Ecological monitoring method and device based on image recognition, equipment and medium

Abstract

The invention relates to an ecological monitoring method and device based on image recognition, equipment and a medium, and is applied to the technical field of ecological monitoring, and the method comprises the steps: obtaining image data and environment monitoring data; identifying the image data to obtain an environment monitoring condition; determining an abnormal condition based on the environment monitoring data and the environment monitoring condition; winged insect detection data are obtained; and determining an abnormal management and control strategy based on the abnormal condition and the winged insect detection data. The method has the effect of improving the efficiency and reliability of ecological monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological monitoring, and in particular to an ecological monitoring method and device based on image recognition, an ecological monitoring equipment and medium. BACKGROUND

[0002] Ecological monitoring technology plays an important role in modern environmental protection and resource management, especially in the application of key areas such as airports, which can significantly improve the identification efficiency and response speed of environmental abnormalities. With the rapid development of the aviation industry, the complexity of the airport ecological environment is increasing, and in the face of the complex environment of the airport runway and surrounding areas, in order to comprehensively and accurately identify and evaluate the safety hazards caused by plant and animal interference, higher requirements are put forward for ecological monitoring technology.

[0003] At present, in the field of airport ecological monitoring, common technical means mainly include manual inspection and fixed sensor monitoring. Although manual inspection can flexibly deal with various environmental problems, it is low in efficiency, high in cost, and prone to errors caused by human factors; fixed sensor monitoring can realize continuous monitoring of specific environmental parameters, but its coverage is limited, which is difficult to meet the needs of airport wide-range monitoring. SUMMARY

[0004] In order to improve the efficiency and reliability of ecological monitoring, the present application provides an ecological monitoring method and device based on image recognition, an ecological monitoring equipment and medium.

[0005] In a first aspect, the present application provides an ecological monitoring method based on image recognition, which adopts the following technical scheme: An ecological monitoring method based on image recognition, comprising: obtaining image data and environmental monitoring data; identifying the image data to obtain an environmental monitoring situation; determining an abnormal situation based on the environmental monitoring data and the environmental monitoring situation; obtaining flying insect detection data; determining an abnormal control strategy based on the abnormal situation and the flying insect detection data.

[0006] By adopting the above technical scheme, the environmental monitoring situation is obtained by identifying the image data, and the abnormal situation is further determined in combination with the environmental monitoring data, and the flying insect detection data is introduced for comprehensive analysis to formulate the abnormal control strategy, that is, the image recognition technology and the comprehensive consideration of the environmental monitoring data and the flying insect detection data are used to formulate the abnormal control strategy, thereby improving the efficiency and reliability of ecological monitoring.

[0007] Optionally, before obtaining the image monitoring data, the method further comprises: Acquire a monitoring range and a camera monitoring range, the monitoring range comprising a plurality of monitoring sub-ranges; Acquire a security level and historical abnormal information of each monitoring sub-range; Analyze the historical abnormal information to determine a historical abnormal level of each monitoring sub-range; Determine a monitoring level of each monitoring sub-range based on the historical abnormal level and the security level; Determine a camera distribution based on the monitoring level and the camera monitoring range.

[0008] By using the above technical solution, the camera distribution is determined by analyzing the monitoring range and the camera monitoring range, combining the security level and the historical abnormal information of each monitoring sub-range, improving the rationality of the camera distribution and the monitoring efficiency, and not only fully monitoring the area with more abnormalities or higher security level, but also reducing resource waste.

[0009] Optionally, the image data is identified to obtain an environment monitoring situation, comprising: Identify the image data to obtain an initial environment monitoring situation; Determine the acquisition camera of each image data; Determine the associated image data with area overlap based on the acquisition camera; Correct the initial environment monitoring situation based on the associated image data to obtain the environment monitoring situation.

[0010] By using the above technical solution, the initial environment monitoring situation is obtained by identifying the image data, the associated image data with area overlap is found out by determining the acquisition camera, and the image information of multiple angles and multiple areas is effectively utilized; the reliability of the monitoring situation is improved by correcting the initial environment monitoring situation based on the associated image data.

[0011] Optionally, the initial environment monitoring situation comprises a monitoring value, and the initial environment monitoring situation is corrected based on the associated image data to obtain the environment monitoring situation, comprising: Divide the initial environment monitoring situation based on the associated image data to obtain a plurality of situation combinations; Determine whether the initial environment monitoring situation in each situation combination is consistent; If the initial environment monitoring situation in the situation combination is inconsistent, determine a deviation value based on the monitoring value; If the deviation value is less than a preset deviation value, acquire the acquisition accuracy of each acquisition camera; determine a correction weight according to the collection accuracy; correct the initial environment monitoring condition in the condition combination based on the correction weight, to obtain the environment monitoring condition.

[0012] By adopting the above technical solution, the initial environment monitoring condition is divided according to the associated image data, a plurality of condition combinations are obtained, which helps to systematically analyze the monitoring results of different regions and improves the orderliness of data processing. By judging whether the initial environment monitoring condition in each condition combination is consistent, the monitoring data that may have errors can be quickly identified, thereby providing a basis for subsequent correction. When the initial environment monitoring conditions in the condition combination are inconsistent, the deviation value is determined based on the monitoring value, which further quantifies the difference between the monitoring data and provides an objective standard for subsequent correction. When the deviation value is less than the preset deviation value, the collection accuracy of each collection camera is obtained, the correction weight is determined according to the collection accuracy, and the initial environment monitoring condition is corrected based on the correction weight, so that a more accurate environment monitoring condition is finally obtained, thereby improving the reliability and accuracy of ecological monitoring.

[0013] Optionally, the environment monitoring condition includes a runway monitoring condition and a lawn monitoring condition, and the determination of the abnormal condition based on the environment monitoring data and the environment monitoring condition includes: if there is a monitoring position with a monitoring value greater than 0 in the runway monitoring condition, a runway abnormal condition is generated; comparing the monitoring value in the lawn monitoring condition with a preset threshold to determine a current lawn abnormal condition; obtaining historical animal and plant growth information; analyzing the historical animal and plant growth information to obtain a corresponding relationship between the environment and the growth speed of animals and plants; based on the environment monitoring data, the corresponding relationship and the lawn monitoring condition, a predicted lawn abnormal condition is obtained; the abnormal condition is determined based on the runway abnormal condition, the current lawn abnormal condition and the predicted lawn abnormal condition.

[0014] By adopting the above technical solution, the runway abnormal condition is generated by judging the monitoring value in the runway monitoring condition, which can quickly locate potential problems on the runway and improve the efficiency of runway safety management. The current lawn abnormal condition is determined by comparing the lawn monitoring condition with the preset threshold, which helps to discover the immediate abnormal state of the lawn in a timely manner. The predicted lawn abnormal condition is obtained by predicting based on the environment monitoring data, the corresponding relationship between the environment and the growth speed of animals and plants, and the lawn monitoring condition, which realizes the upgrading from immediate monitoring to predictive monitoring and enhances the foresight of ecological monitoring.

[0015] Optionally, the determining of the abnormal management strategy based on the abnormal situation and the flying insect detection data comprises: determining an abnormal category based on the abnormal situation; obtaining an animal-plant growth correlation and a biological control measure; determining a first abnormal correlation based on the abnormal category and the animal-plant growth correlation, the first abnormal correlation comprising a positive correlation and a negative correlation; determining a flying insect category and a flying insect quantity based on the flying insect detection data; if the flying insect quantity exceeds a preset quantity, determining a second abnormal correlation based on the animal-plant growth correlation and the flying insect category; determining an abnormal management strategy based on the first abnormal correlation, the second abnormal correlation and the biological control measure.

[0016] By comprehensively considering the animal-plant growth correlation and the biological control measure to determine the abnormal management strategy, the reliability and the universal applicability of the abnormal management are improved.

[0017] Optionally, the method further comprises: obtaining historical abnormal information; dividing the historical abnormal information based on a preset period to obtain a plurality of historical abnormal combinations; analyzing the historical abnormal combinations to determine an abnormal frequency of each preset period; determining an initial data analysis frequency based on the abnormal frequency; obtaining aircraft take-off and landing information; adjusting the initial data analysis frequency based on the aircraft take-off and landing information to obtain a target data analysis frequency.

[0018] By periodically analyzing the historical abnormal information to determine the abnormal frequency, and then determining the initial data analysis frequency, and dynamically adjusting the data analysis frequency in combination with the aircraft take-off and landing information, the timeliness and the pertinence of the ecological monitoring are improved, so that the data analysis is performed at a higher frequency during a key period of aircraft take-off and landing, and thus the potential abnormal situation is more effectively discovered and responded to, and the reliability and the efficiency of the overall ecological monitoring are improved.

[0019] In a second aspect, the present application provides an ecological monitoring device based on image recognition, which adopts the following technical solution: An ecological monitoring device based on image recognition, comprising: a first data acquisition module, configured to acquire image data and environmental monitoring data; a monitoring situation determination module, configured to identify the image data to obtain an environmental monitoring situation; An exception condition determining module is configured to determine an exception condition based on the environmental monitoring data and the environmental monitoring condition; A second data obtaining module is configured to obtain flying insect detection data; A control strategy determining module is configured to determine an exception control strategy based on the exception condition and the flying insect detection data.

[0020] By using the above technical solutions, the environmental monitoring condition is obtained by identifying the image data, the exception condition is further determined based on the environmental monitoring data, the flying insect detection data is introduced, and the exception control strategy is formulated after comprehensive analysis, that is, the exception control strategy is formulated by using the image recognition technology and comprehensively considering the environmental monitoring data and the flying insect detection data, so that the efficiency and reliability of ecological monitoring are improved.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solutions: An electronic device includes a processor coupled with a memory; The memory stores a computer program capable of being loaded and executed by the processor to implement the image recognition-based ecological monitoring method of any one of the first aspect.

[0022] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solutions: A computer readable storage medium stores a computer program capable of being loaded and executed by the processor to implement the image recognition-based ecological monitoring method of any one of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a flowchart of an image recognition-based ecological monitoring method provided by an embodiment of the present application.

[0024] Figure 2 is a structural block diagram of an image recognition-based ecological monitoring device provided by an embodiment of the present application.

[0025] Figure 3 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application will be further described in detail below with reference to the accompanying drawings.

[0027] This application provides an image recognition-based ecological monitoring method, which can be executed by an electronic device. The electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, desktop computer, etc., but is not limited to these.

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0030] like Figure 1 As shown, an ecological monitoring method based on image recognition is described in the following steps (S101-S105): Step S101: Acquire image data and environmental monitoring data.

[0031] Multiple high-definition cameras are installed around the airport runway to collect image data of the runway and the surrounding grass. Image data is obtained from each high-definition camera, and environmental monitoring data is obtained from meteorological departments or various environmental sensors around the runway (such as temperature sensors, humidity sensors, etc.). The environmental monitoring data includes current environmental monitoring data as well as environmental monitoring data for a future preset time period (such as one week, 15 days, etc.).

[0032] Specifically, before acquiring image monitoring data, the method further includes: acquiring the monitoring range and the camera's monitoring range, wherein the monitoring range includes multiple monitoring sub-ranges; acquiring the security level and historical anomaly information of each monitoring sub-range; analyzing the historical anomaly information to determine the historical anomaly level of each monitoring sub-range; determining the monitoring level of each monitoring sub-range based on the historical anomaly level and the security level; and determining the camera distribution based on the monitoring level and the camera's monitoring range.

[0033] In this embodiment, the monitoring sub-ranges, i.e. the ranges where plant and animal monitoring is required, are obtained from the staff. Simultaneously, the monitoring range of the high-definition cameras used at the airport is also obtained from the staff. The safety level (pre-set by the staff based on the safety impact of the monitoring sub-range on aircraft takeoff and landing) and historical anomaly information for each monitoring sub-range are obtained from the database. The historical anomaly information is analyzed using data analysis tools to obtain the historical anomaly frequency for each monitoring sub-range. The database stores the correspondence between the historical anomaly frequency and historical anomaly level of each monitoring sub-range, as well as the correspondence between the historical anomaly level, safety level, and monitoring level of each monitoring sub-range. The historical anomaly level of each monitoring sub-range is obtained from the database using the historical anomaly frequency, and the monitoring level of each monitoring sub-range is obtained from the database using the historical anomaly level and safety level.

[0034] Different monitoring levels have different camera distribution densities. The higher the monitoring level, the greater the camera distribution density and the larger the distribution density coefficient. The initial number of cameras for each sub-area to be monitored = the size of the sub-area to be monitored / the size of the area that the camera can monitor. If the quotient is a decimal, it is rounded up. The corresponding distribution density coefficient is obtained from the database according to the monitoring level of the sub-area to be monitored. The target number of cameras for each sub-area to be monitored = the initial number of cameras × the distribution density coefficient. The cameras are distributed and installed in each sub-area to be monitored according to the target number of cameras. The data analysis tool can be Excel, Python, or SQL.

[0035] Step S102: Identify the image data to obtain the environmental monitoring information.

[0036] Specifically, the process of identifying image data to obtain environmental monitoring information includes: identifying image data to obtain initial environmental monitoring information; identifying the cameras that collect each image data; identifying related image data with overlapping areas based on the cameras; and correcting the initial environmental monitoring information based on the related image data to obtain the final environmental monitoring information.

[0037] In this embodiment, image data is identified using a preset image recognition model to obtain initial environmental monitoring information. This initial environmental monitoring information includes monitoring types, monitoring locations, and monitoring values. Monitoring types include various animals and plants; monitoring locations are the locations where animals and plants exist; and monitoring values ​​are the number of animals divided by the height of the plants. For example, monitoring location A contains plant 1 at height 'a', and monitoring location B contains animal 2 at number 'b'. The camera that collects each image data is determined based on its source. If the areas monitored by the cameras corresponding to two image data points overlap, these two image data points are considered related. Since the monitoring areas of multiple pairs of cameras overlap, there are multiple pairs of related image data. The initial environmental monitoring information obtained from an image data point is corrected based on all related image data points corresponding to that image data point to obtain the final environmental monitoring information. The preset image recognition model includes, for example, AlexNet, VGG, GoogLeNet, ResNet, Inception, and YOLO.

[0038] Specifically, the initial environmental monitoring situation includes monitored values. The environmental monitoring situation is then corrected based on associated image data to obtain the final environmental monitoring situation. This process includes: dividing the initial environmental monitoring situation into multiple combinations based on associated image data; determining whether the initial environmental monitoring situation in each combination is consistent; if the initial environmental monitoring situation in the combination is inconsistent, determining a deviation value based on the monitored values; if the deviation value is less than a preset deviation value, obtaining the acquisition accuracy of each acquisition camera; determining a correction weight based on the acquisition accuracy; and correcting the initial environmental monitoring situation in the combination based on the correction weight to obtain the final environmental monitoring situation.

[0039] In this embodiment, image data with associated image data is identified as first image data. Only the initial environmental monitoring situation obtained through the first image data needs to be corrected; the remaining initial environmental monitoring situations are the final environmental monitoring situations and do not require correction.

[0040] An image combination includes a first image data and all associated image data corresponding to the first image data. An image combination corresponds to a situation combination, which is the initial environmental monitoring situation corresponding to all image data in the image combination. The number of image combinations and the number of situation combinations are the same as the number of first image data. It is determined whether the initial environmental monitoring situation in each situation combination is consistent. If all the initial environmental monitoring situations in the situation combination have the same monitoring value of the same type of monitoring at the same monitoring location, then the initial environmental monitoring situation in the situation combination is consistent, and no correction is required.

[0041] Otherwise, if the initial environmental monitoring conditions in this combination are inconsistent, correction is required. The correction method is to calculate the deviation between every two monitoring values ​​corresponding to the same monitoring location and the same monitoring type in the combination. If all deviation values ​​are less than the preset deviation value (pre-set, not specifically limited here), the acquisition accuracy of each acquisition camera is obtained from the database. Taking the calculation of the correction weight corresponding to a monitoring value m as an example: if the acquisition accuracy of the acquisition camera corresponding to monitoring value m is x, the monitoring value of the same monitoring location and the same monitoring type corresponding to monitoring value m is determined as the first monitoring value (the first monitoring value includes monitoring value m). The correction weight corresponding to monitoring value m = x / the sum of the acquisition accuracy of all acquisition cameras corresponding to the first monitoring value. The monitoring value is corrected by the correction weight. The corrected monitoring value of a monitoring location and a monitoring type = the sum of the monitoring values ​​corresponding to all initial environmental monitoring conditions of that monitoring location and monitoring type × the corresponding correction weights. The environmental monitoring conditions include the corrected monitoring value.

[0042] If a deviation value is greater than or equal to a preset deviation value, the maximum monitoring value corresponding to that monitoring type at that monitoring location is determined as the corrected monitoring value, thus obtaining the final environmental monitoring situation.

[0043] Step S103: Determine abnormal situations based on environmental monitoring data and environmental monitoring conditions.

[0044] The environmental monitoring includes runway monitoring and turf monitoring. Runway monitoring refers to the environmental monitoring at the runway location, while turf monitoring refers to the environmental monitoring at the turf surrounding the runway.

[0045] Specifically, the process of identifying anomalies based on environmental monitoring data and the status of environmental monitoring includes: generating a runway anomaly if there are monitoring locations with values ​​greater than 0 in the runway monitoring data; comparing the monitoring values ​​in the turf monitoring data with preset thresholds to determine the current turf anomaly; acquiring historical plant and animal growth information; analyzing the historical plant and animal growth information to obtain the correspondence between the environment and plant and animal growth rates; making predictions based on environmental monitoring data, the correspondence, and the turf monitoring data to obtain predicted turf anomalies; and confirming the anomaly based on the runway anomaly, the current turf anomaly, and the predicted turf anomaly.

[0046] In this embodiment, since no plants or animals are allowed at any height of the track, if there is a monitoring location with a monitoring value greater than 0 in the track monitoring data, a track anomaly is generated. The track anomaly includes the monitoring location, monitoring type, and monitoring value of the monitoring value greater than 0 in the track monitoring data. The monitoring value in the lawn monitoring data is compared with a preset threshold (a preset allowable height of plants or number of animals). If the monitoring value of a monitoring type exceeds the corresponding preset threshold, a current lawn anomaly is generated. The current lawn anomaly includes the monitoring location, monitoring type, and monitoring value of the monitoring value exceeding the preset threshold.

[0047] Historical plant and animal growth information is obtained from staff or databases, which records animal reproduction and growth as well as plant growth under various environments. This historical growth information is analyzed using data analysis tools to determine the correlation between the environment and plant and animal growth rates. This correlation is then used to train machine learning algorithms, such as neural networks and support vector machines, to create a growth prediction model. Current monitoring values ​​and environmental monitoring data are input into the growth prediction model to obtain monitoring values ​​for various monitoring types at different future times. When a monitoring value at a future time exceeds a preset threshold, a predicted lawn anomaly is generated. Monitoring values ​​exceeding the preset threshold are identified as anomalies. The time, monitoring location, and monitoring type corresponding to the anomaly value are respectively identified as the anomaly time, anomaly location, and anomaly type. The predicted lawn anomaly includes the anomaly time and the corresponding anomaly location, anomaly type, and anomaly value. The track anomaly, the current lawn anomaly, and the predicted lawn anomaly are collectively identified as an anomaly.

[0048] Step S104: Obtain flying insect detection data.

[0049] Intelligent insect monitoring lights are installed around the runway. These lights can attract and kill flying insects, and at the same time identify images of the killed insects to obtain insect detection data for different time periods. The insect detection data obtained from the intelligent insect monitoring lights includes the detection time period, the type of flying insect, and the number of flying insects.

[0050] Step S105: Determine the anomaly control strategy based on the abnormal situation and the flying insect detection data.

[0051] Specifically, anomaly control strategies are determined based on abnormal situations and flying insect detection data, including: identifying the type of anomaly based on the abnormal situation; obtaining correlations between plant and animal growth and biological control measures; determining a first abnormal correlation based on the type of anomaly and the correlation between plant and animal growth, the first abnormal correlation including positive and negative correlations; determining the type and number of flying insects based on flying insect detection data; if the number of flying insects exceeds a preset number, determining a second abnormal correlation based on the correlation between plant and animal growth and the type of flying insect; and determining anomaly control strategies based on the first abnormal correlation, the second abnormal correlation, and biological control measures.

[0052] In this embodiment, the abnormality type is identified from the abnormal situations, i.e., the monitored types of abnormal situations. Plant and animal growth correlations and biological control measures are obtained from the database. Plant and animal growth correlations include the mutual influence relationships of various plant and animal growth, including positive and negative correlations. A positive correlation is, for example, that the growth of plant A promotes the survival and reproduction of animal B; a negative correlation is, for example, that the growth of plant A inhibits the survival and reproduction of animal C. The first abnormal correlation corresponding to the abnormal type is then identified from the plant and animal growth correlations. For example, if the abnormal type is animal C, then the first abnormal correlation includes plant A. The first abnormal correlation includes positive correlations (i.e., plant and animal types that promote the growth of the abnormal type) and negative correlations (i.e., plant and animal types that inhibit the growth of the abnormal type). Flying insects are then identified from the flying insect detection data. The types and number of flying insects; if the number of flying insects exceeds a preset number (preset, not specifically limited here), then a second abnormal association is determined based on the relationship between plant and animal growth and the types of flying insects. The types of flying insects corresponding to the number of flying insects exceeding the preset number are identified as abnormal types. The second abnormal association also includes positive associations (i.e., plant and animal types that promote the growth of abnormal types) and negative associations (i.e., plant and animal types that inhibit the growth of abnormal types). Abnormal control strategies include inhibiting the growth of plant and animal types corresponding to positive associations (or reducing the planting of plant and animal types corresponding to positive associations) according to biological control measures, or promoting the growth of plant and animal types corresponding to negative associations (or increasing the planting of plant and animal types corresponding to negative associations), or directly controlling abnormal types according to biological control measures.

[0053] Specifically, the method also includes: acquiring historical anomaly information; dividing the historical anomaly information based on a preset period to obtain multiple historical anomaly combinations; analyzing the historical anomaly combinations to determine the anomaly frequency of each preset period; determining the initial data analysis frequency based on the anomaly frequency; acquiring aircraft takeoff and landing information; and adjusting the initial data analysis frequency based on the aircraft takeoff and landing information to obtain the target data analysis frequency.

[0054] In this embodiment, historical anomaly information is retrieved from the database and divided into multiple historical anomaly combinations according to preset periods (e.g., one month, one quarter, half a year, etc.), each corresponding to a preset period. Data analysis tools are used to analyze these historical anomaly combinations to obtain the anomaly frequency for each preset period. The database stores the correspondence between anomaly frequencies and initial data analysis frequencies. The initial data analysis frequency is retrieved from the database based on the anomaly frequency. Aircraft takeoff and landing information, including takeoff and landing times, is retrieved from staff or the database within a preset timeframe before takeoff and landing. Within the time periods of [takeoff time - preset duration, takeoff time] and [landing time - preset duration, landing time], the initial data analysis frequency is adjusted to obtain the target data analysis frequency. The target data analysis frequency = initial data analysis frequency × preset ratio. Here, the preset ratio (greater than 1) and the preset duration are pre-set and not specifically limited here. Within the preset duration before aircraft takeoff and landing, image recognition and data analysis are performed according to the target data analysis frequency. At other times, image recognition and data analysis are performed according to the initial data analysis frequency. This improves the monitoring efficiency within the preset duration before aircraft takeoff and landing while reducing resource consumption at other times.

[0055] Figure 2 This is a structural block diagram of an image recognition-based ecological monitoring device 200 provided in an embodiment of this application.

[0056] like Figure 2 As shown, the image recognition-based ecological monitoring device 200 mainly includes: The first data acquisition module 201 is used to acquire image data and environmental monitoring data; The monitoring status determination module 202 is used to identify image data to obtain environmental monitoring status; Anomaly determination module 203 is used to determine anomalies based on environmental monitoring data and environmental monitoring conditions; The second data acquisition module 204 is used to acquire flying insect detection data; The control strategy determination module 205 is used to determine the anomaly control strategy based on the abnormal situation and the flying insect detection data.

[0057] As an optional implementation of this embodiment, the first data acquisition module 201 is specifically used to, before acquiring image monitoring data, further include: acquiring the monitoring range and the camera's monitoring range, the monitoring range including multiple monitoring sub-ranges; acquiring the security level and historical anomaly information of each monitoring sub-range; analyzing the historical anomaly information to determine the historical anomaly level of each monitoring sub-range; determining the monitoring level of each monitoring sub-range based on the historical anomaly level and the security level; and determining the camera distribution based on the monitoring level and the camera's monitoring range.

[0058] As an optional implementation of this embodiment, the monitoring status determination module 202 is specifically used to identify image data to obtain environmental monitoring status, including: identifying image data to obtain initial environmental monitoring status; determining the acquisition camera for each image data; determining related image data with overlapping areas based on the acquisition camera; and correcting the initial environmental monitoring status based on the related image data to obtain environmental monitoring status.

[0059] As an optional implementation of this embodiment, the initial environmental monitoring situation includes monitoring values. The monitoring situation determination module 202 is specifically used to correct the initial environmental monitoring situation based on associated image data to obtain the environmental monitoring situation, including: dividing the initial environmental monitoring situation based on associated image data to obtain multiple situation combinations; determining whether the initial environmental monitoring situation in each situation combination is consistent; if the initial environmental monitoring situation in the situation combination is inconsistent, determining a deviation value based on the monitoring values; if the deviation value is less than a preset deviation value, obtaining the acquisition accuracy of each acquisition camera; determining a correction weight based on the acquisition accuracy; and correcting the initial environmental monitoring situation in the situation combination based on the correction weight to obtain the environmental monitoring situation.

[0060] As an optional implementation of this embodiment, the environmental monitoring status includes track monitoring status and lawn monitoring status. The anomaly determination module 203 is specifically used to determine anomalies based on environmental monitoring data and environmental monitoring status, including: if there is a monitoring location in the track monitoring status with a monitoring value greater than 0, then a track anomaly is generated; the monitoring value in the lawn monitoring status is compared with a preset threshold to determine the current lawn anomaly; historical plant and animal growth information is obtained; the historical plant and animal growth information is analyzed to obtain the correspondence between the environment and plant and animal growth rates; prediction is made based on environmental monitoring data, the correspondence, and lawn monitoring status to obtain a predicted lawn anomaly; and anomalies are determined based on the track anomaly, the current lawn anomaly, and the predicted lawn anomaly.

[0061] As an optional implementation of this embodiment, the control strategy determination module 205 is specifically used to determine an anomaly control strategy based on anomaly conditions and flying insect detection data, including: determining the type of anomaly based on the anomaly conditions, including animal anomalies and plant anomalies; obtaining the correlation between animal and plant growth and biological control measures; determining a first anomaly correlation based on the type of anomaly and the correlation between animal and plant growth, including positive correlation and negative correlation; determining the type and number of flying insects based on the flying insect detection data; if the number of flying insects exceeds a preset number, determining a second anomaly correlation based on the correlation between animal and plant growth and the type of flying insects; and determining the anomaly control strategy based on the first anomaly correlation, the second anomaly correlation, and the biological control measures.

[0062] As an optional implementation of this embodiment, the image recognition-based ecological monitoring device 200 is further specifically used for: acquiring historical anomaly information; dividing the historical anomaly information based on a preset period to obtain multiple historical anomaly combinations; analyzing the historical anomaly combinations to determine the anomaly frequency of each preset period; determining the initial data analysis frequency based on the anomaly frequency; acquiring aircraft take-off and landing information; and adjusting the initial data analysis frequency based on the aircraft take-off and landing information to obtain the target data analysis frequency.

[0063] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0064] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0065] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0066] Figure 3 This is a structural block diagram of an electronic device 300 provided in an embodiment of this application.

[0067] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0068] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps of the image recognition-based ecological monitoring method described above. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0069] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used for wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0070] The electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the image recognition-based ecological monitoring method given in the above embodiments.

[0071] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0072] Electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers, and may also be servers.

[0073] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described image recognition-based ecological monitoring method.

[0074] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0075] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0076] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. An ecological monitoring method based on image recognition, characterized in that, include: Acquire image data and environmental monitoring data; The image data is identified to obtain environmental monitoring information; Anomalies are determined based on the environmental monitoring data and the environmental monitoring situation. Acquire flying insect detection data; An anomaly control strategy is determined based on the aforementioned anomaly and the insect detection data.

2. The method according to claim 1, characterized in that, Prior to acquiring the image monitoring data, the method further includes: The area to be monitored and the area that the camera can monitor are obtained, wherein the area to be monitored includes multiple sub-areas to be monitored; Obtain the security level and historical anomaly information of each of the monitored sub-ranges; The historical anomaly information is analyzed to determine the historical anomaly level of each of the monitored sub-ranges; The monitoring level of each of the sub-ranges to be monitored is determined based on the historical anomaly level and the security level. The distribution of cameras is determined based on the monitoring level and the monitoring range of the cameras.

3. The method according to claim 1, characterized in that, The process of identifying the image data to obtain environmental monitoring information includes: The image data is identified to obtain the initial environmental monitoring information; Identify the cameras that acquire the image data; Based on the acquisition camera, related image data with overlapping areas are determined; The initial environmental monitoring data is corrected based on the associated image data to obtain the final environmental monitoring data.

4. The method according to claim 3, characterized in that, The initial environmental monitoring data includes monitoring values. The process of correcting the initial environmental monitoring data based on the associated image data to obtain the final environmental monitoring data includes: Based on the associated image data, the initial environmental monitoring situation is divided into multiple combinations of situations; Determine whether the initial environmental monitoring conditions are consistent in each of the aforementioned combinations of situations; If the initial environmental monitoring conditions in the combination of conditions are inconsistent, then the deviation value is determined based on the monitoring value; If the deviation value is less than the preset deviation value, the acquisition accuracy of each acquisition camera is obtained; The correction weights are determined based on the acquisition accuracy. The initial environmental monitoring situation in the combination of cases is corrected based on the corrected weights to obtain the environmental monitoring situation.

5. The method according to claim 1, characterized in that, The environmental monitoring includes track monitoring and turf monitoring. The process of determining abnormal situations based on the environmental monitoring data and the environmental monitoring situation includes: If there is a monitoring location with a monitoring value greater than 0 in the runway monitoring data, a runway anomaly is generated; The monitored values ​​in the lawn monitoring data are compared with preset thresholds to determine the current abnormal lawn condition; Obtain historical information on plant and animal growth; The historical plant and animal growth information was analyzed to obtain the correspondence between the environment and the growth rate of plants and animals; Based on the environmental monitoring data, the corresponding relationship, and the lawn monitoring status, a prediction of lawn anomalies is obtained. The abnormal situation is determined based on the runway abnormality, the current turf abnormality, and the predicted turf abnormality.

6. The method according to claim 1, characterized in that, The process of determining anomaly control strategies based on the abnormal situation and the insect detection data includes: The type of anomaly is determined based on the described anomaly. To obtain information on the growth relationships between plants and animals and biological control measures; A first abnormal association is determined based on the types of anomalies and the correlations between plant and animal growth, and the first abnormal association includes positive associations and negative associations. The species and number of flying insects are determined based on the flying insect detection data. If the number of flying insects exceeds a preset number, a second abnormal association is determined based on the plant and animal growth association and the type of flying insect. An anomaly control strategy is determined based on the first anomaly association, the second anomaly association, and the biological control measures.

7. The method according to claim 1, characterized in that, The method further includes: Obtain historical anomaly information; The historical anomaly information is divided based on a preset period to obtain multiple combinations of historical anomalies; The historical anomaly combinations are analyzed to determine the anomaly frequency for each preset period; The initial data analysis frequency is determined based on the aforementioned anomaly frequency; Obtain aircraft takeoff and landing information; The initial data analysis frequency is adjusted based on the aircraft takeoff and landing information to obtain the target data analysis frequency.

8. An ecological monitoring device based on image recognition, characterized in that, include: The first data acquisition module is used to acquire image data and environmental monitoring data; The monitoring status determination module is used to identify the image data to obtain the environmental monitoring status; An anomaly determination module is used to determine anomalies based on the environmental monitoring data and the environmental monitoring situation. The second data acquisition module is used to acquire flying insect detection data; The control strategy determination module is used to determine the anomaly control strategy based on the abnormal situation and the flying insect detection data.

9. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images