Method and device for monitoring eclosion of fruit fly insects

Abstract

The invention discloses a fruit fly insect eclosion monitoring method and device, and the method comprises the steps: obtaining the illumination intensity in an adult cabin in response to an infrared signal transmitted by an infrared sensor; a first instruction is sent out, the first instruction is used for controlling a camera to shoot a first image of the plane where the joint of the eclosion bin and the adult bin is located and recording the first sending moment of the first instruction, and under the condition that the illumination intensity is smaller than a preset light intensity threshold value, a light supplementing lamp is controlled to be turned on; performing image recognition on the first image to obtain a first number of the fruit fly insects in a plane where the joint of the eclosion bin and the adult bin is located and features before wing spreading; determining the eclosion cycle of the fruit fly insects, and calculating the difference value between the first number and the second number; and determining the current eclosion condition of the fruit fly insects according to the difference value and the eclosion period, wherein the current eclosion condition comprises the eclosion rate and the eclosion rate. According to the application, the accuracy of monitoring the eclosion stage of the fruit fly insects can be effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of insect trapping and monitoring, and in particular to a method and device for monitoring the emergence of fruit fly insects. Background Art

[0002] The fruit fly, commonly known as the "citrus maggot", is a global plant quarantine pest and one of the most serious pests that harm citrus. Since the eggs, larvae, and pupae of the fruit fly live in a relatively hidden environment that is difficult to find, it is impossible to effectively prevent and control them, causing economic losses to fruit farmers. Currently, the main way to effectively prevent and control the fruit fly is to spray pesticides during the emergence stage of the fruit fly. Therefore, it is very important to monitor the emergence stage of the fruit fly.

[0003] In order to determine whether the fruit flies are in the emergence stage, currently the main method is to set up fruit fly traps in the monitoring area, and determine whether the fruit flies in the monitoring area are in the emergence stage by checking whether the fruit flies in the traps are in the emergence stage. Existing traps are usually equipped with light sources or food that attracts fruit flies to enter, so as to attract fruit flies to fly in and be captured. Through the traps, monitoring personnel can regularly check the number and status of captured fruit flies to determine whether they are in the emergence stage. The physiological state of the captured adults can be further analyzed, such as whether the wings are fully spread, whether the body color is mature, etc., so as to determine the emergence of fruit flies and calculate the progress of emergence. This monitoring method is crucial for formulating effective fruit fly prevention and control measures and determining the timing of spraying pesticides.

[0004] However, in production, monitoring of fruit fly insects is often done by manually burying pupae, which not only consumes a lot of manpower, but also often leads to missing the critical period of emergence due to untimely observation, affecting the accuracy of monitoring and forecasting, and further affecting the formulation of prevention and control measures and the best time for prevention and control. Summary of the invention

[0005] The embodiments of the present application provide a method and device for monitoring the emergence of fruit flies, which are used to effectively improve the accuracy of monitoring the emergence of fruit flies.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In a first aspect, a method for monitoring the emergence of fruit fly insects is provided, which is applied to a fruit fly insect monitoring device, wherein the fruit fly insect monitoring device comprises a box, an emergence chamber, an adult chamber and a hollow frame, wherein the emergence chamber and the adult chamber are arranged in the box, and at least one infrared sensor is respectively arranged at the outlet of the emergence chamber and the entrance of the adult chamber, the emergence chamber is arranged as a whole in a soil environment, and the adult chamber is arranged as a whole on the ground, the adult chamber is a structure that is narrow at the top and wide at the bottom, and a camera and a fill light for monitoring fruit fly insects are arranged in the adult chamber, the top of the adult chamber is seamlessly connected to the hollow frame, and at least one counting sensor is arranged in the hollow frame, and the method comprises: In response to the infrared signal transmitted by the infrared sensor, obtaining the light intensity in the adult chamber; Issuing a first instruction, wherein the first instruction is used to control the camera to capture a first image of the plane where the eclosion chamber and the adult chamber are connected, and recording a first issuance time of the first instruction, and starting timing from the first issuance time, wherein, when the light intensity is less than a preset light intensity threshold, controlling the fill light to turn on; Performing image recognition on the first image to obtain a first number and pre-wing features of the fruit fly insects on a plane where the eclosion bin and the adult bin are connected; determining the emergence period of fruit fly insects, and calculating the difference between the first number and the second number; The current emergence status of the fruit fly insects is determined according to the difference and the emergence period, wherein the current emergence status includes an emergence rate and an emergence speed.

[0007] In a possible implementation manner of the first aspect, determining the emergence period of fruit fly insects includes: After the first sending moment, the camera is controlled to capture an image at every preset time interval, and image recognition is performed on each captured image to obtain the number of fruit fly insects; Taking an image corresponding to when the number of fruit fly insects is less than a preset number threshold as a final image, and obtaining a shooting time of the final image; The difference between the shooting time and the first sending time is used as the emergence period of the fruit fly insect.

[0008] In a possible implementation manner of the first aspect, a photoelectric sensor is further provided in the adult insect chamber, and before determining the emergence period of the fruit fly insects, the method includes: In response to receiving the photoelectric data transmitted by the photoelectric sensor, determining the fully spread wings feature of the fruit fly insects in the adult insect bin according to the photoelectric data; issuing a second instruction, wherein the second instruction is used to control the camera to capture a second image of the plane where the emergence chamber and the adult chamber are connected; Performing image recognition on the second image to obtain a second number of fruit fly insects on a plane where the emergence bin and the adult bin are connected; Acquire current environmental data, wherein the current environmental data includes temperature data, humidity data and sunshine time; Determining the maturity of the fruit fly insects in the adult insect bin by using the current environmental data and the fully spread wings feature; The first number, the second number and the current environmental data are input into a pre-trained prediction model to predict the future peak emergence time period of fruit fly insects.

[0009] In a possible implementation manner of the first aspect, a tunable light source is provided in the adult insect chamber, the photoelectric data includes the light intensity in the adult insect chamber and light wave reflection data of the wing surface of the fruit fly insect under the tunable light source, and determining the fully spread wings feature of the fruit fly insect in the adult insect chamber according to the photoelectric data includes: When the light intensity in the adult insect bin is greater than a preset first light intensity threshold, determining that the wavelength range of the tunable light source is a target wavelength range, and adjusting the wavelength of the tunable light source to within the target wavelength range; Acquire spectral characteristic data of the wings of giant flies at different growth stages through a preset spectral characteristic database, and compare the light wave reflection data with the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data, and obtain the number of fruit fly insects corresponding to each growth stage; According to the growth stage corresponding to the light wave reflection data, the fully spread wings feature of the fruit fly insects in the adult insect bin is obtained by querying in a preset feature database.

[0010] In a possible implementation manner of the first aspect, comparing the light wave reflection data with the spectral feature data to obtain the growth stage corresponding to the light wave reflection data, and obtaining the number of fruit fly insects corresponding to each growth stage, includes: Performing spectral analysis on the light wave reflection data to obtain a first spectral bandwidth, a first peak position, and a first peak intensity of the light wave reflection data; Acquire a second spectral bandwidth, a second peak position, and a second peak intensity of the spectral characteristic data; According to a preset feature matching algorithm, calculating a first matching degree between the first spectral bandwidth and the second spectral bandwidth, a second matching degree between the first peak position and the second peak position, and a third matching degree between the first peak intensity and the second peak intensity; The sum of the first matching degree, the second matching degree and the third matching degree is used as the target matching degree between the light wave reflection data and the spectral feature data; In the case where the target matching degree is greater than a preset matching degree threshold, determining that the light wave reflection data matches the spectral feature data, and taking the growth stage corresponding to the spectral feature data as the growth stage corresponding to the light wave reflection data matched therewith; The number of fruit fly insects corresponding to each growth stage is obtained by counting.

[0011] In a possible implementation of the first aspect, performing image recognition on the first image to obtain a first number and pre-wing features of the fruit fly insects on a plane where the emergence bin and the adult bin are connected includes: Preprocessing the first image to obtain multiple image features; The first quantity and pre-wing-spreading features of the fruit fly insects on the plane where the emergence bin and the adult bin are connected are determined from the plurality of image features.

[0012] In a possible implementation manner of the first aspect, after performing image recognition on the first image to obtain a first number and pre-wing features of the fruit fly insects on a plane where the emergence bin and the adult bin are connected, the method includes: Screening the features before wingspan to obtain key features; Based on a preset mapping rule, the key features are mapped to obtain corresponding key feature interpretations; According to the key feature interpretation, determining the keyword range in a preset feature database; In the keyword range, the keyword corresponding to the key feature interpretation is determined and output.

[0013] In a possible implementation manner of the first aspect, the method further includes: In the case where the key feature cannot be mapped to obtain a corresponding key feature interpretation, performing image recognition on the first image to obtain a plurality of color features; A cross black horizontal stripe feature and a golden yellow body color feature are screened out from the plurality of color features, and the cross black horizontal stripe feature and the golden yellow body color feature are used as the second target key features; Obtaining the associated interpretation of the key feature interpretation, and expanding the keyword range according to the associated interpretation to obtain a second keyword range; In the second keyword range, the keyword corresponding to the second target key feature is determined and output.

[0014] In a possible implementation manner of the first aspect, before determining the keyword range in a preset feature database according to the key feature interpretation, the method includes: The characteristics of each growth stage of the giant fly are stored in the preset characteristic database, and the to-be-searched range of the preset characteristic database is set; Determining and outputting the keywords corresponding to the key feature interpretation within the keyword range includes: In the range to be searched, the keyword is located, and the growth stage characteristics corresponding to the keyword are determined, wherein the growth stage characteristics corresponding to the keyword are used to characterize the current growth stage of the giant fruit fly in the monitoring area.

[0015] In a second aspect, the present application provides a fruit fly insect monitoring device, the fruit fly insect monitoring device comprising a box body, an embryo chamber, an adult chamber and a hollow frame, the embryo chamber and the adult chamber are arranged in the box body, at least one infrared sensor is respectively arranged at the outlet of the embryo chamber and the entrance of the adult chamber, the embryo chamber is arranged as a whole in a soil environment, the adult chamber is arranged as a whole on the ground, the adult chamber is a narrow upper and wide lower structure, and a camera and a fill light for monitoring fruit fly insects are arranged in the adult chamber, the top of the adult chamber is seamlessly connected to the hollow frame, at least one counting sensor is arranged in the hollow frame, and the fruit fly insect monitoring device also includes: a memory configured to store instructions; and The processor is configured to call the instructions from the memory and implement the above-mentioned method for monitoring the emergence of fruit fly insects when executing the instructions.

[0016] Through the above technical solution, the infrared sensor is set at the connection between the eclosion chamber and the adult chamber. When the infrared sensor detects the movement of the fruit fly insects, it can automatically issue a command to control the camera to capture images and record the shooting time, which effectively reduces the delay of manual operation and improves the timeliness of monitoring. It can also detect the movement of the fruit fly insects in real time, reducing the time interval of manual regular inspections, and ensuring that the critical time of the eclosion of the fruit fly insects will not be missed; the camera is set in the adult chamber to capture the image of the plane at the connection between the eclosion chamber and the adult chamber. By identifying the captured image, the number of fruit fly insects and the features before wing expansion can be obtained, which effectively improves the accuracy of data collection, reduces the subjective error of human judgment, and thus improves the accuracy of monitoring; the fill light is automatically adjusted according to the light intensity to ensure that the image can be clearly captured even in the case of insufficient light. When the infrared sensor detects the movement of the fruit fly insects, the light intensity in the adult chamber is automatically obtained, and a first command is issued to control the camera to capture the image at the connection between the eclosion chamber and the adult chamber, and record the shooting time. Subsequently, the captured image is identified to obtain the number of fruit fly insects and the features before wing expansion. Through historical data and current data, the emergence period of fruit fly insects is determined, and the difference between the current number and the historical number is calculated to evaluate the emergence situation. According to the difference and the emergence period, the emergence rate and emergence speed are calculated to provide data support for prevention and control measures. Through automated monitoring, intelligent control and data analysis, the monitoring accuracy of the emergence stage of fruit fly insects is significantly improved, the time interval for manual monitoring is reduced, ensuring that the critical time for the emergence of fruit fly insects is not missed, and the risk of missed detection is reduced. The automatic adjustment of the fill light and the application of image recognition technology have improved the quality of image acquisition and the accuracy of recognition, providing a scientific basis for formulating effective prevention and control measures and determining the timing of spraying pesticides.

[0017] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a process for monitoring the emergence of fruit flies provided in an embodiment of the present application; Figure 2 A schematic diagram of the overall structure of a fruit fly insect monitoring device provided in an embodiment of the present application; Figure 3 A front view of a fruit fly insect monitoring device provided in an embodiment of the present application; Figure 4 A rear view of a fruit fly insect monitoring device provided in an embodiment of the present application; Figure 5 A partial structural schematic diagram of a fruit fly insect monitoring device provided in an embodiment of the present application.

[0019] Description of Reference Numerals 10 Fruit fly insect monitoring device box 20 Adult chamber 30 Feathering Warehouse 40 Counting sensor 50 Camera 60 Fill Light DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0022] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0023] Figure 1 The following is a schematic diagram showing a process flow of a method for monitoring the emergence of fruit flies according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for monitoring the emergence of fruit fly insects, which is applied to a fruit fly insect monitoring device. The fruit fly insect monitoring device includes a box body, an emergence chamber, an adult chamber and a hollow frame. The emergence chamber and the adult chamber are arranged in the box body, and at least one infrared sensor is respectively provided at the exit of the emergence chamber and the entrance of the adult chamber. The emergence chamber is arranged as a whole in a soil environment, and the adult chamber is arranged as a whole on the ground. The adult chamber is a structure that is narrow at the top and wide at the bottom, and a camera and a fill light for monitoring fruit fly insects are provided in the adult chamber. The top of the adult chamber is seamlessly connected to the hollow frame, and at least one counting sensor is provided in the hollow frame. The method may include the following steps.

[0024] S110, obtaining the light intensity in the adult chamber in response to the infrared signal transmitted by the infrared sensor; S120, issuing a first instruction, the first instruction is used to control the camera to capture a first image of the plane where the eclosion chamber and the adult chamber are connected, and record the first issuance time of the first instruction, and start timing from the first issuance time, wherein, when the light intensity is less than a preset light intensity threshold, the fill light is controlled to turn on; S130, performing image recognition on the first image to obtain a first number of fruit fly insects and features before wing expansion on a plane where the emergence bin and the adult bin are connected; S140, determining the emergence period of fruit fly insects, and calculating the difference between the first number and the second number; S150, determining the current emergence status of the fruit fly insects according to the difference and the emergence period, wherein the current emergence status includes an emergence rate and an emergence speed.

[0025] The fruit fly insects in this embodiment can be trapped into the emergence chamber, or the fruit fly insects can be monitored by placing citrus fruits containing fly eggs in the emergence chamber.

[0026] In this embodiment, the fruit fly insect monitoring device can be applied to fruit fly insects. The following takes the fruit fly as an example. Figure 2 and Figure 3 The housing 10 of the fruit fly insect monitoring device includes an emergence chamber 30, an adult chamber 20 and a camera 50, wherein the emergence chamber 30, the adult chamber 20 and the camera 50 are all located in a monitoring area within the housing 10 of the fruit fly insect monitoring device, and the monitoring area is used to monitor the growth activities of fruit fly insects. The adult chamber 20 is arranged on the upper side of the emergence chamber 30, and at least one infrared sensor is respectively provided at the exit of the emergence chamber and the entrance of the adult chamber. Due to the biological characteristics of fruit fly insects, the adult chamber 20 is designed to be a structure that is narrow at the top and wide at the bottom, so as to allow fruit fly insects to fly from the bottom of the adult chamber 20 to the top, so as to better monitor the fruit fly insects. The adult chamber 20 is provided with a camera 50, a photoelectric sensor and a counting sensor 40. In order to better simulate the natural environment, the surroundings and the top of the housing 10 of the fruit fly insect monitoring device are provided with transparent observation panels, such as Figure 4 As shown, the box body is surrounded by transparent observation panels, and the material of the transparent observation panels is not limited in this application.

[0027] In the specific implementation, the emergence chamber 30 is buried in the soil to simulate the living environment of the fruit fly in nature, so as to ensure that the living environment of the fruit fly in the monitoring area is consistent with that of the outside world. Figure 4The transparent monitoring board shown is used to ensure that the light and temperature inside the monitoring area are suitable, which is convenient for observing the inside of the monitoring area. The infrared sensor is used to determine whether there is an infrared signal of the fruit fly. If the infrared signal of the fruit fly inside the monitoring area is received, the camera 50 above the device will take an image, automatically transmit it back and store the photo. According to the biological characteristics of the fruit fly, the fruit fly will gather upward along the conical structure of the adult bin, gradually gather at the top position of the conical structure, and the fruit flies will be counted by the counting sensor 40 above the conical structure and the data will be stored using a storage device.

[0028] Specifically, Figure 5 FIG. 1 shows a partial structural diagram of a fruit fly insect monitoring device provided in an embodiment of the present application. Figure 5 As shown, the camera 50 is fixed in the adult insect bin, and is used to capture a first image of the plane where the emergence bin and the adult insect bin are connected. Image recognition and analysis are then performed on the first image to obtain the first number of fruit fly insects after they emerge from the emergence bin and their features before they spread their wings. By regulating the light intensity in the monitoring area, the photoelectric sensor can be used to obtain the light wave data reflected by the wings of the fruit fly insects in the monitoring area to determine the growth stage of the fruit fly insects.

[0029] When the infrared sensor in the emergence chamber or the adult chamber captures the activity of fruit flies, an infrared signal will be triggered immediately and transmitted to the controller, wherein the controller can be a processor, a service terminal or other intelligent terminal. At this time, the controller will synchronously obtain the current light intensity in the adult chamber. Non-contact monitoring can be achieved through infrared technology, which can effectively avoid interference with the natural behavior of fruit flies. In a specific implementation, if the light intensity is lower than a preset threshold, such as lower than 200 lux, the fill light 60 is automatically activated to ensure that the camera 50 can clearly capture the picture, providing a high-quality data basis for subsequent image analysis.

[0030] Next, a first instruction is issued to control the camera 50 to capture the first image of the plane at the connection between the emergence chamber and the adult chamber, and the first issuance time of the instruction is recorded. The triggering of the first instruction is based on the feedback of the infrared sensor, which means that the image acquisition process will be started only when the fruit fly activity is detected, thereby effectively saving storage resources and processing time. In actual operation, the camera 50 is configured in high-definition mode and records the video at a speed of 30 frames per second to ensure that every detail of the emergence of the fruit fly is captured. At the same time, if the light is insufficient, the fill light 60 automatically lights up to assist in shooting.

[0031] Image analysis can be performed on the first image collected. An image recognition algorithm can be used to automatically identify and count the number of fruit flies at the junction of the emergence chamber and the adult chamber, and identify specific morphological features of the large fruit flies before they spread their wings, such as the presence of a pupal shell and incompletely spread wings. This can be achieved through a pre-trained machine learning model, which can learn from a large number of samples and accurately distinguish between different life stages and behavioral states of fruit flies. In specific implementation, the image recognition algorithm will traverse every pixel in the image, looking for pixel clusters that meet the characteristics of fruit flies, and then complete counting and feature extraction.

[0032] The emergence cycle can be obtained through historical experience. By comparing the changes in the number of fruit flies in images taken at different time points, the difference between the first number (the number at the initial monitoring) and the second number in the subsequent monitoring is calculated to track the growth or decrease of the fruit fly population in a specific time period, providing a quantitative basis for evaluating the emergence efficiency.

[0033] Finally, according to the difference in the number of fruit flies and the known emergence period, the emergence rate and emergence speed are calculated to reflect the reproductive capacity and emergence speed of the fruit fly population. The emergence rate refers to the proportion of individuals that successfully emerge as adults to the total number of pupae, while the emergence rate describes the number of adults that emerge per unit time. Through the emergence rate and emergence speed, we can further analyze the impact of environmental factors, food sources, etc. on the emergence of fruit flies, and provide precise guidance for agricultural pest control. In summary, this fruit fly insect emergence monitoring method realizes all-round and high-precision monitoring of the fruit fly emergence process through intelligent and automated means, which not only improves the monitoring efficiency, but also provides strong technical support for fruit fly ecology research and pest management practices.

[0034] Through the above technical solution, the infrared sensor is arranged at the connection between the eclosion chamber and the adult chamber. When the infrared sensor detects the movement of the fruit fly insects, it can automatically issue an instruction to control the camera to capture images and record the shooting time, which effectively reduces the delay of manual operation, improves the timeliness of monitoring, and can detect the movement of the fruit fly insects in real time, reducing the time interval of manual regular inspection, and ensuring that the critical time of the eclosion of the fruit fly insects will not be missed; the camera is arranged in the adult chamber, used to capture the image of the plane at the connection between the eclosion chamber and the adult chamber, and by identifying the captured image, the number of fruit fly insects and the features before wing-spreading can be obtained, which effectively improves the accuracy of data collection, reduces the subjective error of human judgment, and thus improves the accuracy of monitoring; the fill light is automatically adjusted according to the light intensity to ensure that the image can be clearly captured even in the case of insufficient light, wherein the fill light can be a tunable light source. When the infrared sensor detects the movement of the fruit fly insects, the light intensity in the adult chamber is automatically obtained, and a first instruction is issued to control the camera to capture the image at the connection between the eclosion chamber and the adult chamber, and record the shooting time. Subsequently, the captured image is identified to obtain the number of fruit fly insects and the features before wing-spreading. Through historical data and current data, the emergence period of fruit fly insects is determined, and the difference between the current number and the historical number is calculated to evaluate the emergence situation. According to the difference and the emergence period, the emergence rate and emergence speed are calculated to provide data support for prevention and control measures. Through automated monitoring, intelligent control and data analysis, the monitoring accuracy of the emergence stage of fruit fly insects is significantly improved, the time interval for manual monitoring is reduced, ensuring that the critical time for the emergence of fruit fly insects is not missed, and the risk of missed detection is reduced. The automatic adjustment of the fill light and the application of image recognition technology have improved the quality of image acquisition and the accuracy of recognition, providing a scientific basis for formulating effective prevention and control measures and determining the timing of spraying pesticides.

[0035] In one implementation of this embodiment, determining the emergence period of fruit fly insects includes the following steps: S210, after the first sending moment, controlling the camera to capture an image at every preset time interval, and performing image recognition on each captured image to obtain the number of fruit fly insects; S220, taking an image corresponding to when the number of fruit fly insects is less than a preset number threshold as a final image, and obtaining a shooting time of the final image; S230: taking the difference between the shooting time and the first sending time as the emergence period of the fruit fly insects.

[0036] After the first instruction is issued, the camera is controlled to capture images periodically. During this process, the camera can be automatically triggered to capture the fruit fly insects at the connection between the emergence chamber and the adult chamber according to a preset time interval, such as every hour or every two hours. After each shot, the image recognition algorithm is immediately activated to accurately count the number of fruit fly insects in the image. During implementation, the image recognition algorithm analyzes each pixel in the image, and accurately identifies and counts the fruit fly insects from the complex background by comparing their morphological characteristics, such as body shape and color. Finally, a series of time series data reflecting the changes in the number of fruit fly insects can be obtained, realizing continuous and dynamic monitoring of the emergence process of fruit fly insects.

[0037] By analyzing the time series data, when the number of fruit fly insects drops below a preset number threshold for the first time, the image corresponding to that moment is marked as the final image, and the shooting time is recorded. For example, it can be set to 10% of the initial number to capture the time point when the emergence activity is basically over. This embodiment can mark the end of the emergence cycle by a significant reduction in the number, thereby avoiding misjudgment due to individual differences or accidental factors.

[0038] By calculating the time difference between the time when the final image was taken and the time when the first instruction was issued, the emergence period of fruit flies can be obtained. For example, if the first instruction was issued at 9 am on June 1, and the final image was taken at 10 am on June 8, then the emergence period is 7 days plus 1 hour.

[0039] This embodiment can accurately and efficiently determine the emergence period of fruit fly insects through periodic shooting, quantity monitoring and time difference calculation. It not only greatly reduces the burden of manual monitoring, but also provides a direct quantitative indicator of the emergence time of fruit fly insects, which helps to deeply understand the biological characteristics of fruit fly insects, provides a scientific basis for formulating targeted prevention and control measures, and improves the accuracy and reliability of data.

[0040] In one implementation of this embodiment, a photoelectric sensor is further provided in the adult insect chamber, and before determining the emergence period of fruit fly insects, the following steps are included: S310, in response to receiving photoelectric data transmitted by the photoelectric sensor, determining the fully spread wings feature of the fruit fly insects in the adult insect bin according to the photoelectric data; S320, issuing a second instruction, the second instruction is used to control the camera to capture a second image of the plane where the eclosion chamber and the adult chamber are connected; S330, performing image recognition on the second image to obtain a second number of fruit fly insects on a plane where the emergence bin and the adult bin are connected; S340, obtaining current environmental data, the current environmental data including temperature data, humidity data and sunshine time; S350, determine the maturity of fruit fly insects in the adult chamber by using current environmental data and fully spread wings characteristics; S360: Input the first quantity, the second quantity and the current environmental data into a pre-trained prediction model to predict the future peak emergence time period of fruit fly insects.

[0041] In this embodiment, the photoelectric sensor can accurately sense the intensity of light and the movement of objects. When the fruit fly insects complete their emergence and spread their wings, their body shape and the reflected light from their wings will trigger the sensor and generate specific photoelectric data. By analyzing the photoelectric data and comparing it with the preset full-wing feature model, such as the angle and area change of the wings, it can be accurately identified that the fruit fly insects have reached the full-wing state.

[0042] The second command is issued to drive the camera to capture the real-time image of the connection between the emergence chamber and the adult chamber to ensure that the timing of image capture is highly consistent with the emergence state of the fruit fly insects. The images captured by the camera include the key moment when the fruit fly insects enter the adult chamber from the emergence chamber, providing an intuitive visual basis for subsequent population statistics and emergence peak prediction.

[0043] Perform image recognition on the captured second image to obtain the number of fruit fly insects in the second image, that is, the second number. Then, obtain current environmental data, which includes temperature, humidity and sunshine time.

[0044] Next, the maturity of fruit flies can be further analyzed by combining the fully spread wings of fruit flies with the current environmental data. By building a mathematical model and taking into account the physiological state of fruit flies and the external environment, it is possible to infer the time required for fruit flies to reach a reproductive state, i.e., maturity, which helps to more accurately predict the peak of emergence and population dynamics of fruit flies.

[0045] Specifically, the maturity of fruit fly insects in the adult chamber can be determined through current environmental data and fully spread wings characteristics by constructing a nonlinear regression model.

[0046] First, assume that the maturity (M) of fruit flies is a function of age (A), temperature (T), humidity (H), etc.: M=f(A,T,H,……); Among them, f() is a nonlinear function. Through the current environmental data (temperature, humidity, food supply, light conditions, etc.) and the full wing characteristics (age, wing spread, etc.), the least squares method, maximum likelihood estimation or other optimization algorithms can be used to estimate the parameters in the nonlinear regression model. The prediction performance of the model is evaluated by cross-validation, and the model structure or parameters are adjusted according to the validation results to improve the prediction accuracy. Finally, the model is applied to predict the maturity of fruit flies in the new environment. For example, given a specific set of age, temperature, humidity and other conditions, the model can output the predicted maturity value. Suppose there is a simplified nonlinear regression model in which the maturity (M) of the fruit fly is only related to the age (A) and temperature (T), as follows: ; Wherein, T0 is a certain reference temperature, indicating that the maturity growth of fruit flies begins to accelerate at this temperature. The maturity of fruit flies is observed under different temperature and age conditions, and data is recorded. By fitting the observed data, the value of T0 and other parameters in the model can be estimated. If it is necessary to predict the maturity of a 5-day-old fruit fly at 25°C, it is only necessary to substitute A=5 and T=25 into the nonlinear regression model for calculation. The maturity in this embodiment is presented in the form of time or probability, i.e., the time required for fruit flies to reach a mature state under specific conditions, or the probability that fruit flies have matured under current conditions. For example, assuming that the fruit fly is at a temperature of 35 degrees Celsius, the light duration is 7 hours, the weight reaches 0.1 grams, the body length exceeds 1 cm and the wings are fully spread, it begins to show active courtship behavior. Based on the above data, a nonlinear regression mathematical model can be constructed, with temperature, light duration, weight, body length and wing spread as input variables, and the output variable is the maturity probability of the fruit fly. When newly captured fruit fly individuals are measured and input into the model, the model outputs a probability value between 0 and 1, indicating the probability that the fruit fly has matured.

[0047] Finally, the first quantity (initial emergence quantity), the second quantity (the number of fruit fly insects at the connection) and the current environmental data are input into the pre-trained prediction model. The prediction model is based on historical data and machine learning algorithms, which can analyze the complex relationship between data and predict the future emergence peak time period of fruit fly insects. By predicting the future emergence peak time period of fruit fly insects, agricultural producers can make prevention and control preparations in advance and reduce the potential threat of fruit fly insects to crops.

[0048] This embodiment can effectively grasp the emergence cycle and population dynamics of fruit fly insects through precise monitoring by photoelectric sensors, image capture by cameras, and prediction models, and provide strong scientific support for agricultural production.

[0049] In one implementation of this embodiment, a tunable light source is provided in the adult insect chamber, and the photoelectric data includes the light intensity in the adult insect chamber and the light wave reflection data on the wing surface of the fruit fly insect under the tunable light source. Determining the fully spread wings feature of the fruit fly insect in the adult insect chamber according to the photoelectric data includes the following steps: S410, when the light intensity in the adult chamber is greater than a preset first light intensity threshold, determining that the wavelength range of the tunable light source is a target wavelength range, and adjusting the wavelength of the tunable light source to within the target wavelength range; S420, obtaining spectral characteristic data of wing reflection of giant fly at different growth stages through a preset spectral characteristic database, and performing data comparison between the light wave reflection data and the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data, and obtain the number of fruit fly insects corresponding to each growth stage; S430, according to the growth stage corresponding to the light wave reflection data, query the preset feature database to obtain the full wing spread feature of the fruit fly insects in the adult insect bin.

[0050] In the adult chamber, in order to accurately capture the wing characteristics of fruit fly insects, a tunable light source is set to adjust the wavelength according to different needs, thereby providing light of a specific wavelength. When the light intensity in the adult chamber exceeds the preset first light intensity threshold, it means that the external environment has sufficient light, which may interfere with the accuracy of the light wave reflection data. At this time, the system will automatically adjust the wavelength range of the tunable light source to a predetermined target wavelength range. This target wavelength range is selected based on the research on the reflection characteristics of fruit fly wings, which can maximize the characteristic differences on the wing surface. During implementation, a light intensity sensor can be used to monitor the light intensity in the chamber in real time. If it exceeds the threshold, the light source adjustment mechanism is triggered to ensure that subsequent light wave reflection data is collected at the optimal wavelength, so as to effectively reduce the interference of ambient light and improve the accuracy and stability of data collection.

[0051] Next, a preset spectral feature database is used, which stores the spectral feature data of the wings of giant flies at different growth stages. These data are obtained through long-term observation and experiments. The currently collected light wave reflection data is compared with the data in the database to determine the most matching spectral feature, and the growth stage of the fruit fly is determined accordingly. At the same time, the number of fruit flies at each growth stage is counted to provide data support for subsequent maturity assessment. In specific implementation, the comparison results can be displayed through the user interface, allowing users to intuitively see the number and proportion of fruit flies at different growth stages, which is convenient for users to make decisions.

[0052] After determining the growth stage of the fruit fly, the fully spread wings feature of the fruit fly in the adult chamber is queried in another preset feature database according to the growth stage corresponding to the light wave reflection data. The preset feature database includes detailed feature descriptions of each stage of the fruit fly from larvae to adults. Based on the query results and the current light wave reflection data, a comprehensive judgment is made as to whether the fruit fly has reached the fully spread wings state.

[0053] The light wave reflection data in this embodiment is obtained by a photoelectric sensor, and the photoelectric sensor is used to detect the reflection of light waves of different wavelengths to obtain the light wave reflection data of the wing surface of the fruit fly insect.

[0054] Specifically, the light wave reflection data includes a first spectral bandwidth, a first peak position, and a first peak intensity. The light wave reflection data of the wing surface of the fruit fly insects is collected under different light intensities because the emergence of the fruit fly insects is affected by environmental factors, mainly the temperature, and the temperature changes with the change of light intensity. Therefore, light intensity is used as an independent variable for monitoring the emergence of fruit fly insects, and the influence of different light intensities on the emergence stage of fruit fly insects is analyzed.

[0055] In one embodiment, light wave reflection data of the wing surface of fruit fly insects can be collected under different light intensities, that is, a plurality of light intensity monitoring data are obtained, and a plurality of light wave reflection data of fruit fly insects under the plurality of light intensity monitoring data are collected. For example, the light intensity monitoring data at 12 noon and 1 pm are selected as the first preset time period. If the average light intensity of the two light intensity data is greater than the first light intensity threshold, the light wavelength is within the target wavelength range. The light intensity monitoring data at 5 pm and 6 pm are selected as the second preset time period. If the average light intensity data at 5 pm and 6 pm is greater than the second light intensity threshold, the light wavelength is within the second wavelength range. The light wave reflection data of the wing surface of fruit fly insects are collected within the target wavelength range and the second wavelength range, respectively, and the changes of the light wave reflection data of the wing surface of fruit fly insects in the two time periods are compared, respectively, to determine whether the fruit fly insects are in full wing spread.

[0056] Spectral characteristics are one of the characteristics of matter, and each substance has its own unique spectrum. Different substances have different spectra. Light wave reflection data is obtained through light wave reflectivity. The curve obtained with wavelength as the horizontal coordinate and reflectivity as the vertical coordinate is called the reflection spectrum characteristic curve of the object. When the light source shines on the surface of an object, the object will selectively reflect electromagnetic waves of different wavelengths. Reflectivity refers to the ratio of the light flux reflected by the object in a certain band to the light flux incident on the object, which is the essential property of the surface of the object. Spectral reflectivity is the characterization of the color of the object itself. However, when the light intensity is too strong, directly using the current light source may cause the reflected light to be too strong, resulting in noise or saturation in the captured image, affecting the accuracy of the determination of the fully spread wings feature. Therefore, it is necessary to adjust the wavelength of the tunable light source to a suitable range to obtain more accurate reflection data.

[0057] Tunable light sources are necessary instruments for wavelength adjustment in optical communication field tests. They can accurately and quickly adjust the appropriate wavelength to meet test requirements. To obtain light wave reflection data from the wings of fruit flies under tunable light sources, first, the wavelength and frequency of the light are adjusted so that the monitored light waves are within the target wavelength range, reducing the interference of excessive light on the reflection data, ensuring the clarity and accuracy of the images captured by the camera and the accuracy of data collection.

[0058] Secondly, light wave reflection data of the wing surface of the fruit fly insects is collected within the target wavelength range, specifically, the first spectral bandwidth, the first peak position and the first peak intensity of the light wave reflection data are collected to obtain the reflectivity of the wing surface of the fruit fly insects. The formula for calculating the reflectivity of the wing of the fruit fly insects is: ; The incident light intensity is , the reflected light intensity is .

[0059] The incident light intensity of the fruit fly insect wings is recorded as and fruit fly wings reflected light intensity , calculate the reflectance of fruit fly insect wings within the target wavelength range .

[0060] By plotting the wavelength as the horizontal axis, The curve with y as the ordinate can obtain the first reflection spectrum characteristic curve of the wing surface of the fruit fly insect, and obtain the first spectral bandwidth, the first peak position and the first peak intensity. The spectral characteristic data of the fruit fly insect in the emergence stage is obtained, and the light wave reflection data is compared with the spectral characteristic data of the fruit fly insect in the emergence stage to obtain the matching degree between the light wave reflection data and the spectral characteristic data of the fruit fly insect. It is determined whether the fruit fly insect is in the emergence stage through the matching degree, and when the fruit fly insect is in the emergence stage, the growth stage characteristics of the fruit fly insect are determined to be the emergence stage characteristics.

[0061] This embodiment obtains the spectral characteristic data of the wing reflections of the big fruit flies at different growth stages through a preset spectral characteristic data database, and compares the light wave reflection data with the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data. It can accurately identify the fully spread wings characteristics of the fruit flies in the adult bin, and provide reliable data support for the maturity assessment and emergence cycle prediction of the fruit flies, which not only improves the accuracy and stability of data collection, but also enables agricultural producers to more conveniently monitor the growth and development of fruit flies.

[0062] In one implementation of this embodiment, data comparison is performed on the light wave reflection data and the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data and the number of fruit fly insects corresponding to each growth stage, including the following steps: S510, performing spectral analysis on the light wave reflection data to obtain a first spectral bandwidth, a first peak position, and a first peak intensity of the light wave reflection data; S520, obtaining a second spectral bandwidth, a second peak position, and a second peak intensity of the spectral characteristic data; S530, calculating, according to a preset feature matching algorithm, a first matching degree between the first spectral bandwidth and the second spectral bandwidth, a second matching degree between the first peak position and the second peak position, and a third matching degree between the first peak intensity and the second peak intensity; S540, taking the sum of the first matching degree, the second matching degree and the third matching degree as the target matching degree between the light wave reflection data and the spectral feature data; S550, when the target matching degree is greater than a preset matching degree threshold, determining that the light wave reflection data matches the spectral feature data, and taking the growth stage corresponding to the spectral feature data as the growth stage corresponding to the light wave reflection data matched therewith; S560. Count and obtain the number of fruit fly insects corresponding to each growth stage.

[0063] In this embodiment, firstly, the spectral analysis technology is used to extract the first spectral bandwidth, the first peak position and the first peak intensity of the light wave reflection data. The spectral bandwidth refers to the frequency width occupied by the light wave reflection data within a certain range, which reflects the color richness of the light reflected from the surface of the fruit fly's wings; the peak position refers to the wavelength corresponding to the point with the highest intensity in the reflected light wave, which is directly related to the specific structure or pigment on the surface of the fruit fly's wings; and the peak intensity is the reflection intensity of the light wave at this wavelength, which reflects the light reflection ability of the fruit fly's wing surface. Through the above three parameters, the characteristic profile of the light wave reflected from the fruit fly's wings can be preliminarily constructed, laying the foundation for subsequent feature matching. During implementation, the collected light wave reflection data can be automatically processed through the preset spectral analysis software to extract the required spectral characteristic parameters.

[0064] Next, it is necessary to obtain the spectral feature data of the wings reflected by the big fruit flies at different growth stages from the preset spectral feature database. The spectral feature data includes the second spectral bandwidth, the second peak position and the second peak intensity. The spectral feature data in the database are obtained through long-term observation and experimental measurement of a large number of fruit fly samples, and represent the typical characteristics of light waves reflected by the wings of fruit flies at different growth stages. In specific implementation, the corresponding spectral feature data can be quickly retrieved according to the species and growth stage of the fruit flies through database query statements, so as to prepare for subsequent feature comparison.

[0065] In order to determine whether the light wave reflection data corresponds to the spectral feature data, feature matching can be used. Among them, the preset feature matching algorithm can calculate the first matching degree between the first spectral bandwidth and the second spectral bandwidth, the second matching degree between the first peak position and the second peak position, and the third matching degree between the first peak intensity and the second peak intensity. The above matching degree is calculated by comparing the similarity between the two sets of spectral feature parameters, usually using a similarity measurement method such as Euclidean distance, cosine similarity, etc. The higher the matching degree, the greater the similarity between the two sets of data, that is, the greater the possibility that the light wave reflection data corresponds to the spectral feature data.

[0066] After obtaining the three matching degrees, the sum of the first matching degree, the second matching degree and the third matching degree is used as the target matching degree, so as to fully consider the importance of each matching degree in feature matching and ensure that the final matching result is more accurate and reliable.

[0067] When the target matching degree is greater than the preset matching degree threshold, it can be determined that the light wave reflection data matches the spectral feature data. At this time, the growth stage corresponding to the spectral feature data is used as the growth stage corresponding to the light wave reflection data that matches it. The mapping from light wave reflection data to fruit fly growth stages is realized, providing key information for subsequent fruit fly population statistics and maturity assessments. Subsequently, after determining the growth stage corresponding to each light wave reflection data, the number of fruit flies corresponding to each growth stage can be statistically obtained. In specific implementation, the statistical results can be presented to users in the form of charts or reports, so that users can intuitively understand the growth and quantity distribution of fruit fly populations.

[0068] In another embodiment, the reflectivity formula can be used to calculate the reflectivity of the light wave reflection data of the wing surface of the fruit fly insect within the target wavelength range. By plotting the wavelength as the horizontal axis and the reflectivity The curve with the ordinate as the second reflection spectrum characteristic curve of the wing surface of the fruit fly insect is obtained, and the second spectrum bandwidth, the second peak position and the second peak intensity are obtained. The first spectrum bandwidth, the first peak position and the first peak intensity are matched with the second spectrum bandwidth, the second peak position and the second peak intensity. The matching degree calculation formula is: ; Where A is the first spectral bandwidth, the first peak position and the first peak intensity in the light wave reflection data; B is the second spectral bandwidth, the second peak position and the second peak intensity.

[0069] The first spectral bandwidth and the second spectral bandwidth are respectively calculated using the matching formula to obtain a first matching degree; the first peak position and the second peak position are calculated using the matching formula to obtain a second matching degree; the first peak intensity and the second peak intensity are calculated using the matching formula to obtain a third matching degree; the sum of the first matching degree, the second matching degree and the third matching degree is compared with the matching degree of the spectral feature data, and when the matching degree is greater than a first preset value, it is determined that the giant fly is in the fully spread wings stage.

[0070] Specifically, the matching degree calculation formula includes: ; In the formula, M is any one of the first matching degree, the second matching degree and the third matching degree. On the basis that M is the first matching degree, B1 is the first spectral bandwidth, and B2 is the second spectral bandwidth; on the basis that M is the second matching degree, B1 is the first peak position, and B2 is the second peak position; on the basis that M is the third matching degree, B1 is the first peak intensity, and B2 is the second peak intensity.

[0071] This embodiment can accurately identify the growth stage of fruit flies in the adult compartment, and obtain the number of fruit flies corresponding to each growth stage by counting. It not only improves the accuracy and efficiency of fruit fly growth stage identification, but also provides an important decision-making basis for agricultural producers. By real-time monitoring of the growth and quantity distribution of fruit fly populations, agricultural producers can formulate prevention and control measures more scientifically, reduce the harm of fruit flies to crops, and improve agricultural production efficiency. At the same time, this technical solution can also be applied to the growth stage identification and quantity statistics of other insects or animals.

[0072] In one implementation of this embodiment, image recognition is performed on the first image to obtain the first number and pre-wing features of the fruit fly insects on the plane where the eclosion chamber and the adult chamber are connected, including: S610, preprocessing the first image to obtain multiple image features; S620, determining a first number of fruit fly insects and features before wing expansion on a plane where a connection between the eclosion chamber and the adult chamber is located from among a plurality of image features.

[0073] In this embodiment, the first image obtained is first preprocessed to improve the quality of the image and enhance the characteristics of the fruit fly insects in the image to facilitate subsequent identification and analysis. The preprocessing steps include graying, filtering, contrast enhancement, etc. of the image. Graying is to convert a color image into a gray image to simplify subsequent processing; filtering is to remove noise in the image to make the characteristics of the insect clearer; contrast enhancement is to highlight the difference between the insect and the background and improve the accuracy of identification. During implementation, image processing software, such as OpenCV, etc., can be used to automatically preprocess the first image. For example, by setting a specific graying algorithm, the color image is converted into a gray image; then by selecting a suitable filter, such as a Gaussian filter, the image is smoothed; finally, by adjusting the brightness and contrast of the image, the characteristics of the insect are made more obvious. After preprocessing, the fruit fly insects in the image will be easier to identify and count.

[0074] After completing the preprocessing of the image, it is necessary to determine the first number and pre-wing features of the fruit fly insects in the plane where the eclosion bin and the adult bin are connected from multiple image features. First, the fruit fly insects in the image are separated from the background by image segmentation technology. This can be achieved by threshold segmentation, edge detection, regional growth and other methods. Then, the key features of the fruit fly insects, such as shape, size, texture, etc., are extracted by feature extraction technology. In implementation, machine learning algorithms such as support vector machines (SVM) and convolutional neural networks (CNN) can be used to classify and identify the extracted features. By training the model, the model can learn the characteristics of fruit fly insects at different growth stages, and accurately identify and count the insects in the image based on this. At the same time, by comparing image data at different time points, the growth trend and quantity changes of fruit fly insects can also be analyzed, providing an important basis for subsequent prevention and control measures.

[0075] Specifically, the process of the image recognition technology in this embodiment is divided into information acquisition, preprocessing, feature extraction and selection, classifier design and classification decision. In this embodiment, the information is mainly acquired by monitoring the infrared signal through the infrared sensor. If the infrared signal is monitored, the camera is used to capture and acquire the information. The steps of processing the captured image are not described in detail here.

[0076] In another embodiment, a convolutional neural network algorithm can be used to extract important features from an image, identify and classify the shape, texture, and pattern of fruit fly insects at different growth stages, thereby achieving accurate classification. A convolutional neural network is a type of feedforward neural network that includes convolution calculations and is used to process high-dimensional input data such as images. The convolutional neural network algorithm efficiently extracts important features of an image through convolutional layers and pooling layers, and then processes the compressed image information through a fully connected layer and outputs the result. This method reduces model parameters, reduces the amount of computation, and can handle the translation invariance of the image well, that is, the different positions of the identified object in the image have the same meaning. This feature of the convolutional neural network algorithm makes it very suitable for image recognition tasks. Converting an image into a feature vector usually requires the use of image processing and machine learning algorithms, especially convolutional neural networks in deep learning. Specifically, the process of converting an image into a feature vector includes the following steps: S1. Use the convolutional layer and pooling layer of the convolutional neural network algorithm to extract features from the image. The convolutional layer and pooling layer can capture key information of the image, such as the edges and colors of fruit fly insects, while reducing the dimension of the data, making subsequent processing more efficient. S2. Through the fully connected layer, the extracted features are mapped to a higher-dimensional space. The representation in the high-dimensional space is more conducive to classification or recognition tasks. S2. The output of the convolutional neural network algorithm can be regarded as a feature vector. The feature vector contains the key information of the image and can be used for image classification. The target image features are obtained through the feature vector, and the pre-wing features are selected from the target image features. In summary, the convolutional neural network algorithm, through its unique architecture and learning ability, converts the image into a feature vector to obtain the target image features, and determines the pre-wing features among the target image features, making image recognition and processing more efficient and accurate.

[0077] This embodiment can realize accurate identification and counting of fruit fly insects on the plane where the emergence chamber and the adult chamber are connected through image recognition, and simultaneously obtain their characteristics before wings are spread. This not only improves the accuracy and efficiency of fruit fly insect identification and counting, but also provides important decision-making basis for agricultural producers.

[0078] In one implementation manner of this embodiment, after performing image recognition on the first image to obtain the first number and pre-wing features of the fruit fly insects on the plane where the eclosion chamber and the adult chamber are connected, the following steps are included: S710, screening the features before wingspan to obtain key features; S720, mapping the key features based on a preset mapping rule to obtain corresponding key feature interpretations; S730, determining a keyword range in a preset feature database according to the key feature interpretation; S740: In the keyword range, determine the keywords corresponding to the key feature interpretation and output them.

[0079] After obtaining the pre-wing-spreading features of fruit fly insects, the pre-wing-spreading features are screened so as to select the most representative and distinguishing features from a large number of features, which is convenient for subsequent analysis and identification. The key features can be screened by principal component analysis to screen out those features that contribute most to classification and identification. In specific implementation, the feature selection algorithm can be used to automatically screen the pre-wing-spreading features. According to the variance, correlation, mutual information and other indicators of the features, the features are sorted and selected, and finally the most representative key features are retained. Through the key features, the pre-wing-spreading state of fruit fly insects can be described more accurately.

[0080] After obtaining the key features, these key features are mapped based on the preset mapping rules to obtain the corresponding key feature interpretations. The mapping rules link the key features with specific biological meanings or classification labels. In specific implementations, a feature-interpretation mapping table can be constructed, which includes various key features and their corresponding interpretations. For example, a key feature corresponds to the wing length of fruit fly insects, and its interpretation is "wing length is an important feature for distinguishing different types of fruit flies." Through the above mapping rules, abstract key features can be converted into biologically meaningful interpretations, providing more intuitive and easy-to-understand information for subsequent analysis and identification.

[0081] This embodiment uses a mapping method to interpret the current key features and automatically map the corresponding keywords. If it is impossible to map to the corresponding keywords, the keywords are obtained by selecting other features of fruit fly insects for secondary mapping. Other features can be body color and morphological features of fruit fly insects. For example, the large fruit fly presents a golden body color after emergence, with a black longitudinal stripe in the center of the back of the mesothorax, extending from the base to the abdomen, and a wider black transverse stripe near the front edge of the third abdominal segment. The longitudinal and transverse stripes intersect in a "cross" shape, which is the body feature information of adult fruit fly insects. The corresponding keywords are searched in a preset database using an algorithm, and the keywords are located in the range to be searched, and the growth stage features corresponding to the keywords are determined, so that the current growth stage of the fruit fly insects in the monitoring area can be obtained.

[0082] After obtaining the key feature interpretation, determine the keyword range in the preset feature database. The feature database is a database that contains a large amount of feature information of fruit fly insects, and can quickly retrieve relevant keywords based on the feature interpretation. During implementation, a database query statement can be used to perform fuzzy matching or exact matching in the feature database based on the key feature interpretation to find the keyword range related to the interpretation. For example, if the key feature interpretation is "wing length", then the keyword range may include "long wings", "short wings", "wingspan" and other words related to wing length. By determining the keyword range, the search space can be further narrowed, and the accuracy and efficiency of subsequent keyword determination can be improved.

[0083] After determining the keyword range, the keywords corresponding to the key feature interpretations can be determined and output. In specific implementation, text mining and natural language processing techniques can be used to automatically screen and sort the words within the keyword range. For example, the degree of match between the keywords and the key feature interpretations can be evaluated by calculating the similarity score between them; at the same time, the frequency and weight of the keywords in the relevant literature or database can also be considered to determine their popularity and relevance. Ultimately, the keyword with the highest score or the one that best meets the needs can be selected as the output result, providing important information for the subsequent classification, identification or prevention and control of fruit fly insects.

[0084] In this embodiment, the mapping rules are first determined. The growth stages of fruit fly insects include four stages: egg, larva, pupa and adult. The characteristics of each stage are recorded in the mapping rules respectively. The unique characteristics of the four growth stages of fruit fly insects include egg stage: the egg is oblong, slightly pointed at one end, slightly curved, milky white in the middle, and relatively transparent at both ends. Larva stage: milky white conical, pointed at the front end, and thick at the back end. The mouth hook is black and often retracted into the prothorax. Pupa stage: oval, golden yellow, turning into yellowish brown before eclosion. The anterior valve papillae of the larval period are still clearly visible. Adult stage: The adult body is like a fly, the individual is smaller, and the body color is like a bee, black and yellow. The adult body length is 10-13mm, the wingspan is about 21mm, and the whole body is light yellowish brown. There is a black line in the center of the back of the mesothorax, from the base to the abdomen. There is a wide black horizontal line near the front edge of the third abdominal segment, and the vertical and horizontal lines intersect to form a "cross" shape.

[0085] After determining the mapping rules, the principal component analysis method can be used to determine the key features. First, each pre-wing feature is processed to remove the average value, that is, decentralized, to make the mean of the data set 0, so as to facilitate subsequent calculations. The second step is to calculate the covariance matrix: Next, the covariance between all pre-wing features is calculated to form a covariance matrix. The covariance matrix reflects the correlation between different pre-wing features. Then, the covariance matrix is ​​decomposed by the pre-wing eigenvalue to obtain the key eigenvalues ​​and key eigenvectors. The key eigenvalues ​​indicate the importance of each principal component, and the key eigenvectors define the direction of the principal component. According to the size of the key eigenvalue, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected. The eigenvectors corresponding to the first k largest eigenvalues ​​constitute a new feature space, namely the principal component. Finally, the original data is projected onto the k principal components to obtain the key features after dimensionality reduction.

[0086] During the retrieval process, a block search method can be used to enter the set to be searched in the preset database. The set to be searched includes the body shape and appearance characteristics of all growth stages of fruit fly insects. Specifically, first divide the search table of information on all growth stages of fruit fly insects into several blocks. The elements in each block do not have to be ordered, but the blocks must be ordered. For each block, select an element and put it into the index table, which is sorted. The search process can include: first search the block where the keyword to be searched is located in the index table, then perform a sequential search in the block where the keyword to be searched is located, and finally determine the keyword corresponding to the current key feature, determine the position of the current keyword and search in the preset database to determine the current growth status of the fruit fly insect.

[0087] This embodiment can filter out key features from the pre-wing features of fruit fly insects and map them into interpretations with biological significance; then, determine the keyword range in the preset feature database, and finally determine the keywords corresponding to the key feature interpretations. It not only improves the accuracy and efficiency of feature analysis and identification of fruit fly insects, but also provides agricultural producers with more intuitive and easy-to-understand information. By real-time monitoring and analysis of the key features of fruit fly insects, agricultural producers can formulate prevention and control measures more scientifically to reduce the harm of fruit flies to crops.

[0088] In one implementation of this embodiment, the following steps are also included: S810: When the key feature cannot be mapped to obtain the corresponding key feature interpretation, perform image recognition on the first image to obtain a plurality of color features; S820, screening out a cross black horizontal stripe feature and a golden yellow body color feature from a plurality of color features, and taking the cross black horizontal stripe feature and the golden yellow body color feature as the second target key features; S830, obtaining the associated interpretation of the key feature interpretation, and expanding the keyword range according to the associated interpretation to obtain a second keyword range; S840: Determine and output keywords corresponding to the second target key features within the second keyword range.

[0089] In the process of image recognition, when the key features cannot be mapped to obtain the corresponding key feature interpretations, it means that the current feature library or mapping rules may not cover all feature situations. In order to make up for this deficiency, further image recognition strategies can be adopted. Specifically, the first image can be subjected to more in-depth image recognition to obtain multiple color features. Color feature is a commonly used feature in image recognition. It describes the color information of objects or regions in the image, which is of great significance for distinguishing different objects or identifying specific patterns. In implementation, the color space conversion algorithm can be used to convert the image from the RGB color space to the HSV or Lab color space to better separate the color information; then, multiple color features in the image can be extracted through methods such as color histogram and color moment.

[0090] After obtaining multiple color features, representative features are selected from these features as the second target key features. According to the biological characteristics of fruit fly insects, the cross black horizontal stripe feature and the golden body color feature are two more significant and common color features. The cross black horizontal stripe feature usually appears on the back or wings of fruit fly insects, and is a cross-shaped or cross-shaped black horizontal stripe; while the golden body color feature is a common manifestation of the body color of fruit fly insects, with a bright golden hue. During implementation, the feature screening algorithm can be used to automatically screen and compare the extracted color features to find the features that best match the cross black horizontal stripe feature and the golden body color feature. These screened features will be used as the second target key features for subsequent identification and keyword determination.

[0091] After determining the second target key feature, in order to find the corresponding keywords, it is necessary to further expand the keyword range. This can be achieved by obtaining the associated interpretations of the key feature interpretation. Associated interpretations refer to other interpretations that are related or similar to the key feature interpretation, which may contain more information or a wider description. During implementation, semantic similarity calculation technology can be used to find associated interpretations similar to the key feature interpretation; then, based on these associated interpretations, the keyword range is further searched and expanded in the preset feature database to obtain the second keyword range. The second keyword range will include more keywords related to the second target key feature, improving the accuracy and diversity of subsequent keyword determination.

[0092] After obtaining the second keyword range, the keywords corresponding to the second target key features are determined within the second keyword range and output. In specific implementation, text mining and natural language processing techniques can be used to automatically screen and sort the words within the second keyword range. For example, the degree of match between the keywords and the second target key features can be evaluated by calculating the similarity score between them; at the same time, the frequency and weight of the keywords in the relevant literature or database can also be considered to determine their popularity and relevance. Ultimately, the keyword with the highest score or the one that best meets the needs can be selected as the output result, providing important information for subsequent classification, identification or prevention and control of fruit fly insects.

[0093] This embodiment can further extract color features and screen the second target key features when the key features cannot be mapped to the corresponding key feature interpretations; then, by obtaining the associated interpretations and expanding the keyword range, the keywords corresponding to the second target key features are finally determined. It not only improves the flexibility and accuracy of feature analysis and identification of fruit fly insects, but also provides agricultural producers with richer and more diverse information. By real-time monitoring and analysis of the color characteristics of fruit fly insects, agricultural producers can formulate prevention and control measures more scientifically to reduce the harm of fruit flies to crops.

[0094] In one implementation of this embodiment, before determining the keyword range in the preset feature database according to the key feature interpretation, the following steps are also included: S910, storing each growth stage feature of the giant fly in a preset feature database, and setting a to-be-searched range of the preset feature database; S920: Determine and output keywords corresponding to the key feature interpretation in the keyword range, including: S930. Locate the keyword in the scope to be searched, and determine the growth stage characteristics corresponding to the keyword, wherein the growth stage characteristics corresponding to the keyword are used to characterize the current growth stage of the giant fly in the monitoring area.

[0095] In order to effectively identify the growth stage of the giant fly, it is first necessary to store the characteristics of each growth stage of the giant fly in a preset feature database. The growth stages of the giant fly generally include stages such as eggs, larvae, pupae and adults, and each stage has its unique morphological and biological characteristics. In specific implementation, a large amount of images, videos or text descriptions of the giant fly at each growth stage can be collected, and then representative features such as morphology, color, texture, etc. can be extracted by image processing, feature extraction, etc., and stored in a preset feature database to form a giant fly growth stage feature library. At the same time, in order to improve the retrieval efficiency, it is also necessary to set the scope to be searched of the preset feature database, that is, according to actual needs, the retrieval is limited to a specific growth stage or a specific feature type, thereby reducing unnecessary calculations and data comparisons.

[0096] After the keyword range is determined, the keyword is located within the keyword range, and the growth stage characteristics corresponding to the keyword are determined. In specific implementation, fuzzy matching or exact matching can be performed in the database according to the keyword to find all feature records related to the keyword. Then, by comparing these feature records with the characteristics of the current growth stage of the giant fly, the most matching growth stage characteristics are determined. For example, if the keyword is "fully spread wings", all features related to fully spread wings, such as body shape, color, behavior, etc., will be searched in the database and compared with the currently monitored giant fly characteristics to determine whether the giant fly is currently in the fully spread wings stage.

[0097] At the same time, S930 can not only determine the growth stage characteristics corresponding to the keywords, but also use these characteristics to characterize the current growth stage of the giant fly in the monitoring area. This means that through this step, agricultural producers or researchers can understand the growth status of the giant fly in real time, providing an important basis for formulating effective prevention and control measures or research plans. For example, if it is determined that the giant fly is currently in the adult stage, targeted pesticide application measures can be taken to control its growth and reproduction.

[0098] This embodiment stores the characteristic information of each growth stage of the giant fly through a preset characteristic database, and sets the range to be searched to improve the search efficiency; then, the keyword is located within the keyword range, and the growth stage characteristics corresponding to the keyword are determined, so as to characterize the current growth stage of the giant fly in the monitoring area in real time. It not only improves the accuracy and efficiency of the growth stage identification of the giant fly, but also provides more intuitive and easy-to-understand information for agricultural producers and researchers. By monitoring the growth status of the giant fly in real time, prevention and control measures and research plans can be formulated more scientifically, reducing the harm of the giant fly to crops and promoting the sustainable development of agricultural production.

[0099] like Figure 2 and Figure 3As shown, the embodiment of the present application also provides a fruit fly insect monitoring device, which includes a fruit fly insect monitoring device box 10, an embryo chamber 30, an adult chamber 20 and a hollow frame. The embryo chamber 30 and the adult chamber 20 are arranged in the fruit fly insect monitoring device box 10, and at least one infrared sensor is respectively arranged at the outlet of the embryo chamber 30 and the entrance of the adult chamber 20. The embryo chamber 30 is arranged as a whole in the soil environment, and the adult chamber 20 is arranged as a whole on the ground. The adult chamber 20 is a narrow upper and wide lower structure, and a camera 50 and a fill light 60 for monitoring fruit fly insects are arranged in the adult chamber 20. The top of the adult chamber 20 is seamlessly connected to the hollow frame, and at least one counting sensor 40 is arranged in the hollow frame. The fruit fly insect monitoring device also includes: a memory configured to store instructions; and The processor is configured to call instructions from the memory and implement the above-mentioned method for monitoring the emergence of fruit fly insects when executing the instructions.

[0100] The fruit fly insect monitoring device includes an embryo chamber 30, an adult chamber 20 and a camera 50, wherein the embryo chamber 30, the adult chamber 20 and the camera 50 are all located in the monitoring area of ​​the fruit fly insect monitoring device housing 10, and the monitoring area is used to monitor the growth activities of fruit fly insects. The adult chamber 20 is arranged on the upper side of the embryo chamber 30. Due to the biological characteristics of fruit fly insects, the adult chamber 20 is designed to be narrow at the top and wide at the bottom, so as to allow fruit fly insects to fly from the bottom of the adult chamber 20 to the top, so as to better monitor the fruit fly insects. The adult chamber 20 is provided with a camera 50, a photoelectric sensor and a counting sensor 40. The infrared sensor can be set to one, or two or more, and this application does not limit this.

[0101] In a specific implementation, a counting sensor 40 for counting is also provided in the housing 10 of the fruit fly insect monitoring device. The counting sensor 40 can be a photoelectric sensor, an ultrasonic sensor, a vibration sensor, etc. Taking the ultrasonic sensor as an example, it can count the fruit fly insects by the changes in the reflected ultrasonic wave when the insects pass through the sensor, so as to better determine the degree of emergence of the fruit fly insects in the monitoring area, and then determine the current growth status of the fruit fly insects, wherein the counting sensor 40 is arranged in a hollow frame.

[0102] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0107] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0108] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0109] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0110] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for monitoring the emergence of fruit flies, characterized in that: The invention is applied to a fruit fly insect monitoring device, the fruit fly insect monitoring device comprises a box, an embryo chamber, an adult chamber and a hollow frame, the embryo chamber and the adult chamber are arranged in the box, at least one infrared sensor is respectively arranged at the outlet of the embryo chamber and the entrance of the adult chamber, the embryo chamber is arranged in a soil environment as a whole, the adult chamber is arranged on the ground as a whole, the adult chamber is a narrow upper and wide lower structure, and a camera and a fill light for monitoring fruit fly insects are arranged in the adult chamber, the top of the adult chamber is seamlessly connected to the hollow frame, and at least one counting sensor is arranged in the hollow frame. The method comprises: In response to the infrared signal transmitted by the infrared sensor, obtaining the light intensity in the adult chamber; Issuing a first instruction, wherein the first instruction is used to control the camera to capture a first image of the plane where the eclosion chamber and the adult chamber are connected, and recording a first issuance time of the first instruction, and starting timing from the first issuance time, wherein, when the light intensity is less than a preset light intensity threshold, controlling the fill light to turn on; Performing image recognition on the first image to obtain a first number and pre-wing features of the fruit fly insects on a plane where the eclosion bin and the adult bin are connected; determining the emergence period of fruit fly insects, and calculating the difference between the first number and the second number; The current emergence status of the fruit fly insects is determined according to the difference and the emergence period, wherein the current emergence status includes an emergence rate and an emergence speed.

2. A method for monitoring the emergence of fruit flies according to claim 1, characterized in that: The method of determining the emergence period of fruit fly insects comprises: After the first sending moment, the camera is controlled to capture an image at every preset time interval, and image recognition is performed on each captured image to obtain the number of fruit fly insects; Taking an image corresponding to when the number of fruit fly insects is less than a preset number threshold as a final image, and obtaining a shooting time of the final image; The difference between the shooting time and the first sending time is used as the emergence period of the fruit fly insect.

3. The method for monitoring the emergence of fruit flies according to claim 1, characterized in that: The adult insect chamber is also provided with a photoelectric sensor, and before determining the emergence period of the fruit fly insects, the following steps are performed: In response to receiving the photoelectric data transmitted by the photoelectric sensor, determining the fully spread wings feature of the fruit fly insects in the adult insect bin according to the photoelectric data; issuing a second instruction, wherein the second instruction is used to control the camera to capture a second image of the plane where the emergence chamber and the adult chamber are connected; Performing image recognition on the second image to obtain a second number of fruit fly insects on a plane where the emergence bin and the adult bin are connected; Get current environment data; Determining the maturity of the fruit fly insects in the adult insect bin by using the current environmental data and the fully spread wings feature; The first number, the second number and the current environmental data are input into a pre-trained prediction model to predict the future peak emergence time period of fruit fly insects.

4. A method for monitoring the emergence of fruit flies according to claim 3, characterized in that: The adult insect chamber is provided with a tunable light source, the photoelectric data includes the light intensity in the adult insect chamber and light wave reflection data of the wing surface of the fruit fly insect under the tunable light source, and the fully spread wing characteristics of the fruit fly insect in the adult insect chamber are determined according to the photoelectric data, including: When the light intensity in the adult insect bin is greater than a preset first light intensity threshold, determining that the wavelength range of the tunable light source is a target wavelength range, and adjusting the wavelength of the tunable light source to within the target wavelength range; Acquire spectral characteristic data of the wings of giant flies at different growth stages through a preset spectral characteristic database, and compare the light wave reflection data with the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data, and obtain the number of fruit fly insects corresponding to each growth stage; According to the growth stage corresponding to the light wave reflection data, the fully spread wings feature of the fruit fly insects in the adult insect bin is obtained by querying in a preset feature database.

5. A method for monitoring the emergence of fruit flies according to claim 4, characterized in that: The step of comparing the light wave reflection data with the spectral characteristic data to obtain the growth stage corresponding to the light wave reflection data and the number of fruit fly insects corresponding to each growth stage includes: Performing spectral analysis on the light wave reflection data to obtain a first spectral bandwidth, a first peak position, and a first peak intensity of the light wave reflection data; Acquire a second spectral bandwidth, a second peak position, and a second peak intensity of the spectral characteristic data; According to a preset feature matching algorithm, calculating a first matching degree between the first spectral bandwidth and the second spectral bandwidth, a second matching degree between the first peak position and the second peak position, and a third matching degree between the first peak intensity and the second peak intensity; The sum of the first matching degree, the second matching degree and the third matching degree is used as the target matching degree between the light wave reflection data and the spectral feature data; In the case where the target matching degree is greater than a preset matching degree threshold, determining that the light wave reflection data matches the spectral feature data, and taking the growth stage corresponding to the spectral feature data as the growth stage corresponding to the light wave reflection data matched therewith; The number of fruit fly insects corresponding to each growth stage is obtained by counting.

6. The method for monitoring the emergence of fruit flies according to claim 1, characterized in that: The performing image recognition on the first image to obtain a first number and pre-wing features of the fruit fly insects on a plane where the eclosion bin and the adult bin are connected includes: Preprocessing the first image to obtain multiple image features; The first quantity and pre-wing-spreading features of the fruit fly insects on the plane where the emergence bin and the adult bin are connected are determined from the plurality of image features.

7. A method for monitoring the emergence of fruit flies according to claim 1, characterized in that: After performing image recognition on the first image to obtain the first number and pre-wing features of the fruit fly insects on the plane where the eclosion bin and the adult bin are connected, the method includes: Screening the features before wingspan to obtain key features; Based on a preset mapping rule, the key features are mapped to obtain corresponding key feature interpretations; According to the key feature interpretation, determining the keyword range in a preset feature database; In the keyword range, the keyword corresponding to the key feature interpretation is determined and output.

8. A method for monitoring the emergence of fruit flies according to claim 7, characterized in that: The method further comprises: In the case where the key feature cannot be mapped to obtain a corresponding key feature interpretation, performing image recognition on the first image to obtain a plurality of color features; A cross black horizontal stripe feature and a golden yellow body color feature are screened out from the plurality of color features, and the cross black horizontal stripe feature and the golden yellow body color feature are used as the second target key features; Obtaining the associated interpretation of the key feature interpretation, and expanding the keyword range according to the associated interpretation to obtain a second keyword range; In the second keyword range, the keyword corresponding to the second target key feature is determined and output.

9. A method for monitoring the emergence of fruit flies according to claim 7, characterized in that: Before determining the keyword range in the preset feature database according to the key feature interpretation, the method includes: The characteristics of each growth stage of the giant fly are stored in the preset characteristic database, and the to-be-searched range of the preset characteristic database is set; Determining and outputting the keyword corresponding to the key feature interpretation in the keyword range includes: In the range to be searched, the keyword is located, and the growth stage characteristics corresponding to the keyword are determined, wherein the growth stage characteristics corresponding to the keyword are used to characterize the current growth stage of the giant fruit fly in the monitoring area.

10. A fruit fly insect monitoring device, characterized in that: The fruit fly insect monitoring device comprises a box body, an embryo chamber, an adult chamber and a hollow frame, wherein the embryo chamber and the adult chamber are arranged in the box body, at least one infrared sensor is respectively arranged at the outlet of the embryo chamber and the entrance of the adult chamber, the embryo chamber is arranged in a soil environment as a whole, the adult chamber is arranged on the ground as a whole, the adult chamber is a narrow upper and wide lower structure, and a camera and a fill light for monitoring fruit fly insects are arranged in the adult chamber, the top of the adult chamber is seamlessly connected to the hollow frame, and at least one counting sensor is arranged in the hollow frame, and the fruit fly insect monitoring device also comprises: a memory configured to store instructions; and A processor is configured to call the instructions from the memory and implement a method for monitoring emergence of fruit fly insects according to any one of claims 1 to 9 when executing the instructions.

Images