image detects no target and the infrared image previously showed a target, output the target detection result and target position coordinates based on a second count value, where the second count value is the cumulative number of consecutive undetected frames of the infrared image, thereby realizing target correction based on cached frame weights, improving the accuracy and stability of target detection results, and enhancing the user experience. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A schematic diagram of the structure of an air conditioner according to an embodiment of the present invention is shown;

[0045] Figure 2 This diagram illustrates the function of a first count value according to an embodiment of the present invention.

[0046] Figure 3 This diagram illustrates the function of a second count value according to an embodiment of the present invention.

[0047] Figure 4 The diagram shows a flowchart of a method for enhancing the stability of infrared target detection results in an air conditioner, as proposed in an embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0050] In this application, the air conditioner performs a refrigeration cycle by using a compressor, condenser, expansion valve, and evaporator. The refrigeration cycle includes a series of processes involving compression, condensation, expansion, and evaporation, and supplies refrigerant to the conditioned and heat-exchanged air.

[0051] The compressor compresses the refrigerant gas under high temperature and high pressure and discharges the compressed refrigerant gas. The discharged refrigerant gas flows into the condenser, where the condenser condenses the compressed refrigerant into a liquid phase, and the heat is released to the surrounding environment through the condensation process.

[0052] The expansion valve expands the high-temperature, high-pressure liquid refrigerant condensed in the condenser into a low-pressure liquid refrigerant. The evaporator evaporates the expanded refrigerant in the expansion valve, returning the low-temperature, low-pressure refrigerant gas to the compressor. The evaporator achieves its cooling effect by utilizing the latent heat of refrigerant evaporation to exchange heat with the material being cooled. Throughout the cycle, the air conditioner regulates the temperature of the indoor space.

[0053] The outdoor unit of an air conditioner refers to the part of the refrigeration cycle that includes the compressor and the outdoor heat exchanger. The indoor unit of an air conditioner includes the indoor heat exchanger, and an expansion valve can be provided in either the indoor or outdoor unit.

[0054] The indoor and outdoor heat exchangers function as either condensers or evaporators. When the indoor heat exchanger is used as a condenser, the air conditioner functions as a heater in heating mode; when the indoor heat exchanger is used as an evaporator, the air conditioner functions as a cooler in cooling mode.

[0055] This application provides an air conditioner, such as... Figure 1 ,include:

[0056] The refrigerant circulation loop 100 allows the refrigerant to circulate in the loop consisting of the compressor 130, condenser 120, expansion valve 110, and evaporator 140.

[0057] An outdoor heat exchanger and an indoor heat exchanger, one of which operates as a condenser 120 and the other as an evaporator 140;

[0058] Infrared thermopile sensor 200 is used to acquire infrared lumen value data and acquire infrared images based on the lumen value data;

[0059] The detection frame counter 300 is used to acquire a first count value, which is the cumulative number of consecutively detected frames of the infrared image;

[0060] Undetected frame counter 400 is used to obtain a second count value, which is the cumulative number of consecutive undetected frames in the infrared image;

[0061] Controller 500 is configured as follows:

[0062] When the infrared image detects a target, the weight of the cached frame is weighted based on the first count value, and the target detection result and target position coordinates are output.

[0063] When the infrared image detects no target and the infrared image previously showed a target, the target detection result and target location coordinates are output based on the second count value.

[0064] In this embodiment, as described in the background art, most target detection algorithms based on infrared thermopile sensing currently use single-frame image processing and do not utilize the contextual information of the video. In addition, target detection algorithms also have the problem of not achieving a 100% detection rate. Furthermore, the inherent shortcomings of the aforementioned infrared thermopile sensor devices and the generally low computing power of the processors inside home appliances mean that when the quality of the input frame is poor, it will directly affect the accuracy and stability of the output results, resulting in intermittent detection results. This will adversely affect subsequent processing and other modules, ultimately leading to a poor product functional experience.

[0065] In this scheme, since there are many heat source interferences in the heated air and furniture of the infrared thermopile, in order to ensure that the detected target is the real target to be detected, a detection frame counter and an undetected frame counter are set. The first count value and the second count value obtained by the detection frame counter and the undetected frame counter are used to determine whether the target has been really detected, thereby improving the detection accuracy. Secondly, when the infrared image detects a target, the weight of the buffer frame is weighted according to the first count value, and the target detection result and the target position coordinates are output. When the infrared image detects no target this time and the infrared image previously had a target, the second count value is used to make a judgment, and the target detection result and the target position coordinates are output.

[0066] In order to achieve weighted processing of the cached frame weights using the first count value and output the target detection result and target position coordinates, in some embodiments of this application, the controller is specifically configured as follows:

[0067] When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold.

[0068] If so, output the target detection result as "detected" and output the target's location coordinates;

[0069] If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

[0070] In this embodiment, since the infrared thermopile is exposed to a large number of heat-generating interference objects in the heated air and furniture, in order to ensure that the detected target is the real target, when the number of consecutively detected superimposed frames of the target exceeds a first count value, the detected target is considered to be the real target, and the system outputs that the target has been detected. Figure 2 As shown, in frame processing, the left-hand "undetected" stage indicates that no target appears in the frame stream or the target has not been detected. The middle "continuous detection" stage indicates that the target has been successfully detected, but the cumulative number of detected frames has not reached the first count value, so the final output still shows that the target has not been detected. Only in the right-hand stage, when the cumulative number of detected frames reaches the first count value, is the target considered successfully detected, and the output shows the target as detected.

[0071] The controller acquires infrared lumen value data from the infrared thermopile sensor, generates an infrared image through an image generation program, and inputs it into the target detection program. If a target is detected in the frame image, it checks whether the number of consecutive detected frames exceeds a first count value. If not, it outputs "not detected," but the target's position coordinates are stored in the cached frame result. The next infrared image frame is then retrieved and processed accordingly. If a target is detected in that frame, the first count value corresponding to the consecutive detected frames is incremented by 1. Simultaneously, the position coordinates are compared with the previous frame's position to determine if they represent the same target. Specifically, if the target's position area changes very little and the current frame's detection result position and the previous frame's result coordinates meet a set coordinate threshold, the two detected targets are considered the same. If they are the same target, they are weighted according to the cached frame weight relationship table and added to the cached frame. This process continues until the number of consecutive detected frames exceeds the first count value. At this point, the system outputs "target detected," along with the weighted and integrated position area.

[0072] In order to accurately determine whether the target image has disappeared, in some embodiments of this application, the controller is specifically configured as follows:

[0073] When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold.

[0074] If so, the output result will be "None", and the target position coordinates will be set to 0.

[0075] In this embodiment, a second count value for a fixed buffer duration of undetected frames is set. When the number of consecutive frames in which the target is not detected exceeds the second count value, the target is considered to have truly disappeared, and the target detection result is output as "none". Figure 3 As shown, the left-hand target detection stage in frame processing indicates that the target in the frame stream has been successfully detected. The middle continuous non-detection stage indicates that the target detection result in frame processing is "none," but the cumulative number of undetected frames has not reached the second count value, and the final output still shows that the target has been detected. Until the right-hand stage, the cumulative number of undetected frames reaches the second count value, at which point the target is considered to have truly disappeared, and the output shows the target detection status as "none." When the target disappears, after the non-detected frame counter reaches the second count value, the system outputs the target detection result as "none," and all target position coordinates are set to 0.

[0076] In order to perform weighted processing on the cached frames, in some embodiments of this application, the controller is specifically configured as follows:

[0077] When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:1.

[0078] When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

[0079] In this embodiment, the two parameters, the first count value and the second count value, can resolve the instability during the process of the target appearing and disappearing from nothing, and also resolve the intermittent detection of some suspected target interference objects. However, the above-mentioned fixed buffer duration frame method only addresses the presence or absence of the target detection result, so it does not correct the detected position of the target. Therefore, this invention also proposes another method that corrects the position of the detected target, which is referred to as buffer frame weighted method in this paper.

[0080] A buffer frame does not represent a single frame, but rather a buffer space of N consecutive frames. When two consecutive frames both indicate that a target has been detected, the target's location area changes very little, and the coordinates of the current frame's detection result and the previous frame's result satisfy a set coordinate threshold, the target detected in the two frames is considered to be the same target. To ensure accurate and smooth display of the target's location, the preceding N frames are designated as buffer frames and assigned certain weights. The final output representing the target's location is the combined result of the buffer frame's result multiplied by weight B and the current frame's detection result multiplied by weight A.

[0081] The weights of the current frame and the buffer frame are determined using an automatic adjustment method, with different weights assigned based on the number of times a target is detected. If a target is detected consecutively in a buffer frame, the buffer frame weight B increases; otherwise, the current frame weight A increases. For example: when a target is detected for the first time, the result is not output directly, but the detection result position is temporarily stored in the buffer frame, and a counter is incremented by 1. When the target is detected in the next frame and matches the condition of the same target, its result is adjusted according to the initial weights A = 0.5 and B = 0.5, and the output result is saved to the buffer, while the counter is incremented by 1. If the target is still detected successfully in the next frame, the weights of the two frames are adjusted to A = 0.4 and B = 0.6, and the counter is incremented by 1. This rule is followed for the next frame. If successful, the weights are further adjusted to A = 0.3 and B = 0.7. If the same target is detected repeatedly, the final weights are A = 0.1 and B = 0.9. It can be seen that the weight changes accordingly as the count value changes, and the relationship is shown in Table 1.

[0082]

[0083] Table 1

[0084] In order to obtain the detection result of the current frame, in some embodiments of this application, the detection result of the current frame is specifically determined by the following formula:

[0085] The detection result of the current frame = current frame * current frame weight + buffered frame * buffered frame weight

[0086] By applying the above technical solutions, in an air conditioner including a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter, and a controller, the controller is configured to: when the infrared image detects a target, perform weighted processing on the cached frame weights based on a first count value, and output the target detection result and target position coordinates, where the first count value is the cumulative number of consecutive detected frames of the infrared image; when the infrared image detects no target and the infrared image previously showed a target, output the target detection result and target position coordinates based on a second count value, where the second count value is the cumulative number of consecutive undetected frames of the infrared image, thereby realizing target correction based on cached frame weights, improving the accuracy and stability of target detection results, and enhancing the user experience.

[0087] To further illustrate the technical concept of this invention, the technical solution of this invention will now be described in conjunction with specific application scenarios.

[0088] This application provides a method for enhancing the stability of infrared target detection results in an air conditioner. This method is applied to an air conditioner including a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter, and a controller. Figure 4 As shown, the method includes:

[0089] Step S401: When the infrared image detects a target, the weight of the cached frame is weighted based on the first count value, and the target detection result and target position coordinates are output. The first count value is the cumulative number of consecutively detected frames of the infrared image.

[0090] Because infrared thermopile is exposed to many heat sources and interference objects in heated air and furniture, in order to ensure that the detected target is the real target, a detection frame counter and an undetected frame counter are set. The first count value and the second count value obtained by the detection frame counter and the undetected frame counter are used to determine whether the target has been truly detected, thereby improving the detection accuracy. Secondly, when the infrared image detects a target, the weight of the buffer frame is weighted according to the first count value, and the target detection result and the target position coordinates are output.

[0091] To achieve weighted processing of the cached frame weights based on the first count value and output the target detection result and target location coordinates, in some embodiments of this application, the weighted processing of the cached frame weights is based on the first count value, and the target detection result and target location coordinates are output as follows:

[0092] When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold.

[0093] If so, output the target detection result as "detected" and output the target's location coordinates;

[0094] If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

[0095] In this embodiment, since the infrared thermopile is exposed to a large number of heat-generating interference objects in the heated air and furniture, in order to ensure that the detected target is the real target, when the number of consecutively detected superimposed frames of the target exceeds a first count value, the detected target is considered to be the real target, and the system outputs that the target has been detected. Figure 2 As shown, in frame processing, the left-hand "undetected" stage indicates that no target appears in the frame stream or the target has not been detected. The middle "continuous detection" stage indicates that the target has been successfully detected, but the cumulative number of detected frames has not reached the first count value, so the final output still shows that the target has not been detected. Only in the right-hand stage, when the cumulative number of detected frames reaches the first count value, is the target considered successfully detected, and the output shows the target as detected.

[0096] The controller acquires infrared lumen value data from the infrared thermopile sensor, generates an infrared image through an image generation program, and inputs it into the target detection program. If a target is detected in the frame image, it checks whether the number of consecutive detected frames exceeds a first count value. If not, it outputs "not detected," but the target's position coordinates are stored in the cached frame result. The next infrared image frame is then retrieved and processed accordingly. If a target is detected in that frame, the first count value corresponding to the consecutive detected frames is incremented by 1. Simultaneously, the position coordinates are compared with the previous frame's position to determine if they represent the same target. Specifically, if the target's position area changes very little and the current frame's detection result position and the previous frame's result coordinates meet a set coordinate threshold, the two detected targets are considered the same. If they are the same target, they are weighted according to the cached frame weight relationship table and added to the cached frame. This process continues until the number of consecutive detected frames exceeds the first count value. At this point, the system outputs "target detected," along with the weighted and integrated position area.

[0097] To achieve weighted processing of the cached frame weights, in some embodiments of this application, the cached frame weights are weighted as follows:

[0098] When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:1.

[0099] When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

[0100] In this embodiment, the two parameters, the first count value and the second count value, can resolve the instability during the process of the target appearing and disappearing from nothing, and also resolve the intermittent detection of some suspected target interference objects. However, the above-mentioned fixed buffer duration frame method only addresses the presence or absence of the target detection result, so it does not correct the detected position of the target. Therefore, this invention also proposes another method that corrects the position of the detected target, which is referred to as buffer frame weighted method in this paper.

[0101] A buffer frame does not represent a single frame, but rather a buffer space of N consecutive frames. When two consecutive frames both indicate that a target has been detected, the target's location area changes very little, and the coordinates of the current frame's detection result and the previous frame's result satisfy a set coordinate threshold, the target detected in the two frames is considered to be the same target. To ensure accurate and smooth display of the target's location, the preceding N frames are designated as buffer frames and assigned certain weights. The final output representing the target's location is the combined result of the buffer frame's result multiplied by weight B and the current frame's detection result multiplied by weight A.

[0102] The weights of the current frame and the buffered frames are determined using an automatic adjustment method, with different weights assigned based on the number of times a target is detected. If a target is detected consecutively in a buffered frame, the weight B of the buffered frame is increased; otherwise, the weight A of the current frame is increased.

[0103] In order to obtain the detection result of the current frame, in some embodiments of this application, the detection result of the current frame is specifically determined by the following formula:

[0104] The detection result obtained from the current frame = current frame * current frame weight + cached frame * cached frame weight.

[0105] Step S402: When the infrared image is detected as having no target and the infrared image previously showed a target, the target detection result and target position coordinates are output based on the second count value, where the second count value is the cumulative number of consecutive undetected frames in the infrared image.

[0106] When the infrared image detection shows no target and the previous infrared image showed a target, the judgment is made based on the second count value, and the target detection result and target position coordinates are output.

[0107] To accurately determine whether the target image has disappeared, in some embodiments of this application, the target detection result and target location coordinates are output based on the second count value, specifically as follows:

[0108] When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold.

[0109] If so, the output result will be "None", and the target position coordinates will be set to 0.

[0110] In this embodiment, a second count value for a fixed buffer duration of undetected frames is set. When the number of consecutive frames in which the target is not detected exceeds the second count value, the target is considered to have truly disappeared, and the target detection result is output as "none". Figure 3 As shown, the left-hand target detection stage in frame processing indicates that the target in the frame stream has been successfully detected. The middle continuous non-detection stage indicates that the target detection result in frame processing is "none," but the cumulative number of undetected frames has not reached the second count value, and the final output still shows that the target has been detected. Until the right-hand stage, the cumulative number of undetected frames reaches the second count value, at which point the target is considered to have truly disappeared, and the output shows the target detection status as "none." When the target disappears, after the non-detected frame counter reaches the second count value, the system outputs the target detection result as "none," and all target position coordinates are set to 0.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An air conditioner, characterized in that, include: The refrigerant circulation loop allows the refrigerant to circulate within a loop consisting of the compressor, condenser, expansion valve, and evaporator. An outdoor heat exchanger and an indoor heat exchanger, one of which functions as a condenser and the other as an evaporator; An infrared thermopile sensor is used to acquire infrared lumen value data and to acquire infrared images based on the lumen value data; A detection frame counter is used to acquire a first count value, wherein the first count value is the cumulative number of consecutively detected frames of the infrared image; A non-detected frame counter is used to obtain a second count value, which is the cumulative number of consecutive non-detected frames in the infrared image; The controller is configured as follows: When the infrared image detects a target, the weight of the cached frame is weighted based on the first count value, and the target detection result and target position coordinates are output. When the infrared image detects no target and the infrared image previously showed a target, the target detection result and target position coordinates are output based on the second count value. The controller is specifically configured as follows: When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold. If so, output the target detection result as "detected" and output the target's location coordinates; If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

2. The air conditioner as described in claim 1, characterized in that, The controller is specifically configured as follows: When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold. If so, the output result will be "None", and the target position coordinates will be set to 0.

3. The air conditioner as described in claim 1, characterized in that, The controller is specifically configured as follows: When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:

1. When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

4. The air conditioner as described in claim 3, characterized in that, The detection result of the current frame is determined by the following formula: The detection result obtained in the current frame = the current frame Current frame weight + buffered frames Cache frame weights.

5. A method for enhancing the stability of infrared target detection results in an air conditioner, characterized in that, Applied to an air conditioner as described in any one of claims 1 to 4, comprising a refrigerant circulation loop, an outdoor heat exchanger and an indoor heat exchanger, an infrared thermopile sensor, a detected frame counter, an undetected frame counter, and a controller, the method comprises: When the infrared image detects a target, the weight of the cached frames is weighted based on the first count value, and the target detection result and target position coordinates are output. The first count value is the cumulative number of consecutively detected frames of the infrared image. When the infrared image detects no target and the infrared image previously showed a target, the target detection result and target location coordinates are output based on the second count value, where the second count value is the cumulative number of consecutive undetected frames in the infrared image.

6. The method as described in claim 5, characterized in that, The weights of the buffered frames are weighted based on the first count value, and the target detection result and target location coordinates are output, specifically: When the infrared image detects a target, it is determined whether the first count value is greater than the first threshold. If so, output the target detection result as "detected" and output the target's location coordinates; If not, the target result is output as not detected, and the target position coordinates are stored in the buffer frame. The first count value is incremented by one. When the current target and the previous target are the same target, the weight of the buffer frame is weighted and the first count value is re-evaluated to see if it is greater than the first threshold until the first count value is greater than the first threshold.

7. The method as described in claim 5, characterized in that, Based on the second count value, the target detection result and target position coordinates are output, specifically: When the infrared image is detected as having no target and the infrared image was previously showing a target, it is determined whether the second count value is greater than the second threshold. If so, the output result will be "None", and the target position coordinates will be set to 0.

8. The method as described in claim 6, characterized in that, The weights of the cached frames are weighted as follows: When the infrared image is the first time the target is detected, the initial weight ratio is stored in the cache space and the first count value is incremented by one. The initial weight ratio is the ratio of the current frame to the cached frame, which is 1:

1. When the infrared image is not the target detected for the first time, the weight of the current frame is reduced and the weight of the cached frame is increased.

9. The method as described in claim 8, characterized in that, The detection result of the current frame is determined by the following formula: The detection result obtained in the current frame = the current frame Current frame weight + buffered frames Cache frame weights.

Images