Control method of vehicle-mounted mosquito repelling device, vehicle-mounted mosquito repelling device and storage medium

Abstract

The invention discloses a control method of a vehicle-mounted mosquito repelling device, the vehicle-mounted mosquito repelling device and a storage medium, relates to the field of vehicle-mounted technologies, and discloses the control method of the vehicle-mounted mosquito repelling device, the control method is applied to the vehicle-mounted mosquito repelling device, and the vehicle-mounted mosquito repelling device comprises an image acquisition device and a sound wave mosquito repelling device. The method comprises the following steps: determining a mosquito identification result based on an image in a cabin acquired by an image acquisition device; determining an action recognition result according to the image in the cabin; determining a mosquito repelling mode according to the mosquito recognition result and the action recognition result; and controlling the sound wave mosquito repelling device to operate according to the operation parameters corresponding to the mosquito repelling mode. On the basis, the mosquito information can be automatically detected, the mosquito repelling device is automatically started after the mosquito information is detected, and the mosquito repelling effect is improved.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, and particularly to a control method for an in-vehicle mosquito repellent device, an in-vehicle mosquito repellent device, and a storage medium. Background Art

[0002] When a car is parked in an environment with high humidity and relatively high external temperature, mosquitoes are likely to breed inside the car, bringing annoyance to users.

[0003] In related mosquito repellent methods, it is necessary for the user inside the car to manually turn on the mosquito repellent device. However, when mosquitoes appear, users usually turn on the mosquito repellent device only after being bitten by mosquitoes or hearing the sound of mosquitoes, resulting in a significant reduction in the mosquito repellent effect due to the startup delay. Therefore, the current in-vehicle mosquito repellent device has the defect of poor mosquito repellent effect.

[0004] The above content is only used to assist in understanding the technical solution of this application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a control method for an in-vehicle mosquito repellent device, an in-vehicle mosquito repellent device, and a storage medium, aiming to solve the technical problem of poor mosquito repellent effect caused by the need to manually turn on the mosquito repellent device.

[0006] To achieve the above purpose, this application proposes a control method for an in-vehicle mosquito repellent device, which is applied to the in-vehicle mosquito repellent device. The in-vehicle mosquito repellent device includes an image acquisition device and a sound wave mosquito repellent device. The method includes: Based on the image of the cockpit collected by the image acquisition device, determine the mosquito recognition result; Determine the action recognition result according to the image of the cockpit; Determine the mosquito repellent mode according to the mosquito recognition result and the action recognition result; Control the sound wave mosquito repellent device to operate according to the operating parameters corresponding to the mosquito repellent mode.

[0007] In one embodiment, the step of determining the mosquito recognition result based on the image of the cockpit collected by the image acquisition device includes: Perform target detection on the image of the cockpit to obtain the confidence level of the suspicious target; If there is a suspicious target with the confidence level of the suspicious target greater than or equal to the preset confidence level, set the mosquito recognition result to the presence of mosquitoes.

[0008] In one embodiment, the in-vehicle mosquito repellent device further includes an ultra-wideband module. The step of determining the mosquito recognition result based on the image of the cockpit collected by the image acquisition device further includes: Perform target detection on the image of the cockpit to obtain the confidence level of the suspicious target and the position of the suspicious target; Determine the living body probability corresponding to the suspicious target according to the wing vibration characteristics extracted by the ultra-wideband module based on the position. If the weighted average of the suspicious target confidence and the living body probability is greater than or equal to a preset threshold, set the mosquito recognition result to the presence of mosquitoes.

[0009] In one embodiment, the step of determining the action recognition result based on the image inside the cockpit includes: Perform object detection on the image inside the cockpit to obtain the suspicious action confidence. If there is a suspicious action confidence greater than or equal to a preset suspicious confidence, and the number of executions of the suspicious action within a preset time is greater than or equal to a preset number, set the action recognition result to the presence of a mosquito repelling action.

[0010] In one embodiment, the vehicle-mounted mosquito repelling device further includes an ultra-wideband module, and the step of determining the action recognition result based on the image inside the cockpit further includes: Perform object detection on the image inside the cockpit to obtain the suspicious action confidence and the personnel position of the target person. Determine the average breathing change frequency corresponding to the target person according to the breathing characteristics extracted by the ultra-wideband module based on the personnel position. If the suspicious action confidence is greater than or equal to a preset action confidence, the number of executions of the suspicious action is greater than or equal to a preset number, and the average breathing change frequency is greater than or equal to a preset frequency, set the action recognition result to the presence of a mosquito repelling action.

[0011] In one embodiment, the mosquito repelling mode includes a direct mosquito repelling mode and an indirect mosquito repelling mode, and the step of controlling the acoustic mosquito repelling device to operate according to the operating parameters corresponding to the mosquito repelling mode includes: If the mosquito repelling mode is the direct mosquito repelling mode, control the acoustic mosquito repelling device to operate based on preset parameters until the mosquito recognition result is the absence of mosquitoes. If the mosquito repelling mode is the indirect mosquito repelling mode, control the acoustic mosquito repelling device to operate based on a preset time period and preset parameters.

[0012] In one embodiment, the step of determining the mosquito repelling mode according to the mosquito recognition result and the action recognition result includes: If the mosquito recognition result is the presence of mosquitoes, determine the mosquito repelling mode to be the direct mosquito repelling mode. If the action recognition result is the presence of a mosquito repelling action and the mosquito recognition result is the absence of mosquitoes, determine the mosquito repelling mode to be the indirect mosquito repelling mode.

[0013] In one embodiment, when any of the following conditions is met, the step of determining the mosquito recognition result by executing the in-cabin image collected by the image acquisition device is performed: The current month is a preset month; The current temperature is within a preset temperature range; The current location is at a preset latitude; The current humidity is greater than the preset humidity; The current time is from the preset sunrise time to the preset sunset time.

[0014] In addition, to achieve the above object, the present application also proposes a vehicle-mounted mosquito repellent device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the method of the vehicle-mounted mosquito repellent device as described above.

[0015] In addition, to achieve the above object, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the control method of the vehicle-mounted mosquito repellent device as described above.

[0016] One or more technical solutions proposed by the present application have at least the following technical effects: Automatically analyze and process the in-cabin image collected by the image acquisition device of the vehicle-mounted mosquito repellent device to obtain the recognition result of the presence of mosquitoes or the recognition result of the scratching action of the user in the cabin, and then determine the mosquito repellent mode executed by the vehicle-mounted mosquito repellent device based on the two recognition results. Finally, control the sound wave mosquito repellent device to operate based on the operating parameters corresponding to the mosquito repellent mode. Based on this, it is possible to automatically detect the mosquito information and human movement information in the cabin, automatically turn on the mosquito repellent device and perform mosquito repellent treatment based on the detected information, without the need for the user to manually turn it on, thereby improving the mosquito repellent effect. At the same time, detecting the two recognition results improves the accuracy of mosquito recognition. Description of the Drawings

[0017] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing the embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flowchart provided for the first embodiment of the control method of the vehicle-mounted mosquito repellent device of the present application; Figure 2 A schematic flowchart provided for the second embodiment of the control method of the vehicle-mounted mosquito repellent device of the present application; Figure 3 A schematic flowchart provided for the third embodiment of the control method of the vehicle-mounted mosquito repellent device of the present application; Figure 4 A schematic diagram of the device structure of the hardware operating environment involved in the control method of the vehicle-mounted mosquito repellent device in the embodiments of the present application.

[0020] The realization of the purpose, functional characteristics and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] The main solution of the embodiments of the present application is: analyze the image in the cockpit through the vehicle-mounted mosquito repellent device to obtain the recognition result of whether there are mosquitoes currently and the recognition result of whether there is a mosquito repellent action, and then determine the mosquito repellent mode to be executed based on the recognition result, and finally perform mosquito repellent treatment based on the mosquito repellent mode. Through two recognition methods, while improving the accuracy of mosquito recognition, it can automatically control the operation of the mosquito repellent device based on the recognition result, improving the mosquito repellent effect.

[0023] In this embodiment, for the convenience of description, the vehicle-mounted mosquito repellent device is used as the execution subject for elaboration below.

[0024] In the related mosquito repellent methods, the user in the vehicle needs to manually turn on the mosquito repellent device. However, when mosquitoes appear, the user usually turns on the mosquito repellent device after being bitten by mosquitoes or hearing the sound of mosquitoes, resulting in a significant reduction in the mosquito repellent effect due to the startup delay. Therefore, the current vehicle-mounted mosquito repellent device has the defect of poor mosquito repellent effect.

[0025] The present application provides a solution, by simultaneously detecting whether mosquitoes appear in the cabin and whether the personnel in the cockpit perform relevant mosquito repellent actions, and analyzing and judging the mosquito repellent mode to be executed based on the corresponding recognition results, and finally controlling the sonic mosquito repellent device to perform mosquito repellent treatment, so as to be able to automatically turn on the mosquito repellent device and improve the mosquito repellent effect.

[0026] To better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings of the specification and specific embodiments.

[0027] An embodiment of the present application provides a control method for an in-vehicle mosquito repellent device, which is applied to the in-vehicle mosquito repellent device. The in-vehicle mosquito repellent device includes an image acquisition device and a sound wave mosquito repellent device. Among them, the image acquisition device can be a camera built in or externally connected to the in-vehicle mosquito repellent device, and this camera can be an OMS (Occupant Monitoring System) camera, an infrared camera, a depth camera, etc. The sound wave mosquito repellent device can be a small ultrasonic generator, which achieves the mosquito repellent effect by emitting ultrasonic frequency bands with mosquito repellent effects. Optionally, the sound wave mosquito repellent device can also be a composite sound wave generator that combines multiple sound wave frequencies and waveforms, and can simulate sounds that repel mosquitoes in various natural environments, such as the sound of wind, rain, or the flapping of wings of other insects, to enhance the diversity and effect of mosquito repellent. In addition, the sound wave mosquito repellent device can automatically adjust the intensity and frequency of the sound wave output according to environmental changes and the actual situation of mosquito activities, realizing more accurate and efficient mosquito repellent.

[0028] Furthermore, the sound wave mosquito repellent device can use the in-vehicle seat armrest as a carrier and be integrated into the internal space of the seat armrest, so as to quickly repel mosquitoes when there are mosquitoes and reduce the interference to the cabin environment. It can be understood that in the cockpit, the in-vehicle armrest is the vehicle component closest to the human body. Based on the in-vehicle seat armrest as the sound wave drive carrier, the best mosquito repellent effect can be achieved.

[0029] Optionally, the sound wave mosquito repellent device can also be installed at the air-conditioning outlet, on the in-vehicle seat or other positions, and the present application does not make too many limitations here.

[0030] Based on this, please refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the control method for the in-vehicle mosquito repellent device of the present application.

[0031] In this embodiment, the control method for the in-vehicle mosquito repellent device includes steps S10 to S40: Step S10, based on the image of the cabin collected by the image acquisition device, determine the mosquito recognition result.

[0032] It should be noted that the mosquito recognition result includes the presence of mosquitoes and the absence of mosquitoes. When the mosquito recognition result indicates that there are mosquitoes in the cabin, the sound wave mosquito repellent device can be activated to repel mosquitoes. The image of the cabin can be multiple consecutive photos or a real-time video stream of the cabin.

[0033] In this embodiment, the in-vehicle mosquito repellent device is usually in a standby state. When the environmental information in the current vehicle cabin or the environmental information where the vehicle is located meets the corresponding conditions, for example, the current environmental temperature is between 25 and 30 °C suitable for mosquito activities and the current humidity is above 60%, the mosquito detection process of the in-vehicle mosquito repellent device is triggered. That is, at this time, it is necessary to actively detect whether there are mosquitoes in the cabin, so as to automatically start the acoustic mosquito repellent device for mosquito repellent treatment when detecting relevant recognition results indicating the presence of mosquitoes.

[0034] When determining the mosquito recognition result and the action recognition result based on the cabin image respectively, the cabin image can be analyzed through image detection technology / image recognition technology to obtain the mosquito characteristics of the suspicious targets suspected of being mosquitoes in the image, so as to determine the mosquito recognition result based on the mosquito characteristics. Among them, the mosquito characteristics include mosquito shape, size, color, wings, texture, movement trajectory, wing vibration frequency and other characteristics. The in-vehicle mosquito repellent device can parse the cabin image through the mosquito characteristic recognition module to obtain the mosquito characteristics. If there are no suspicious targets suspected of being mosquitoes in the cabin image, the mosquito recognition result can be directly determined as no mosquitoes.

[0035] Optionally, in addition to determining the mosquito recognition result through mosquito characteristics, the mosquito recognition result can also be determined by infrared detection based on the infrared signals reflected by mosquitoes in the cabin image. It should be noted that when detecting the cabin image, due to factors such as the shooting accuracy of the cabin image, the mosquito characteristics may be misrecognized, or misjudged because the regular actions performed by the people in the cabin are similar to the mosquito repellent actions. Therefore, when obtaining the mosquito characteristics, the in-vehicle mosquito repellent device will also output the confidence levels corresponding to these characteristics, so as to determine the mosquito recognition result based on the mosquito characteristics and the confidence levels corresponding to the mosquito characteristics.

[0036] Therefore, as an optional implementation manner of determining the mosquito recognition result, the cabin image can be subjected to target detection to obtain the suspicious target confidence level; if there is a suspicious target with the suspicious target confidence level greater than or equal to the preset confidence level, the mosquito recognition result is set to there are mosquitoes. In this process, by detecting the cabin image, the mosquito characteristics of the suspected mosquito flying objects are obtained, and at the same time the confidence level corresponding to this characteristic is determined. Furthermore, when its confidence level exceeds the set threshold, such as the probability of there being mosquitoes is 90% (greater than the preset 85%), it is considered that there are mosquitoes, that is, the mosquito recognition result is set to there are mosquitoes.

[0037] Step S20, determine the action recognition result according to the cabin image It should be noted that the action recognition result includes the presence of mosquito repellent actions and the absence of mosquito repellent actions.

[0038] In this embodiment, image detection technology / image recognition technology can be used to analyze the images inside the cockpit, so as to obtain the motion characteristics of the people inside the cockpit, and based on the motion characteristics, the motion recognition result can be determined. Among them, the motion characteristics include the actions of the people inside the cockpit such as patting with the palm and driving away mosquitoes, the waving of the arm when using an object to drive away mosquitoes, changes in facial expressions, and changes in breathing frequency. If the above motion characteristics are obtained after analyzing the images inside the cockpit, it can be determined that the motion recognition result is that there is a mosquito repelling action. The motion information of the people appearing in the images inside the cockpit can be analyzed by a motion feature recognition module to obtain the motion characteristics.

[0039] Optionally, when determining the motion recognition result, if the image inside the cockpit is a video stream, the motion recognition result can be determined by analyzing the voice signal of the user inside the cockpit in the image inside the cockpit.

[0040] Optionally, when determining the motion recognition result based on the motion characteristics, it is also necessary to analyze and process the confidence level of the motion characteristics. Therefore, as an optional implementation manner for determining the motion recognition result, target detection can be performed on the image inside the cockpit to obtain the confidence level of the suspicious action; if there is a confidence level of the suspicious action greater than or equal to a preset suspicious confidence level, and the number of executions of the suspicious action within a preset time is greater than or equal to a preset number of times, the motion recognition result is set to be that there is a mosquito repelling action. In this process, in addition to analyzing the confidence level of the suspicious action, it is also necessary to analyze and compare the number of its executions to avoid misjudgment when detecting similar actions. For example, if there is a user scratching action, the confidence level of this action is greater than the preset 85%, and at the same time, the number of executions within 30 seconds exceeds the preset 3 times, it indicates that there are mosquitoes currently, and then the motion recognition result is set to be that there is a mosquito repelling action.

[0041] Step S30, determine the mosquito repelling mode according to the mosquito recognition result and the motion recognition result.

[0042] It should be noted that the mosquito recognition result is determined by detecting whether there are mosquito characteristics in the images inside the cockpit. Since there may be shooting blind spots in the image acquisition device, for example, the leg area of the people inside the cockpit is usually difficult to shoot, or the mosquito characteristics cannot be recognized due to insufficient light. At this time, the motion recognition result corresponding to the action triggered when the people inside the cockpit pat mosquitoes in the leg area can be recognized to determine that there are mosquitoes inside the cockpit. Therefore, the mosquito recognition result can be used as the main judgment basis for the existence of mosquitoes, and the motion recognition result can be used as an auxiliary judgment basis, so as to improve the recognition range of mosquito recognition.

[0043] In this embodiment, the mosquito repellent mode includes a direct mosquito repellent mode and an indirect mosquito repellent mode. If the mosquito recognition result indicates the presence of mosquitoes, the determined mosquito repellent mode is the direct mosquito repellent mode; if the mosquito recognition result indicates the absence of mosquitoes and the action recognition result indicates the presence of a mosquito repellent action, it means that the mosquitoes are in the shooting blind area. At this time, the determined mosquito repellent mode is the indirect mosquito repellent mode. Among them, the difference between the direct mosquito repellent mode and the indirect mosquito repellent mode lies in the operation strategy of the sonic mosquito repellent device. The direct mosquito repellent mode requires controlling the sonic mosquito repellent device to run continuously until the mosquito recognition result indicates the absence of mosquitoes, while the indirect mosquito repellent mode controls the sonic mosquito repellent device to run for a preset period, such as 1 to 5 minutes. It can be understood that when performing sonic mosquito repellent treatment, the ultrasonic signal may cause interference to the personnel in the cockpit. In the indirect mosquito repellent mode, usually the sonic mosquito repellent device is controlled to run for a short time to achieve rapid mosquito repellent while reducing interference to the personnel. In the direct mosquito repellent mode, the purpose is to repel mosquitoes and there is no limit to the running time of the sonic mosquito repellent device. The running time in the indirect mosquito repellent mode can be set based on actual needs and is not limited in this application.

[0044] Further, in this embodiment, the priority of the direct mosquito repellent mode is higher than that of the indirect mosquito repellent mode, that is, when both the mosquito recognition result and the action recognition result indicate the current presence of mosquitoes, the running mode of the sonic mosquito repellent device is the direct mosquito repellent mode.

[0045] Optionally, if the mosquito recognition result indicates the absence of mosquitoes and the action recognition result indicates the absence of a mosquito repellent action, there is no need to perform mosquito repellent treatment, that is, the determined mosquito repellent mode is no mosquito repellent or maintaining the current running state of the sonic mosquito repellent device.

[0046] Step S40, controlling the sonic mosquito repellent device to run according to the running parameters corresponding to the mosquito repellent mode.

[0047] In this embodiment, the running parameters corresponding to the direct mosquito repellent mode are preset mosquito repellent parameters, and the running time is unlimited. Among them, the preset mosquito repellent parameters include the sound wave frequency emitted by the sonic mosquito repellent device. For example, controlling the sonic mosquito repellent device to continuously emit ultrasonic waves between 20 kHz and 100 kHz that mosquitoes find repulsive, so that the mosquitoes actively move away from the ultrasonic sound source.

[0048] Specifically, if the mosquito repellent mode is the direct mosquito repellent mode, it is necessary to control the sonic mosquito repellent device to run based on the preset parameters until the mosquito recognition result indicates the absence of mosquitoes. Therefore, during the operation of the sonic mosquito repellent device, the vehicle-mounted mosquito repellent device analyzes the images collected by the image acquisition device in real time, so as to control the sonic mosquito repellent device to stop running after driving away all mosquitoes to achieve the intelligent opening and closing of the sonic mosquito repellent device.

[0049] Optionally, if the mosquito repellent mode is the indirect mosquito repellent mode, it is necessary to control the operation of the sonic mosquito repellent device based on a preset time period and preset parameters, and turn off the sonic mosquito repellent device after the preset time period, so as to effectively repel mosquitoes while reducing the impact of the sound waves on the people in the cockpit. It should be noted that the preset time period and preset parameters can be set according to specific requirements, and the present application does not limit this here.

[0050] This embodiment provides a control method for an in-vehicle mosquito repellent device. The feature recognition module processes the image of the cockpit collected by the image acquisition device, so as to obtain the mosquito characteristics in the cockpit and the motion characteristics of the people in the cockpit. Then, based on the personnel characteristics and motion characteristics, a mosquito recognition result and a motion recognition result for judging whether mosquito repellent treatment is required in the cockpit are generated. Based on these two recognition results, the situations of misrecognition and missed recognition can be effectively reduced, and the accuracy and range of mosquito recognition can be improved. When mosquito repellent treatment is required in the cockpit, based on the mosquito recognition result and the motion recognition result, the required mosquito repellent mode is determined, and the sonic mosquito repellent device is controlled to operate according to the operation parameters of the required mosquito repellent mode, realizing automatic mosquito repellent treatment in the cockpit. At the same time, the mosquito repellent time is flexibly controlled, the energy consumption is reduced, the damage to the environment in the cockpit is reduced, and the comfort of the people in the cockpit is improved.

[0051] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as that in the above first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, the in-vehicle mosquito repellent device further includes a UWB (Ultra Wide Band) module. Please refer to Figure 2 , in step S10, the step of determining the mosquito recognition result based on the image of the cockpit collected by the image device includes steps S11 to S13: Step S11, perform target detection on the image of the cockpit to obtain the confidence level of the suspicious target and the position of the suspicious target.

[0052] In this embodiment, the image detection algorithm / image recognition algorithm, etc. of the mosquito feature recognition module can be used to perform target detection on the image of the cockpit, so as to obtain a suspicious target suspected of being a mosquito and the position information of the suspicious target. Among them, the target detection process may include identifying the physical characteristics of the mosquito such as the shape, size, and color of the suspicious target. At the same time as obtaining the physical characteristics of the mosquito, the confidence level of the suspicious target corresponding to the feature is output.

[0053] Further, after the position of the suspicious target, the wing vibration characteristics of the suspicious target can be extracted through the UWB module, so as to analyze and judge based on the confidence level of the suspicious target determined based on the physical characteristics of the mosquito and the living probability determined based on the wing vibration characteristics and other two different dimensions of mosquito characteristics, improving the accuracy of the mosquito recognition result.

[0054] Step S12: Determine the living body probability corresponding to the suspicious target according to the wing vibration characteristics extracted by the ultra-wideband module based on the position.

[0055] In this embodiment, when extracting the wing characteristics of the suspicious target through the ultra-wideband module, based on the real-time positioning function of the ultra-wideband module, the vibration signal at the position where the suspicious target is located can be extracted, and through the processing algorithm in the ultra-wideband module, based on the time-frequency analysis of wavelet transform, the vibration spectrum characteristics of the vibration signal can be extracted, so as to determine whether the vibration characteristics of the suspicious target are the wing vibration characteristics of mosquitoes based on the spectrum characteristics.

[0056] Exemplarily, the vibration spectrum characteristics of the suspicious target can be calculated by the following formula:

[0057] where is the wavelet coefficient, which represents the similarity or correlation between the original signal and the wavelet basis function under specific scale and translation parameters. r(t) is the original signal, is the wavelet function, T is the scale parameter, which is used to convert the signal from the time domain to the frequency domain.

[0058] Further, when determining the living body probability of the mosquito corresponding to the wing vibration characteristics, it is necessary to compare the extracted spectrum characteristics with the pre-calibrated characteristic threshold to judge the probability that the vibration characteristics conform to the wing vibration characteristics of mosquitoes, that is, to obtain the living body probability of mosquitoes. Specifically, if the wing vibration characteristics are detected multiple times as the characteristic parameters associated with the preset vibration signal, the living body probability corresponding to the wing vibration characteristics can be analyzed. For example, in the wing vibration characteristics, the vibration frequency, amplitude, period, etc. have a high similarity with the preset vibration signal, that is, the vibration signal of the actual mosquito, and the living body probability of the suspicious target being a mosquito can be calculated based on the similarity of these parameters.

[0059] Step S13: If the weighted average of the confidence of the suspicious target and the living body probability is greater than or equal to the preset threshold, set the mosquito recognition result to the presence of mosquitoes.

[0060] In this embodiment, by performing weighted processing on the confidence level of the suspicious target corresponding to the physical characteristics of the mosquito and the probability of being alive corresponding to the wing vibration characteristics of the mosquito, the weight ratio of the two different dimensional parameters is adjusted, and the weighted average value is compared with the preset survival probability to determine whether there is a mosquito currently. By performing weighted fusion processing on the confidence level of the suspicious target recognized visually and the probability data of being alive judged based on wing vibration, if the weighted average value of the two probabilities is greater than a preset threshold, such as greater than the preset 80%, it is considered that there is a mosquito. At this time, a mosquito recognition result indicating the presence of a mosquito is obtained. Otherwise, a mosquito recognition result indicating the absence of a mosquito is obtained. Through weighted processing, the weight ratio of the confidence levels obtained from the visual dimension and the positioning dimension is adjusted, improving the accuracy of determining the mosquito recognition result based on mosquito characteristics.

[0061] This embodiment provides a control method for an in-vehicle mosquito repellent device. By means of visual analysis of a mosquito feature recognition module, the physical characteristics of mosquitoes are obtained, and by means of precise positioning of an ultra-wideband module, the wing vibration characteristics are obtained. Furthermore, based on the confidence levels / survival probabilities corresponding to the mosquito characteristics in two different dimensions, namely the physical characteristics of mosquitoes and the wing vibration characteristics, the mosquito recognition result is determined. Based on this, the accuracy of mosquito recognition is improved, and furthermore, the effectiveness and intelligence of mosquito repellent treatment by means of a sound wave mosquito repellent device are improved.

[0062] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar content as that in the above first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, the in-vehicle mosquito repellent device further includes an ultra-wideband module. Please refer to Figure 3 , in step S20, the step of determining the action recognition result according to the in-cabin image includes steps S21 to S23: Step S21, perform target detection on the in-cabin image to obtain the suspicious action confidence level and the personnel position of the target person.

[0063] In this embodiment, the detected in-cabin video stream can be input into an action feature recognition module so that the module performs target detection on it through a scratching feature recognition algorithm, thereby obtaining suspicious actions such as scratching actions and slapping actions and the suspicious action confidence level, and at the same time determining the personnel position of the target person performing these suspicious actions.

[0064] Specifically, in this process, the video stream is input into the scratching feature recognition module, and the module analyzes the video frames in real time based on the human pose estimation algorithm to determine whether there is a scratching action, and extracts the scratching features corresponding to the scratching action through the following calculation formula:

[0065] Among them, is the input 4D tensor, that is, the stacking of video frames, with a shape of , is the width, is the height, is the depth, i.e., the time dimension, is the number of channels (RGB); is the 3D convolutional kernel , is the size of the convolutional kernel in the spatial dimension, is the number of input channels, is the number of output channels; is the index in the spatial dimension, is the depth of the output feature map.

[0066] Based on this, key features of scratching actions such as the hand quickly approaching the face or the hand quickly rubbing on the arm are extracted through the above formula, and then extracted and abstracted to obtain suspicious actions. In addition, long-term action capture can be performed through the LSTM recurrent layer to improve the accuracy of the extracted scratching features. After obtaining the suspicious actions, they are parsed to obtain the corresponding confidence levels of the suspicious actions.

[0067] Further, after identifying suspicious actions such as scratching actions of the personnel in the cockpit, by positioning the target occupant's position, converting its position in the cockpit to the vehicle coordinate system and sending it to the ultra-wideband module, the breathing features of the target person are extracted based on the ultra-wideband module.

[0068] Step S22: Determine the average breathing change frequency corresponding to the target person according to the breathing features extracted by the ultra-wideband module based on the personnel position.

[0069] In this embodiment, after sending the position information to the ultra-wideband module, the ultra-wideband module acquires the breathing signal corresponding to the position information and performs wavelet transform processing on the breathing signal to obtain the breathing features of the target person.

[0070] Specifically, the wavelet transform formula is as follows:

[0071] where, is the result of wavelet transform, is the scale parameter, is the translation parameter, is the input signal; is the wavelet function, is the complex conjugate of the wavelet function; is the normalization factor to ensure consistent energy at different scales.

[0072] Based on this, wavelet transform analysis is performed on the breathing signals collected in real time by the ultra-wideband module to monitor the breathing pattern of the target person in real time, and then the corresponding breathing characteristics are obtained. After obtaining the breathing characteristics, the average breathing change frequency of the target person is directly determined based on the breathing characteristics. For example, if the breathing characteristic is that the average breathing frequency is a within the past 1 minute and the average breathing frequency 1 minute ago is b, the average breathing change frequency is obtained by a - b.

[0073] Step S23, if the suspicious action confidence is greater than or equal to the preset action confidence, the number of times of the suspicious action execution is greater than or equal to the preset number, and the average breathing change frequency is greater than or equal to the preset frequency, set the action recognition result as the existence of a mosquito repelling action.

[0074] Exemplarily, if the target person has scratching actions with a confidence level greater than 90% twice within 30s, and it is detected by the ultra-wideband module that the average breathing frequency within one minute is 4 times / minute higher than the average breathing frequency within the previous ten minutes, which exceeds the preset breathing frequency, it is considered that there are mosquitoes near the user at this time. When the user drives away the mosquitoes by slapping actions, a tense emotion is generated, resulting in an increase in breathing. Based on this, it is considered that there are mosquitoes around this person, and then an action recognition result indicating the existence of a mosquito repelling action is generated to represent the current presence of mosquitoes.

[0075] This embodiment provides a control method for an in-vehicle mosquito repelling device. By means of visual analysis, the scratching characteristics of the scratching action are obtained. At the same time, by means of the precise positioning of the ultra-wideband module, the breathing characteristics of the target person triggering the scratching action are obtained. Then, based on the confidence levels corresponding to the action characteristics in two different dimensions, namely the scratching characteristics and the breathing characteristics, and the average breathing change frequency, the action recognition result is determined. Based on this, the accuracy of mosquito recognition by action recognition is improved, and further the effectiveness and intelligence of mosquito repelling treatment by the sound wave mosquito repelling device are improved.

[0076] Based on any of the above embodiments, in the fourth embodiment of the present application, when any of the following conditions is met, the in-vehicle mosquito repelling device is controlled to execute the action in step S10: The current month is the preset month, the current temperature is within the preset temperature range, the current location is at the preset latitude, and the current humidity is greater than the preset humidity, the current time is from the preset sunrise time to the preset sunset time, and the weather at the current location is rainy within the preset time.

[0077] It can be understood that if the current time is between March and November or the current external temperature is between 20°C and 30°C, it indicates that the external environment where the current vehicle is located is suitable for mosquito activities. Therefore, real-time mosquito monitoring is required. It can be understood that the preset month information can be determined according to the current regional information. For example, the months with high-frequency mosquito activities in the current region are from February to December, and the preset month is determined to be from February to December. Or the preset month can be determined according to historical detection results. For example, the in-vehicle mosquito repellent device is usually turned on from March to November and not turned on in other months. At this time, the preset month can be determined to be from March to November. The above month information is only for explanation and is not a limitation to this application.

[0078] Exemplarily, if the current location of the vehicle is between 40°N and 40°S, or the relative humidity exceeds 70%, mosquito detection is required. If the current time is within one hour before sunset to one hour after sunrise at the geographical location of the vehicle, mosquito monitoring is also required. Mosquito detection is still required within 24 hours after rainfall at the geographical location where the vehicle is located.

[0079] This application provides an in-vehicle mosquito repellent device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the control method of the in-vehicle mosquito repellent device in the above first embodiment.

[0080] Next, refer to Figure 4 , which shows a schematic structural diagram of an in-vehicle mosquito repellent device suitable for implementing the embodiments of this application. Figure 4 The in-vehicle mosquito repellent device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0081] As Figure 4As shown, the in-vehicle mosquito repellent device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the in-vehicle mosquito repellent device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the in-vehicle mosquito repellent device to communicate with other devices wirelessly or wiredly to exchange data. Although the in-vehicle mosquito repellent device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0082] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0083] The in-vehicle mosquito repellent device provided in the present application adopts the control method of the in-vehicle mosquito repellent device in the above embodiment, and can solve the technical problem that the mosquito repellent effect is poor due to the need to manually turn on the mosquito repellent device. Compared with the prior art, the beneficial effects of the in-vehicle mosquito repellent device provided in the present application are the same as those of the control method of the in-vehicle mosquito repellent device provided in the above embodiment, and other technical features in the in-vehicle mosquito repellent device are the same as those disclosed in the previous embodiment method, and will not be elaborated here.

[0084] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0085] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0086] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the control method of the vehicle-mounted mosquito repellent device in the above embodiments.

[0087] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0088] The above computer-readable storage medium can be included in the vehicle-mounted mosquito repellent device; it can also exist separately without being assembled into the vehicle-mounted mosquito repellent device.

[0089] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the vehicle-mounted mosquito repellent device, the vehicle-mounted mosquito repellent device is caused to: Determine the mosquito recognition result based on the in-cabin image collected by the image acquisition device; Determine the action recognition result based on the in-cabin image; Determine the mosquito repellent mode according to the mosquito recognition result and the action recognition result; Control the sonic mosquito repellent device to operate according to the operating parameters corresponding to the mosquito repellent mode.

[0090] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., by connecting through an Internet service provider using the Internet).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0092] The modules involved in the embodiments of the present application may be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0093] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the control method of the above vehicle-mounted mosquito repellent device, which can solve the technical problem that the mosquito repellent effect is poor due to the need to manually turn on the mosquito repellent device. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the control method of the vehicle-mounted mosquito repellent device provided in the above embodiments, and will not be elaborated here.

[0094] The above are only some embodiments of this application, and thus do not limit the patent scope of this application. Any equivalent structural transformation made under the technical concept of this application by using the content of the specification and drawings of this application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of this application.

Claims

1. A control method for a vehicle-mounted mosquito repellent device, characterized in that: Applied to a vehicle-mounted mosquito repellent device, the vehicle-mounted mosquito repellent device includes an image acquisition device and a sound wave mosquito repellent device, and the control method of the vehicle-mounted mosquito repellent device includes: Determining a mosquito identification result based on the cabin image captured by the image acquisition device; Determining an action recognition result based on the in-cabin image; Determining a mosquito repellent mode according to the mosquito identification result and the action identification result; The sonic mosquito repellent device is controlled to operate according to the operating parameters corresponding to the mosquito repellent mode.

2. The control method of the vehicle-mounted mosquito repellent device according to claim 1, characterized in that: The step of determining the mosquito identification result based on the cabin image collected by the image acquisition device comprises: Performing target detection on the image in the cockpit to obtain a confidence level of a suspicious target; If there is a suspicious target whose confidence level is greater than or equal to a preset confidence level, the mosquito identification result is set as the presence of mosquitoes.

3. The control method of the vehicle-mounted mosquito repellent device according to claim 1, characterized in that: The vehicle-mounted mosquito repellent device further includes an ultra-wideband module, and the step of determining the mosquito identification result based on the cabin image acquired by the image acquisition device further includes: Performing target detection on the image in the cockpit to obtain the confidence level of the suspicious target and the position of the suspicious target; Determining the probability of a live object corresponding to the suspicious target according to the wing vibration characteristics extracted by the ultra-wideband module based on the position; If the weighted average of the suspicious target confidence and the live probability is greater than or equal to a preset threshold, the mosquito identification result is set to the presence of mosquitoes.

4. The control method of the vehicle-mounted mosquito repellent device according to claim 1, characterized in that: The step of determining the action recognition result based on the in-cabin image comprises: Performing target detection on the image in the cockpit to obtain a confidence level of a suspicious action; If the suspicious action confidence is greater than or equal to the preset suspicious confidence, and the suspicious action is performed more than or equal to the preset number of times within the preset time, the action recognition result is set to indicate that there is a mosquito repelling action.

5. The control method of the vehicle-mounted mosquito repellent device according to claim 1, characterized in that: The vehicle-mounted mosquito repellent device further includes an ultra-wideband module, and the step of determining the action recognition result based on the image in the cabin further includes: Performing target detection on the image in the cockpit to obtain the confidence level of the suspicious action and the position of the target person; Determine the average breathing change frequency corresponding to the target person according to the breathing characteristics extracted by the ultra-wideband module based on the position of the person; If the suspicious action confidence is greater than or equal to the preset action confidence, the number of suspicious action executions is greater than or equal to the preset number, and the average breathing change frequency is greater than or equal to the preset frequency, the action recognition result is set as the presence of a mosquito repellent action.

6. The control method of the vehicle-mounted mosquito repellent device according to claim 1, characterized in that: The mosquito repelling mode includes a direct mosquito repelling mode and an indirect mosquito repelling mode, and the step of controlling the acoustic mosquito repelling device to operate according to the operating parameters corresponding to the mosquito repelling mode includes: If the mosquito repellent mode is the direct mosquito repellent mode, controlling the acoustic mosquito repellent device to operate based on preset parameters until the mosquito identification result is that there are no mosquitoes; If the mosquito repellent mode is the indirect mosquito repellent mode, the operation of the acoustic mosquito repellent device is controlled based on a preset time period and preset parameters.

7. The control method of the vehicle-mounted mosquito repellent device according to claim 6, characterized in that: The step of determining the mosquito repellent mode according to the mosquito identification result and the action identification result comprises: If the mosquito identification result is that mosquitoes are present, determining that the mosquito repellent mode is the direct mosquito repellent mode; If the action recognition result is that there is a mosquito repelling action, and the mosquito recognition result is that there is no mosquito, it is determined that the mosquito repelling mode is the indirect mosquito repelling mode.

8. The control method of the vehicle-mounted mosquito repellent device according to any one of claims 1 to 7, characterized in that: When any of the following conditions is met, the step of determining the mosquito identification result based on the cabin image acquired by the image acquisition device is performed: The current month is the preset month; The current temperature is within the preset temperature range; The current location is at the preset latitude; The current humidity is greater than the preset humidity; The current time is from the preset sunrise time to the preset sunset time.

9. A vehicle-mounted mosquito repellent device, characterized in that: The vehicle-mounted mosquito repellent device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the vehicle-mounted mosquito repellent device according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the control method of the vehicle-mounted mosquito repellent device according to any one of claims 1 to 8 are implemented.

Images