Intelligent analysis method and system for monitoring data of visual termite monitoring device

Abstract

The invention relates to the technical field of termite monitoring data processing, in particular to an intelligent analysis method and system for monitoring data of a visual termite monitoring device.The method comprises the steps that the visual termite monitoring device is designed and used for monitoring termite activities; the method comprises the following steps: acquiring a video through a visual termite monitoring device, calculating a background difference value by adopting a frame difference method, dynamically updating a background template, and extracting a termite activity frame; in combination with a termite detection model, obtaining the coordinates and number of activity bounding boxes, calculating the moving direction and speed of termites, generating termite data and uploading the termite data to the cloud; termite data are obtained through the cloud, the movement index, the activity index, the frequency index and the activity degree are calculated, and meanwhile, the termite activity trend in the future is predicted through an activity prediction model in combination with environment data. Through real-time monitoring and activity prediction, the first alarm information and the second alarm information are respectively sent out, comprehensive analysis and accurate early warning of termite activities are realized, and thus the monitoring efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of termite monitoring data processing, and in particular to a monitoring data intelligent analysis method and system of a termite visual monitoring device. Background Art

[0002] Termites are a type of pest that is highly destructive to infrastructure such as underground buildings, houses, and bridges. With the acceleration of global climate change and urbanization, the distribution range and activity intensity of termites are increasing, which in turn leads to property losses and structural safety issues. Therefore, termite monitoring has become an important research direction in the current field of pest control.

[0003] Existing monitoring solutions can record and analyze termite activities to a certain extent. For example, by trapping termites and collecting monitoring videos, combined with online monitoring and early warning functions, termite activities can be intuitively understood. However, on the one hand, these solutions are limited by the performance of the monitoring device, and lack the depth and multi-dimensional analysis capabilities of equipment status monitoring. They are unable to comprehensively monitor termite activities in complex environments, especially in the quantitative analysis of characteristics such as termite activity paths and frequencies. On the other hand, these solutions are mostly based on static analysis, and fail to conduct real-time analysis of the dynamic behavior of termite colonies and further explore the time trend of termite activities, resulting in deficiencies in monitoring efficiency.

[0004] Therefore, a monitoring data intelligent analysis method and system of a termite visualization monitoring device are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a monitoring data intelligent analysis method and system of a visual termite monitoring device, which is used to monitor termite activities by designing a visual termite monitoring device; collecting videos through the visual termite monitoring device, using the frame difference method to calculate the background difference, dynamically updating the background template, and extracting the termite activity frame; combining the termite detection model, obtaining the coordinates and number of the activity boundary box, calculating the movement direction and speed of the termites, generating termite data and uploading it to the cloud; obtaining termite data through the cloud, calculating the movement index, activity index, frequency index and activity level, and combining environmental data, using the activity prediction model to predict the future termite activity trend. Through real-time monitoring and activity prediction, the first and second alarm messages are respectively issued, realizing a comprehensive analysis and accurate early warning of termite activities, thereby improving the monitoring efficiency.

[0006] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, a monitoring data intelligent analysis method of a termite visualization monitoring device comprises: Step S1: a visual termite monitoring device, wherein the visual termite monitoring device is used to monitor termite activities; Step S2: according to the termite visualization monitoring device, an initial video frame without termite activity is obtained; the pixel average value of the initial video frame is calculated to obtain a background template; a new termite video frame is obtained, and the absolute difference between the termite video frame and the background template is calculated using a frame difference method; if the absolute difference is greater than a first threshold, the termite video frame is extracted; otherwise, the background template is updated according to the termite video frame; Step S3: binarize the termite video frame, and use the termite detection model to obtain the bounding box coordinates and the number of bounding boxes; if the number of bounding boxes is greater than a second threshold, issue a first alarm message; if the number of bounding boxes is greater than zero, segment the termite video frame to obtain a grid area; calculate the termite movement direction and termite movement speed according to the bounding box coordinates and the grid area; combine the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp into termite data and send it to the cloud; Step S4: Obtain the termite data from the cloud, calculate the mobility index, activity index, frequency index and termite activity level based on the termite data; obtain environmental data, use an activity prediction model to output the future termite activity level based on the environmental data and the termite activity level, and issue a second alarm message based on the future termite activity level.

[0007] Furthermore, the termite visualization monitoring device includes a monitoring box, a switch and an edge device; an industrial camera, a light bulb and a termite edible cylinder are installed in the monitoring box, the industrial camera is connected to the switch via a network cable, and the collected termite video frames are transmitted to the switch; the switch is connected to the edge device via the network cable; the edge device receives the termite video frames, monitors the termite activities according to the termite video frames, and generates the termite data; the edge device transmits the termite data to the cloud via a wireless network.

[0008] Furthermore, the process of updating the background template includes: ; in, The updated coordinates are The background template; is the smoothing factor; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; in, The update process is expressed as: ; in, is the smoothing factor, is the updated smoothing factor; is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

[0009] Furthermore, the calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; Taking the average value of the termite center coordinates in each frame to obtain the termite center of gravity coordinates; For the coordinates of the termite center of gravity of the continuous frames, the termite displacement vector is calculated using the Euclidean formula, and the termite movement speed is obtained according to the termite displacement vector; The termite moving direction is calculated using an azimuth calculation formula for the termite center of gravity coordinates of continuous frames.

[0010] Furthermore, the calculation process of the movement index, the activity index, the frequency index and the termite activity level includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; According to the fixed time period, averaging the termite movement speeds to obtain an average termite movement speed; weighted multiplying the average termite movement speed by the number of bounding boxes to obtain the activity index; According to the fixed time period, counting the number of changes in the number of bounding boxes, and dividing the number of changes by the length of the fixed time period to obtain the frequency index; The termite activity degree is obtained by weighted summing the movement index, the activity index and the frequency index.

[0011] In a second aspect, a monitoring data intelligent analysis system of a termite visualization monitoring device includes: Termite visual monitoring device design module, used to monitor termite activities; The video acquisition module is used to design a module for the visual termite monitoring device, obtain an initial video frame without termite activity, calculate the pixel average of the initial video frame, and obtain a background template; obtain a new termite video frame, and use a frame difference method to calculate the absolute difference between the termite video frame and the background template; if the absolute difference is greater than a first threshold, extract the termite video frame; otherwise, update the background template according to the termite video frame; The edge processing module is used to binarize the termite video frame, obtain the bounding box coordinates and the number of bounding boxes using the termite detection model; if the number of bounding boxes is greater than a second threshold, issue a first alarm message; if the number of bounding boxes is greater than zero, segment the termite video frame to obtain a grid area; calculate the termite movement direction and termite movement speed according to the bounding box coordinates and the grid area; combine the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp into termite data and send it to the cloud; A cloud processing module is used to obtain the termite data from the cloud, calculate the mobility index, activity index, frequency index and termite activity level based on the termite data; obtain environmental data, use an activity prediction model to output the future termite activity level based on the environmental data and the termite activity level, and issue a second alarm message based on the future termite activity level.

[0012] Furthermore, the termite visualization monitoring device includes a monitoring box, a switch and an edge device; an industrial camera, a light bulb and a termite edible cylinder are installed in the monitoring box, the industrial camera is connected to the switch via a network cable, and the collected termite video frames are transmitted to the switch; the switch is connected to the edge device via the network cable; the edge device receives the termite video frames, monitors the termite activities according to the termite video frames, and generates the termite data; the edge device transmits the termite data to the cloud via a wireless network.

[0013] Furthermore, the process of updating the background template includes: ; in, The background template is updated; is the smoothing factor; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; in, The update process is expressed as: ; in, is the smoothing factor, is the updated smoothing factor; is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

[0014] Furthermore, the calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; Taking the average value of the termite center coordinates in each frame to obtain the termite center of gravity coordinates; For the coordinates of the termite center of gravity of the continuous frames, the termite displacement vector is calculated using the Euclidean formula, and the termite movement speed is obtained according to the termite displacement vector; The termite moving direction is calculated using an azimuth calculation formula for the termite center of gravity coordinates of continuous frames.

[0015] Furthermore, the calculation process of the movement index, the activity index, the frequency index and the termite activity level includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; According to the fixed time period, averaging the termite movement speeds to obtain an average termite movement speed; weighted multiplying the average termite movement speed by the number of bounding boxes to obtain the activity index; According to the fixed time period, counting the number of changes in the number of bounding boxes, and dividing the number of changes by the length of the fixed time period to obtain the frequency index; The termite activity degree is obtained by weighted summing the movement index, the activity index and the frequency index.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention integrates industrial cameras, lights and edge devices by designing a visual termite monitoring device, thereby realizing efficient capture and monitoring of termite activities. The device can automatically extract key features through edge devices and generate termite data in real time, thereby reducing data transmission delays and cloud pressure, ensuring that it can quickly respond to sudden termite activities and issue the first alarm information. Then, the termite data is transmitted to the cloud for storage and analysis, fully realizing the efficient division of labor between the edge and the cloud, making data processing and storage more flexible, thereby improving the overall operational efficiency and reliability of termite monitoring.

[0017] 2. The present invention generates a background template based on the initial video frame, uses the frame difference method to calculate the difference between the video frame and the background template, and dynamically updates the background template through an adaptive smoothing factor, which can eliminate environmental interference in real time and provide stable and reliable input for subsequent data analysis. In addition, a termite detection model is deployed on the edge device to achieve accurate identification of termite activities. Through the identified termite activities, the movement direction and speed of the termites are further calculated, so that the dynamic changes of termite activities can be accurately captured, thereby quickly responding to emergencies and improving the overall operating efficiency and reliability of the termite monitoring system.

[0018] 3. After receiving termite data in the cloud, the present invention combines the number of bounding boxes, termite movement speed and direction and other information to calculate the movement index, activity index and frequency index, and then obtains the termite activity level, which can quantify the intensity of termite activity and help evaluate the current status and change trend of termite activity. By combining data such as environmental temperature and humidity with the termite activity level, using the activity prediction model to output future activity trends, and issuing a second alarm message based on future activity trends, an early warning is issued before termite activity changes significantly, which can comprehensively predict potential risks, thereby improving the overall operational efficiency of termite monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a monitoring data intelligent analysis method of a visual termite monitoring device of the present invention; Figure 2 It is a structural schematic diagram of the visual termite monitoring device of the present invention; Figure 3 It is a schematic diagram of the monitoring box of the present invention; Figure 4 The present invention is a schematic diagram of the structure of a monitoring data intelligent analysis system of a visual termite monitoring device.

[0020] In the figure: 1. Monitoring box; 2. Switch; 3. Edge device; 4. Network cable; 11. Industrial camera; 12. Light bulb; 13. Termite edible cylinder. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Termites, this extremely destructive pest is widely distributed around the world, and they pose a huge threat to buildings, farmland, and forestry resources. However, existing monitoring technologies face many challenges. For example, interference from environmental factors may reduce the accuracy of monitoring, and the efficiency of data transmission and analysis also affects the timeliness of monitoring, ultimately leading to insufficient overall monitoring efficiency. In response to these problems, the present invention proposes a monitoring data intelligent analysis method and system for a visual termite monitoring device, which aims to improve the efficiency of termite monitoring and provide a more scientific solution for termite prevention and control, thereby reducing the damage caused by termites. Please refer to Figures 1 to 4 , the technical solution of the present invention is as follows:

[0023] Embodiment 1 is as follows: Figure 1 The present invention is a flowchart of a method for intelligently analyzing monitoring data of a visual termite monitoring device.

[0024] like Figure 1 As shown, a monitoring data intelligent analysis method of a termite visualization monitoring device includes: refer to Figure 1 Step S1: designing a visual termite monitoring device, wherein the visual termite monitoring device is used to monitor termite activities; Figure 2 It is a schematic diagram of the structure of the visual termite monitoring device of the present invention.

[0025] Furthermore, if Figure 2 As shown, the termite visualization monitoring device includes a monitoring box 1, a switch 2 and an edge device 3; an industrial camera 11, a light bulb 12 and a termite edible cylinder 13 are installed in the monitoring box 1, the industrial camera 11 is connected to the switch 2 via a network cable 4, and the collected termite video frame is transmitted to the switch 2; the switch 2 is connected to the edge device 3 via the network cable 4; the edge device 3 receives the termite video frame, monitors the termite activity according to the termite video frame, and generates the termite data; the edge device 3 transmits the termite data to the cloud via a wireless network; the gray shaded part is the soil layer, the monitoring box 1 is buried under the soil layer, and the switch 2 and the edge device 3 are placed on the soil layer.

[0026] Figure 3 It is a schematic diagram of the monitoring box 1 of the present invention; Specifically, in this embodiment, Figure 3As shown, the monitoring box 1 has a size of 300 mm × 250 mm × 200 mm, a circumferential aperture of 5.0 mm, and is made of polypropylene, which is both sturdy and lightweight. The appearance design of the monitoring box 1 adopts a pull-out opening and closing mechanism, which not only improves its aesthetics but also makes it easier to operate. An industrial camera 11 is equipped inside the monitoring box 1 to capture clear termite activity videos. The model of the industrial camera 11 is ala2400-20gm, equipped with a 2 / 3-inch chip and a 5mm lens, which can provide a field of view of 245 mm × 205 mm at a working distance of 150 mm. In order to ensure that a clear image can be obtained under different lighting conditions, a bulb 12 is provided as a fill light device. In actual applications, the fill light function of the industrial camera 11 itself can be tested first. If its fill light effect is not ideal, the bulb 12 will be enabled to provide additional light source.

[0027] In addition, the monitoring box 1 is connected to the edge device 3 through the switch 2, which allows one switch 2 to connect multiple monitoring boxes 1, so that the edge device 3 can pull and manage multiple monitoring screens. In this embodiment, in order to simplify the operation process, only one monitoring box 1 is connected. The edge device 3 performs the extraction of termite video frames and the identification of termite activities by accessing the switch 2, and transmits data through the 4G network, ensuring the real-time and transmission efficiency of the monitoring data. Among them, for the identification of termite activities, the RK3588 computing platform is adopted, which can process data in real time and respond in seconds, so as to effectively identify the termite activities around the termite eating cylinder 13. In order to ensure a stable connection between the monitoring box 1 and the edge device 3, a sufficiently long network cable 4 is used, so that the monitoring box 1 can be flexibly deployed in various environments, whether indoors or outdoors, to ensure the stable operation of termite monitoring.

[0028] The capture, data processing and transmission of termite activities by this visual termite monitoring device can ensure the real-time and accuracy of termite monitoring, reduce the data transmission burden and cloud pressure, and thus improve the efficiency of termite monitoring.

[0029] refer to Figure 1 Step S2: according to the termite visualization monitoring device, an initial video frame without termite activity is obtained; the pixel average value of the initial video frame is calculated to obtain a background template; a new termite video frame is obtained, and the absolute difference between the termite video frame and the background template is calculated using a frame difference method; if the absolute difference is greater than a first threshold, the termite video frame is extracted; otherwise, the background template is updated according to the termite video frame; Among them, the calculation process of the background template is expressed as: ; in, The coordinates in the background template are The pixel value of The total number of selected frames can be 30; For the The frame coordinates are The pixel value of is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; is the frame sequence number of the initial video frame.

[0030] The frame difference method is used to calculate the absolute difference between the termite video frame and the background template, that is, the background template has changed, and termites may exist, which is expressed as: ; in, is the absolute difference matrix between the current termite video frame and the background template, is the coordinate of the current termite video frame The pixel value of For the current moment.

[0031] Assume that the difference matrix is ​​expressed as: ; Assuming that the pixel value of pixel point (2,2) is 150 and the background template is 180, the absolute difference is 30. The first threshold is set to 25, then the pixel point (2,2) is marked as a suspected termite activity area, and the frame is extracted.

[0032] Furthermore, the process of updating the background template includes: ; in, The background template is updated; is the smoothing factor, ensuring that the background template is updated slowly to adapt to environmental changes; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template.

[0033] in, The update process is expressed as: ; in, is the smoothing factor, is the updated smoothing factor; is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

[0034] Specifically, in this embodiment, The initial value is set to 0.1. Set to 0.05. If the absolute difference is not greater than the first threshold, the background template is updated every 10 minutes, and the update time can be adjusted according to the actual situation. If the absolute difference is greater than the first threshold, the timestamp of the last update of the background template is recorded. When the absolute difference no longer changes, the current timestamp is recorded and the background template is updated. By dynamically updating the background template, it is possible to better adapt to environmental changes, such as changes in the termite edible cylinder 13. At the same time, it helps to distinguish termites from the background and avoid misjudging termites as part of the background, which can reduce the false detection rate and reduce the burden of data processing, thereby improving the efficiency of termite monitoring.

[0035] refer to Figure 1 Step S3: binarize the termite video frame, use the termite detection model to obtain the bounding box coordinates and the number of bounding boxes; if the number of bounding boxes is greater than a second threshold, issue a first alarm message; if the number of bounding boxes is greater than zero, segment the termite video frame to obtain a grid area; calculate the termite movement direction and termite movement speed according to the bounding box coordinates and the grid area; combine the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp into termite data and send it to the cloud.

[0036] The termite detection model may be YOLO or Faster R-CNN. In this embodiment, YOLOV8 is selected as the termite detection model. YOLOV8 outputs a set of bounding box coordinates according to the termite video frame, and these bounding boxes surround each termite area in the video frame. The number of bounding boxes is counted to obtain the number of termites. In this embodiment, the second threshold value may be set to 10, which indicates that the termite activity is abnormal, triggers the first alarm information, and notifies the system to warn, thereby indicating that the termite activity is intensive.

[0037] In addition, if the number of bounding boxes is greater than zero, the current termite video frame is segmented into multiple small grid areas. Assuming that the size of the video frame is W×H, the video frame can be segmented into m×n grids to obtain m×n small areas. For example, for a video frame with a resolution of 800×600, it can be divided into 4×3 grids, and the size of each small grid is 200×200 pixels. Through this segmentation, each grid area is regarded as a group of termite colonies, and each group of termite colonies is assigned a unique ID through DeepSORT, and its cross-frame trajectory is continuously tracked. By analyzing each area independently, the accuracy of identifying termites with different behaviors is improved, while avoiding the problem of excessive data volume caused by excessive segmentation, thereby improving the efficiency of termite monitoring.

[0038] Furthermore, the calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; The coordinates of the termite center are averaged for each frame to obtain the coordinates of the termite center of gravity, which is expressed as: ; in, is the horizontal center of gravity, is the vertical center of gravity, are the coordinates of the termite center of gravity, is the number of termites in the current frame, For the The coordinates of the termite centers, is the termite center coordinate sequence number.

[0039] The termite displacement vector is calculated using the Euclidean formula for the coordinates of the termite center of gravity in the continuous frames, and the termite movement speed is obtained according to the termite displacement vector, which is expressed as: ; in, is the termite displacement vector, For the Frame termite center of gravity coordinates, For the Frame termite center of gravity coordinates, is the termite movement speed, is the inter-frame time, is the current time.

[0040] The termite moving direction is calculated using the azimuth calculation formula for the termite center coordinates of the continuous frames, and is expressed as: ; in, The direction of termite movement.

[0041] By treating the entire grid area as a group, the tracking of individual termites is simplified and the computational cost is reduced. In addition, by calculating the center of gravity trajectory, the movement direction and speed of termite activities can be clearly reflected, which helps to determine the diffusion trend of the group and provide data support for the study of termite activities, thereby improving the efficiency of termite monitoring.

[0042] refer to Figure 1 Step S4: Acquire the termite data from the cloud, calculate the mobility index, activity index, frequency index and termite activity level based on the termite data; acquire environmental data, output the future termite activity level using an activity prediction model based on the environmental data and the termite activity level, and issue a second alarm message based on the future termite activity level.

[0043] Furthermore, the calculation process of the movement index, the activity index, the frequency index and the termite activity level includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; It is expressed as: ; in, is the movement index, i.e. the average direction and concentration of termites, ranging from , the higher the concentration, the larger the value; is the number of termite movement directions obtained within a fixed time period, is the serial number of the termite's moving direction; is the cosine function; is a sine function; For the The direction in which termites move.

[0044] According to the fixed time period, the moving speeds of the termites are averaged to obtain an average moving speed of the termites; the average moving speed of the termites is weighted and multiplied by the number of the bounding boxes to obtain the activity index, which is expressed as: ; in, is the activity index, is the length of a fixed time period, For the The weight of the timestamp, For the The average termite movement speed at the timestamp, For the The number of bounding boxes at the timestamp.

[0045] in, By assigning different weights to timestamps, more attention can be paid to specific timestamps. Set both to 1.

[0046] According to the fixed time period, the number of changes in the number of bounding boxes is counted, and the number of changes is divided by the length of the fixed time period to obtain the frequency index, which is expressed as: ; in, is the frequency index, is the number of changes in the number of bounding boxes, The duration of a fixed time period.

[0047] The mobility index, the activity index and the frequency index are normalized and weighted summed to obtain the termite activity level, which is expressed as: ; in, The activity level of termites. , and are weight factors for the mobility index, activity index, and frequency index, which may be 0.3, 0.5, and 0.2, respectively.

[0048] Specifically, in this embodiment, the fixed time period is set to 10 seconds. The mobility index can be used to measure whether the overall movement direction of termites in a time period is concentrated. If the movement direction of termites is highly consistent, it means that the termites are performing collective behavior, such as looking for food or migrating. The calculation of the activity index combines the movement speed and activity range of termites, which helps to understand the activity level of termite colonies in a specific environment. The frequency index can reveal the fluctuation frequency of termite activities. If the activities of termites change frequently, it means that their behavior may be more unstable. By analyzing the frequency index, we can better understand the sensitivity of termite colonies to environmental changes. The multi-dimensional analysis of termite activities through mobility index, activity index and frequency index can fully reflect the characteristics and laws of their activities, and the factors of concern can be adjusted according to actual needs, providing data support for subsequent predictions of future termite activity levels, thereby improving the efficiency of termite monitoring.

[0049] Furthermore, data related to the termite habitat is obtained through sensors or local environmental monitoring systems. This may be the temperature, humidity, light intensity, etc. of the termite habitat. In addition, the activity prediction model may select an LSTM model. The LSTM model can effectively predict future termite activity based on historical data. After inputting environmental data and termite activity levels into the LSTM model, the LSTM model outputs future termite activity levels, that is, termite activity levels at the next moment. If the future termite activity level exceeds the third threshold, a second alarm message is issued to warn the operator that termite activity may be abnormal in the future. By combining environmental data to predict termite activity, the efficiency of termite monitoring and early warning is improved, providing a strong guarantee for timely prevention and control measures.

[0050] Through the termite visualization monitoring device, relevant video data of termite activities can be obtained in real time, and effective background modeling and difference calculation can be performed through the frame difference method to accurately distinguish the difference between termite activities and the background environment, ensuring that the capture of termite activities is not interfered with by external factors. The termite detection model is used to extract the coordinates and number of the termite boundary box. When the termite activity reaches a certain threshold, the first alarm message will be automatically issued to notify the staff to take corresponding measures in time, thereby enhancing the sensitivity and response speed of termite monitoring. Then, by calculating the movement direction and speed of termites, combined with the number of boundary boxes and timestamps, detailed termite activity data is generated, which can not only be used for real-time monitoring, but also provide data support for subsequent activity trend analysis and prediction. All termite data is sent to the cloud, combined with environmental data and the termite activity level calculated in real time, and the activity prediction model is used to predict future termite activities. If the prediction results show that the termite activity will reach a dangerous level in the future, the system will automatically issue a second alarm message, take preventive measures in advance, improve the efficiency of termite monitoring, and reduce potential damage.

[0051] Based on the intelligent analysis method for monitoring data of a visual termite monitoring device provided in Example 1, a real estate development company uses an intelligent analysis system for monitoring data of a visual termite monitoring device to ensure the structural safety of buildings after delivery because the project is located in a humid and hot environment and the underground infrastructure is very likely to become a place for termite activities. Monitoring devices are deployed in the basement and surrounding green belts, and the data is connected to the cloud platform to help developers prevent termite hazards during construction and improve the efficiency of termite monitoring.

[0052] Embodiment 2 is as follows: Figure 4 The present invention is a schematic diagram of the structure of a monitoring data intelligent analysis system of a visual termite monitoring device.

[0053] like Figure 4As shown, a monitoring data intelligent analysis system of a termite visualization monitoring device includes: Reference Figure 4 The design module of the termite visual monitoring device is used to monitor termite activities; Reference Figure 4 The video acquisition module in the design module of the termite visualization monitoring device is used to obtain an initial video frame without termite activity according to the design module, calculate the pixel average value of the initial video frame, and obtain a background template; obtain a new termite video frame, and use a frame difference method to calculate the absolute difference between the termite video frame and the background template; if the absolute difference is greater than a first threshold, extract the termite video frame; otherwise, update the background template according to the termite video frame; Reference Figure 4 The edge processing module in the termite video frame is used to binarize the termite video frame, and use the termite detection model to obtain the bounding box coordinates and the number of bounding boxes; if the number of bounding boxes is greater than a second threshold, a first alarm message is issued; if the number of bounding boxes is greater than zero, the termite video frame is segmented to obtain a grid area; the termite movement direction and the termite movement speed are calculated according to the bounding box coordinates and the grid area; the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp are combined into termite data and sent to the cloud; Reference Figure 4 The cloud processing module in the system is used to obtain the termite data from the cloud, calculate the mobility index, activity index, frequency index and termite activity level based on the termite data; obtain environmental data, use an activity prediction model to output the future termite activity level based on the environmental data and the termite activity level, and issue a second alarm message based on the future termite activity level.

[0054] Figure 2 It is a schematic diagram of the structure of the visual termite monitoring device of the present invention.

[0055] Furthermore, if Figure 2 As shown, the termite visualization monitoring device includes a monitoring box 1, a switch 2 and an edge device 3; an industrial camera 11, a light bulb 12 and a termite edible cylinder 13 are installed in the monitoring box 1, the industrial camera 11 is connected to the switch 2 via a network cable 4, and the collected termite video frame is transmitted to the switch 2; the switch 2 is connected to the edge device 3 via the network cable 4; the edge device 3 receives the termite video frame, monitors the termite activity according to the termite video frame, and generates the termite data; the edge device 3 transmits the termite data to the cloud via a wireless network; the gray shaded part is the soil layer, the monitoring box 1 is buried under the soil layer, and the switch 2 and the edge device 3 are placed on the soil layer.

[0056] Table 1 Example of the composition of industrial camera 11

[0057] Among them, the composition of the industrial camera 11 is shown in Table 1, including an industrial camera, an industrial lens, a power cord and a data cord. The equipment of this configuration can operate stably in a variety of environments without incurring excessively high equipment costs, and provides stable video transmission and image processing, enhancing the adaptability of the system, thereby improving the efficiency of termite monitoring.

[0058] Furthermore, the process of updating the background template includes: ; in, The background template is updated; is the smoothing factor; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; in, The update process is expressed as: ; in, is the smoothing factor, is the updated smoothing factor; is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

[0059] Furthermore, the calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; Taking the average value of the termite center coordinates in each frame to obtain the termite center of gravity coordinates; For the coordinates of the termite center of gravity of the continuous frames, the termite displacement vector is calculated using the Euclidean formula, and the termite movement speed is obtained according to the termite displacement vector; The termite moving direction is calculated using an azimuth calculation formula for the termite center of gravity coordinates of continuous frames.

[0060] Furthermore, the calculation process of the movement index, the activity index, the frequency index and the termite activity level includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; According to the fixed time period, averaging the termite movement speeds to obtain an average termite movement speed; weighted multiplying the average termite movement speed by the number of bounding boxes to obtain the activity index; According to the fixed time period, counting the number of changes in the number of bounding boxes, and dividing the number of changes by the length of the fixed time period to obtain the frequency index; The termite activity degree is obtained by weighted summing the movement index, the activity index and the frequency index.

[0061] Specifically, in this embodiment, the termite detection model uses the YOLOv5 model, which is trained using pre-labeled video frame images of termite activities to generate bounding boxes as detection targets. Faster R-CNN and SSD are selected as comparison models, and the performance comparison on the test set is shown in Table 2. It can be seen from the table that YOLOv5 has the highest detection accuracy and is particularly suitable for termite detection tasks.

[0062] The activity prediction model selects the Transformer-LSTM hybrid model that combines multi-scale features, including the Transformer module and the LSTM module. The Transformer module can capture the long-range dependency characteristics of termite data, and the LSTM module can extract the dynamic characteristics of activity intensity in a short period of time. Then, the Transformer output and the LSTM output are fused through the fully connected layer to obtain the future termite activity level. The Transformer-LSTM hybrid model is compared with other time series prediction models. As shown in Table 3, the other three prediction models are given. It can be seen from the table that the Transformer-LSTM model performs best in MAE and MAPE indicators, indicating that it has excellent ability to extract long-term and short-term features. The R² value is closest to 1, indicating that the prediction result is most consistent with the real data. By combining the above models, it is possible to monitor termite activities in real time and provide high-precision activity trend prediction, providing comprehensive support for termite control.

[0063] Table 2 Performance comparison of termite detection models

[0064] Table 3 Performance comparison of activity prediction models

[0065] The project site was divided into two experimental areas. Area A used the visual termite monitoring device of the present invention, and area B used a traditional termite trap. The traditional trap attracts termites through bait. When termites enter the trap and eat the bait material, their activities trigger the internal gravity device, and the captured termites are retained by the collection device. Ensure that the two devices are started in the experiment and run continuously for 30 days, and record relevant data for comparison.

[0066] The experimental results show that the average response time of area A is about 5 minutes, and the average response time of area B is about 6 minutes. Area A has a shorter response time and stronger real-time performance, which is suitable for high-frequency monitoring tasks. The false alarm rate of area A is less than 10%, and the false alarm rate of area B is about 11%. The false alarm rate of area A is lower than that of area B, which can reduce false alarm interference. In addition, area B cannot predict activities, and the prediction error of area A is about 8.2%, which can more effectively capture active termite colonies, thereby improving the efficiency of termite monitoring.

[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A monitoring data intelligent analysis method of a termite visual monitoring device, characterized in that: include: Step S1: designing a visual termite monitoring device, wherein the visual termite monitoring device is used to monitor termite activities; Step S2: according to the termite visualization monitoring device, an initial video frame that does not contain the termite activity is obtained; the pixel average value of the initial video frame is calculated to obtain a background template; a new termite video frame is obtained, and the absolute difference between the termite video frame and the background template is calculated using a frame difference method; if the absolute difference is greater than a first threshold, the termite video frame is extracted; otherwise, the background template is updated according to the termite video frame; Step S3: Binarize the termite video frame, and use the termite detection model to obtain the bounding box coordinates and the number of bounding boxes; if the number of bounding boxes is greater than a second threshold, issue a first alarm message; if the number of bounding boxes is greater than zero, segment the termite video frame to obtain a grid area; obtain the termite movement direction and termite movement speed according to the bounding box coordinates and the grid area; combine the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp into termite data and send it to the cloud; Step S4: Obtain the termite data from the cloud, and calculate the movement index, activity index, frequency index and termite activity level; Environmental data is acquired, future termite activity levels are output using an activity prediction model according to the environmental data and the termite activity levels, and a second alarm message is issued according to the future termite activity levels.

2. The monitoring data intelligent analysis method of a termite visual monitoring device according to claim 1 is characterized in that: The termite visual monitoring device comprises a monitoring box (1), a switch (2) and an edge device (3); an industrial camera (11), a light bulb (12) and a termite edible cylinder (13) are installed in the monitoring box (1); the industrial camera (11) is connected to the switch (2) via a network cable (4) and transmits the collected termite video frames to the switch (2); the switch (2) is connected to the edge device (3) via the network cable (4); the edge device (3) receives the termite video frames, monitors the termite activities according to the termite video frames, and generates the termite data; the edge device (3) transmits the termite data to the cloud via a wireless network.

3. The monitoring data intelligent analysis method of a termite visual monitoring device according to claim 1 is characterized in that: The background template updating process includes: ； in, The updated coordinates are The background template; is the smoothing factor; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; in, The update process is expressed as: ； in, is the updated smoothing factor; is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

4. The monitoring data intelligent analysis method of a termite visual monitoring device according to claim 1 is characterized in that: The calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; Taking the average value of the termite center coordinates in each frame to obtain the termite center of gravity coordinates; For the coordinates of the termite center of gravity of the continuous frames, the termite displacement vector is calculated using the Euclidean formula, and the termite movement speed is obtained according to the termite displacement vector; The termite moving direction is calculated using an azimuth calculation formula for the termite center of gravity coordinates of continuous frames.

5. The monitoring data intelligent analysis method of a termite visual monitoring device according to claim 1, characterized in that: The calculation process of the movement index, the activity index, the frequency index and the termite activity degree includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; According to the fixed time period, averaging the termite movement speeds to obtain an average termite movement speed; weighted multiplying the average termite movement speed by the number of bounding boxes to obtain the activity index; According to the fixed time period, counting the number of changes in the number of bounding boxes, and dividing the number of changes by the length of the fixed time period to obtain the frequency index; The termite activity degree is obtained by weighted summing the movement index, the activity index and the frequency index.

6. A monitoring data intelligent analysis system for a visual termite monitoring device, characterized in that: include: Termite visual monitoring device design module, used to monitor termite activities; A video acquisition module is used to design a module for the visual termite monitoring device, obtain an initial video frame that does not contain the termite activity, calculate the pixel average of the initial video frame, and obtain a background template; obtain a new termite video frame, and use a frame difference method to calculate the absolute difference between the termite video frame and the background template; if the absolute difference is greater than a first threshold, extract the termite video frame; otherwise, update the background template according to the termite video frame; The edge processing module is used to binarize the termite video frame, obtain the bounding box coordinates and the number of bounding boxes using the termite detection model; if the number of bounding boxes is greater than a second threshold, issue a first alarm message; if the number of bounding boxes is greater than zero, segment the termite video frame to obtain a grid area; calculate the termite movement direction and termite movement speed according to the bounding box coordinates and the grid area; combine the termite movement direction, the termite movement speed, the number of bounding boxes and the timestamp into termite data and send it to the cloud; A cloud processing module, used for obtaining the termite data from the cloud, and calculating a movement index, an activity index, a frequency index and a termite activity degree according to the termite data; Environmental data is acquired, future termite activity levels are output using an activity prediction model according to the environmental data and the termite activity levels, and a second alarm message is issued according to the future termite activity levels.

7. The monitoring data intelligent analysis system of the termite visual monitoring device according to claim 6 is characterized in that: The termite visual monitoring device comprises a monitoring box (1), a switch (2) and an edge device (3); an industrial camera (11), a light bulb (12) and a termite edible cylinder (13) are installed in the monitoring box (1); the industrial camera (11) is connected to the switch (2) via a network cable (4) and transmits the collected termite video frames to the switch (2); the switch (2) is connected to the edge device (3) via the network cable (4); the edge device (3) receives the termite video frames, monitors the termite activities according to the termite video frames, and generates the termite data; the edge device (3) transmits the termite data to the cloud via a wireless network.

8. The monitoring data intelligent analysis system of the termite visual monitoring device according to claim 6, characterized in that: The background template updating process includes: ； in, The background template is updated; is the smoothing factor; is the pixel value of the current termite video frame; is the background template; for the current moment; is the horizontal distance from the lower left corner of the background template; is the vertical distance from the lower left corner of the background template; in, The update process is expressed as: ； in, is the updated smoothing factor, is a constant that controls the speed increase; is the timestamp of the current update of the background template, is the timestamp of the last update of the background template.

9. The monitoring data intelligent analysis system of the termite visual monitoring device according to claim 6, characterized in that: The calculation process of the termite movement direction and termite movement speed includes: For the bounding box coordinates in each of the grid areas, generating termite center coordinates; Taking the average value of the termite center coordinates in each frame to obtain the termite center of gravity coordinates; For the coordinates of the termite center of gravity of the continuous frames, the termite displacement vector is calculated using the Euclidean formula, and the termite movement speed is obtained according to the termite displacement vector; The termite moving direction is calculated using an azimuth calculation formula for the termite center of gravity coordinates of continuous frames.

10. The monitoring data intelligent analysis system of the termite visual monitoring device according to claim 6, characterized in that: The calculation process of the movement index, the activity index, the frequency index and the termite activity degree includes: Setting a fixed time period, and performing a direction distribution analysis on the termite movement direction according to the fixed time period to obtain the movement index; According to the fixed time period, averaging the termite movement speeds to obtain an average termite movement speed; weighted multiplying the average termite movement speed by the number of bounding boxes to obtain the activity index; According to the fixed time period, counting the number of changes in the number of bounding boxes, and dividing the number of changes by the length of the fixed time period to obtain the frequency index; The termite activity degree is obtained by weighted summing the movement index, the activity index and the frequency index.

Images