Pine forest yellowing reason determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a pine forest yellowing reason determination method and device, a storage medium and electronic equipment, and the method is applied to the field of artificial intelligence, and comprises the steps: collecting image data of a pine forest region, and detecting whether there is a pine forest yellowing target region in the pine forest region or not according to the image data; under the condition that the target area is detected, whether the pine forest yellowing process of the target area belongs to a first type change or a second type change is judged according to the image data of the target area within a preset time period; obtaining the growth condition of the pine forest area, and calculating the confidence of the first type of reasons or the second type of reasons according to the rule base and the growth condition; and according to the confidence of the first type of reasons or the confidence of the second type of reasons, determining the reasons for yellowing of the pine forest in the target area. Through the method and the device, the problem that the pine forest yellowing reason obtained through analysis is inaccurate due to the fact that the pine forest yellowing reason can only be analyzed according to a single reason when the image data is analyzed through an artificial intelligence algorithm in related technologies is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a pine forest discoloration reason determination method and device, a storage medium and an electronic equipment. BACKGROUND

[0002] As an important ecological and economic tree species, the health status of pine trees directly affects the stability of forest ecosystems and economic benefits. Pine forest discoloration is an intuitive manifestation of the deterioration of pine tree health, usually caused by factors such as pests and diseases, environmental pollution, and climate change. Timely and accurate monitoring of pine forest discoloration and identifying the causes is of great significance for protecting forest resources and maintaining ecological safety.

[0003] For a long time, pine forest discoloration monitoring has mainly relied on manual ground investigation and remote sensing technology. Although manual ground investigation has high accuracy, it is time-consuming and labor-intensive and requires manual analysis to determine the cause of pine forest discoloration, making it difficult to achieve large-scale and high-frequency monitoring. Remote sensing technology, including satellite remote sensing and aerial remote sensing, can quickly obtain large-scale forest information, but is limited by resolution and weather conditions, making it difficult to accurately identify early and small-scale pine forest discoloration.

[0004] In recent years, with the development of artificial intelligence, deep learning-based automatic identification technology for pine forest discoloration has gradually become a research hotspot. Existing models mostly can only be trained for pine forest discoloration in a single scenario, making it difficult to generalize to other scenarios for cause analysis, and the analysis of the causes of pine forest discoloration is limited to single-cause analysis, ignoring the interrelationships between facts, so even if the model is used to analyze pine forest discoloration, it is also prone to being limited by information silos.

[0005] To address the issue of related technologies that can only analyze the causes of pine forest discoloration based on a single cause when analyzing image data using artificial intelligence algorithms, resulting in inaccurate analysis of the causes of pine forest discoloration, no effective solutions have been proposed. SUMMARY

[0006] The main purpose of the present application is to provide a pine forest discoloration reason determination method and device, a storage medium and an electronic equipment to solve the problem of related technologies that can only analyze the causes of pine forest discoloration based on a single cause when analyzing image data using artificial intelligence algorithms, resulting in inaccurate analysis of the causes of pine forest discoloration.

[0007] In order to achieve the above object, according to one aspect of the present application, a method for determining the cause of yellowing of pine forest is provided, which comprises: collecting image data of a pine forest area, and detecting whether a target area of yellowing of pine forest exists in the pine forest area according to the image data; in the case that the target area is detected, judging whether the yellowing process of pine forest in the target area belongs to a first type of change or a second type of change according to image data of the target area in a preset time period, wherein the change speed of the first type of change is faster than that of the second type of change, the first type of change corresponds to a first type of cause of yellowing of pine forest, and the second type of change corresponds to a second type of cause of yellowing of pine forest; obtaining the growth condition of the pine forest area, calculating the confidence of the first type of cause or the confidence of the second type of cause according to a rule base and the growth condition, wherein the rule base stores analysis rules related to yellowing of pine forest; and determining the cause of yellowing of pine forest in the target area according to the confidence of the first type of cause or the confidence of the second type of cause.

[0008] Further, before calculating the confidence of the first type of cause or the confidence of the second type of cause according to the rule base and the growth condition, the method further comprises: extracting a first type of knowledge directly related to yellowing of pine forest in the target area based on expert field knowledge and historical data, and generating rules through a semantic analysis model; or extracting a plurality of second type of knowledge related to yellowing of pine forest in the target area based on expert field knowledge and historical data, and generating rules through semantic network analysis, wherein the plurality of second type of knowledge comprises: a preceding event, an actual event, and an association relationship between the preceding event and the actual event; determining the confidence corresponding to the rules, and constructing the rule base according to the rules and the confidence corresponding to the rules.

[0009] Further, in the case that the yellowing process of pine forest in the target area belongs to the first type of change, calculating the confidence of the first type of cause or the confidence of the second type of cause according to the rule base and the growth condition comprises: determining a first type of information according to the growth condition, wherein the first type of information comprises at least one of: a first sub-type of information and a second sub-type of information, the first sub-type of information is information related to human activities, and the second sub-type of information is information related to natural environment; determining a first type of rule related to the first type of change in the rule base through a semantic analysis model, wherein the first type of rule comprises at least one of: a first sub-type of rule and a second sub-type of rule, the first sub-type of rule is a rule related to human activities, and the second sub-type of rule is a rule related to natural environment; and matching the first type of rule with the first type of information to determine the confidence that the cause of yellowing of pine forest in the target area belongs to the first type of cause.

[0010] Further, the pine forest yellowing process of the target region belongs to the second type of change, and the confidence of the first type of reason or the confidence of the second type of reason is calculated according to the rule base and the growth condition, including: determining the second type of information in the growth condition, wherein the second type of information includes at least one of the third sub-type information and the fourth sub-type information, the third sub-type information is information related to the pine forest growth environment, and the fourth sub-type information is information related to the disease and insect pests; determining the second type of rule related to the pine forest growth environment in the rule base through a semantic analysis model, wherein the second type of rule includes at least one of the third sub-type rule and the fourth sub-type rule, the third sub-type rule is a rule related to the pine forest growth environment, and the fourth sub-type rule is a rule related to the disease and insect pests; and matching the second type of rule with the second type of information to determine the confidence of the pine forest yellowing reason in the target region belonging to the second type of reason.

[0011] Further, the number of the first type of rules is N, N is an integer greater than 1, the first type of rules are matched with the first type of information to determine the confidence of the pine forest yellowing reason in the target region belonging to the first type of reason, including: judging whether there is a logical relationship between each rule in the plurality of first type of rules, wherein the logical relationship includes at least one of and, or, and not; in the case that there is a logical relationship between each rule, the confidence of the pine forest yellowing reason in the target region belonging to the first type of reason is calculated according to a preset mathematical algorithm and the logical relationship; and in the case that there is no association relationship between each rule, the confidence of the pine forest yellowing reason in the target region belonging to the first type of reason is calculated according to the preset mathematical algorithm and a rule merging algorithm.

[0012] Further, whether the target region of pine forest yellowing exists in the pine forest region is detected according to the image data, including: photographing a preset position in the pine forest region by a camera device to obtain the image data; inputting the image data into a target detection model, and detecting whether the target region exists in the pine forest region by the target detection model for the first time to obtain a detection result; in the case that the detection result indicates that the target region exists, reacquiring image data of the target region by adjusting device parameters of the camera device to obtain secondary acquired image data; and detecting the secondary acquired image data by the target detection model to detect whether the target region exists in the pine forest region for the second time.

[0013] Further, the method further includes: obtaining device identification information of the camera device and coordinate information of the target region; obtaining image data of the target region in the preset time period according to the device identification information and the coordinate information; segmenting the target region in the image data of the target region in the preset time period by using an image segmentation algorithm to obtain a segmentation result sequence in the preset time period; and determining whether the pine forest yellowing process of the target region belongs to the first type of change or the second type of change according to segmentation results at different times in the segmentation result sequence.

[0014] To achieve the above object, according to another aspect of the present application, a device for determining a pine forest yellowing cause is provided, which includes: a detection unit configured to collect image data of a pine forest region and detect whether a target region of pine forest yellowing exists in the pine forest region according to the image data; a judgment unit configured to, when the target region is detected, determine whether a pine forest yellowing process of the target region belongs to a first type of change or a second type of change according to image data of the target region in a preset time period, wherein the first type of change has a faster change speed than the second type of change, the first type of change corresponds to a first type of pine forest yellowing cause, and the second type of change corresponds to a second type of pine forest yellowing cause; a calculation unit configured to obtain a growth condition of the pine forest region, calculate a confidence degree of the first type of cause or a confidence degree of the second type of cause according to a rule base and the growth condition, wherein the rule base stores analysis rules related to pine forest yellowing; and a determination unit configured to determine the pine forest yellowing cause in the target region according to the confidence degree of the first type of cause or the confidence degree of the second type of cause.

[0015] Further, the device further includes: a first generation unit configured to, before the calculation of the confidence degree of the first type of cause or the confidence degree of the second type of cause according to the rule base and the growth condition, extract a first type of knowledge directly related to pine forest yellowing in the target region by using a semantic analysis model based on expert field knowledge and historical data to generate a rule; or a second generation unit configured to extract a plurality of second types of knowledge related to pine forest yellowing in the target region by using a semantic network analysis based on expert field knowledge and historical data to generate a rule, wherein the plurality of second types of knowledge include a preceding event and an actual event, and the preceding event and the actual event have an association relationship; and a construction unit configured to determine a confidence degree corresponding to the rule, and construct the rule base according to the rule and the confidence degree corresponding to the rule.

[0016] Further, the pine forest yellowing process of the target area belongs to the first type of change, and the computing unit comprises: a first determining subunit configured to determine first type information according to the growth condition, wherein the first type information comprises at least one of: first sub-type information and second sub-type information, the first sub-type information is information related to human activities, and the second sub-type information is information related to the natural environment; a second determining subunit configured to determine first type rules related to the first type of change in the rule base through a semantic analysis model, wherein the first type rules comprise at least one of: first sub-type rules and second sub-type rules, the first sub-type rules are rules related to human activities, and the second sub-type rules are rules related to the natural environment; and a matching subunit configured to match the first type rules with the first type information to determine a confidence level of the pine forest yellowing reason in the target area belonging to the first type of reason.

[0017] Further, the pine forest yellowing process of the target area belongs to the second type of change, and the computing unit comprises: a third determining subunit configured to determine second type information according to the growth condition, wherein the second type information comprises at least one of: third sub-type information and fourth sub-type information, the third sub-type information is information related to the pine forest growth environment, and the fourth sub-type information is information related to diseases and pests; a fourth determining subunit configured to determine second type rules related to the pine forest growth environment in the rule base through a semantic analysis model, wherein the second type rules comprise at least one of: third sub-type rules and fourth sub-type rules, the third sub-type rules are rules related to the pine forest growth environment, and the fourth sub-type rules are rules related to diseases and pests; and a fifth matching subunit configured to match the second type rules with the second type information to determine a confidence level of the pine forest yellowing reason in the target area belonging to the second type of reason.

[0018] Further, the number of the first type rules is N, N is an integer greater than 1, and the matching subunit comprises: a judgment module configured to judge whether there is a logical relationship between each rule in the plurality of first type rules, wherein the logical relationship comprises at least one of: AND, OR, and NOT; a first calculation module configured to, in the case that there is a logical relationship between each rule, calculate the confidence level of the pine forest yellowing reason in the target area belonging to the first type of reason according to a preset mathematical algorithm and the logical relationship; and a second calculation module configured to, in the case that there is no logical relationship between each rule, calculate the confidence level of the pine forest yellowing reason in the target area belonging to the first type of reason according to the preset mathematical algorithm and a rule merging algorithm.

[0019] Further, the detection unit comprises: a first acquisition subunit configured to capture a preset position in the pine forest area by using a camera device to obtain the image data; a first detection subunit configured to input the image data into a target detection model, and detect whether the target area exists in the pine forest area by using the target detection model for a first time to obtain a detection result; a second acquisition subunit configured to, when the detection result indicates that the target area exists, re-acquire image data of the target area by adjusting device parameters of the camera device to obtain second-acquired image data; and a second detection subunit configured to detect the second-acquired image data by using the target detection model to detect whether the target area exists in the pine forest area for a second time.

[0020] Further, the judgment unit comprises: a first acquisition subunit configured to acquire device identification information of a camera device and coordinate information of the target area; a second acquisition subunit configured to acquire image data of the target area in the preset time period according to the device identification information and the coordinate information; a segmentation subunit configured to segment the target area in the image data of the target area in the preset time period by using an image segmentation algorithm to obtain a segmentation result sequence in the preset time period; and a judgment subunit configured to judge whether the pine forest yellowing process of the target area belongs to the first type of change or the second type of change according to segmentation results at different moments in the segmentation result sequence.

[0021] To achieve the above object, according to an aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the pine forest yellowing reason determination method of any one of the above.

[0022] To achieve the above object, according to an aspect of the present application, a computer readable storage medium is provided, comprising stored computer instructions, wherein when the computer instructions are executed by a processor, the pine forest yellowing reason determination method of any one of the above is implemented.

[0023] To achieve the above object, according to an aspect of the present application, an electronic device is provided, comprising one or more processors and a memory, the memory being configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the pine forest yellowing reason determination method of any one of the above.

[0024] According to the application, the following steps are adopted: image data of a pine forest area is collected, and it is detected according to the image data whether there is a target area of pine forest yellowing in the pine forest area; in the case that the target area is detected, it is judged according to image data of the target area in a preset time period whether a pine forest yellowing process of the target area belongs to a first type of change or a second type of change, wherein the change speed of the first type of change is faster than the change speed of the second type of change, the first type of change corresponds to a first type of reason of pine forest yellowing, and the second type of change corresponds to a second type of reason of pine forest yellowing; growth conditions of the pine forest area are obtained, and the confidence of the first type of reason or the confidence of the second type of reason is calculated according to a rule base and the growth conditions, wherein the rule base stores analysis rules related to pine forest yellowing; and the reason of pine forest yellowing in the target area is determined according to the confidence of the first type of reason or the confidence of the second type of reason, thereby solving the problem in the related art that when image data is analyzed by an artificial intelligence algorithm, only a single reason can be used to analyze the reason of pine forest yellowing, resulting in inaccurate analysis of the reason of pine forest yellowing.

[0025] By deploying a pan-tilt camera at a high point to periodically collect image data of a pine forest area, and using advanced image processing technology to detect whether there is a target area of pine forest yellowing, subtle changes in the health of the pine forest can be captured in a timely manner, achieving the technical effects of early warning and timely intervention in the pine forest yellowing process. At the same time, by analyzing the image data of the target area in a preset time period, it is judged whether the pine forest yellowing process belongs to a first type of change with fast change speed or a second type of change with slow change speed, so that the system can not only distinguish between sudden events and long-term problems, but also achieve accurate classification, further achieving the technical effects of improving diagnosis efficiency and accuracy, and shortening response time. In addition, by obtaining growth environment data of the pine forest area, the confidence of the first type or the second type of reason is calculated according to rich analysis rules in the rule base and the growth conditions, which can comprehensively consider multiple potential factors, realize complex reason analysis, greatly improve the accuracy of pine forest yellowing reason analysis, and further achieve the technical effects of providing comprehensive and scientific solutions, and providing strong support for forestry resource protection and ecological environment construction. BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The embodiments of the present application illustrated in the drawings and their descriptions are used to explain the present application and are not intended to limit the present application. In the drawings:

[0027] Figure 1 is a flowchart of a method for determining the reason of pine forest yellowing according to an embodiment of the present application;

[0028] Figure 2is a schematic diagram of optional semantic analysis results of loose line diseases and pests provided according to Embodiment One of the present application;

[0029] Figure 3 is a schematic diagram of optional reasoning analysis results of the monochamus alternatus provided according to Embodiment One of the present application;

[0030] Figure 4 is a schematic diagram of the structure of an optional determination system of the pine forest yellowing reason provided according to Embodiment One of the present application;

[0031] Figure 5 is a schematic diagram of the analysis flow of the pine forest yellowing reason provided according to Embodiment One of the present application;

[0032] Figure 6 is a schematic diagram of optional rule hierarchy and priority provided according to Embodiment One of the present application;

[0033] Figure 7 is a schematic diagram of a determination device of the pine forest yellowing reason provided according to Embodiment Two of the present application;

[0034] Figure 8 is a schematic diagram of a determination electronic device of the pine forest yellowing reason provided according to Embodiment Five of the present application. DETAILED DESCRIPTION

[0035] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] It should be noted that the user information (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and data (including but not limited to data for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards of relevant countries and regions, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user selection authorization or refusal. For example, an interface is provided between the system and the related users or institutions, and before obtaining the relevant information, the interface needs to send an acquisition request to the aforementioned user or institution, and after receiving the consent information feedback from the aforementioned user or institution, the relevant information is acquired.

[0037] It should be noted that the present application provides a corresponding operation portal for the user to select to agree or refuse the automatic decision result; if the user chooses to refuse, the expert decision process is entered.

[0038] In order to make the person skilled in the art better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should be within the scope of protection of the present application.

[0039] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0040] Embodiment one

[0041] The present application will be described below in combination with the preferred implementation steps, Figure 1 is a flowchart of the method for determining the reasons for pine forest yellowing provided according to Embodiment one of the present application, as Figure 1 shown, the method comprises the following steps:

[0042] Step S101, collect image data of the pine forest area, and detect whether there is a target area of pine forest yellowing in the pine forest area according to the image data.

[0043] In this embodiment one, a pan-tilt camera is deployed at a relatively high geographical location to periodically collect image data of the pine forest area. Subsequently, the collected images are analyzed using an image processing model to identify the pine forest areas in the images and detect whether there is a pine forest yellowing phenomenon in these areas. This process makes full use of the field of view advantage of the high camera, combined with intelligent image recognition technology, realizes the automatic monitoring of the pine forest yellowing phenomenon, and provides a data basis for subsequent analysis and diagnosis.

[0044] Step S102, in the case of detecting the target area, judging whether the pine forest yellowing process of the target area belongs to the first type of change or the second type of change according to the image data of the target area within a preset time period, wherein the change speed of the first type of change is faster than that of the second type of change, the first type of change corresponds to the first type of reason for pine forest yellowing, and the second type of change corresponds to the second type of reason for pine forest yellowing.

[0045] In the first embodiment, when a suspected yellowing target region is detected in the pine forest area, the yellowing process of the target region is further analyzed to determine whether it belongs to the first type of change or the second type of change. This determination is based on image data collected within a predetermined time period (e.g., 30 days) by continuously monitoring the target region, thereby capturing the speed and trend of color change.

[0046] The first type of change mentioned above refers to the color change speed during the pine forest yellowing process, i.e., the pine forest yellowing process belongs to mutation, for example, the color change can be significantly observed within a week. This rapid change is often caused by sudden events such as fire, lightning or human damage, etc., which can cause severe damage to the pine forest in a short period of time, showing rapid color change.

[0047] The second type of change mentioned above refers to the color change speed during the pine forest yellowing process, i.e., the pine forest yellowing process belongs to gradual change, for example, the pine forest has started to gradually turn yellow three weeks ago. This type of change is usually caused by long-term problems or diseases in the pine forest growing environment, such as pine wood nematode disease, malnutrition or persistent environmental stress.

[0048] By determining whether the yellowing process of the target region belongs to the first type of change or the second type of change, the type of cause leading to the pine forest yellowing can be preliminarily locked, i.e., the first type of cause or the second type of cause. The former is usually related to sudden human activities or environmental events, and the latter may be related to chronic diseases or growth conditions. This classification helps to narrow the scope of problem analysis, improve the pertinence and efficiency of subsequent cause analysis, thereby quickly responding to and effectively handling the pine forest yellowing situation, avoiding unnecessary losses. In addition, based on the classification results, further refined analysis can be performed, combined with more evidence and rules, to accurately point out the specific cause of the yellowing and its confidence, achieving the effect of improving the accuracy of analyzing the cause of the pine forest yellowing.

[0049] In step S103, the growth condition of the pine forest area is obtained, and the confidence of the first type of cause or the confidence of the second type of cause is calculated according to the rule base and the growth condition, wherein the rule base stores analysis rules related to the pine forest yellowing.

[0050] In the first embodiment, the environmental data and growth conditions of the pine forest region, such as temperature, humidity, rainfall, soil nutrition, etc., can be obtained by calling the database or application program interface (API) of the deployment region (which can be referred to as API for short), such as meteorological station data, information collected by insect trapping devices, information collected by various types of sensors, etc. The collected growth condition data of the pine forest region is used as evidence for reasoning the reasons for the pine forest turning yellow, and is matched and calculated with the analysis rules in the rule base. The rule base is constructed based on expert knowledge and historical data analysis, and contains rules and their confidence levels for various reasons that may cause the pine forest to turn yellow.

[0051] Specifically, for the first type of reason (abrupt change), it can be inferred from the growth condition data of the pine forest region whether there are events such as fire, lightning or human logging, and the confidence level is calculated by combining the probability and impact degree; for the second type of reason (gradual change), it is evaluated whether the growth environment of the pine forest is suitable and whether there are signs of pest activities, etc., and the corresponding confidence level is calculated through the rules in the rule base. This process uses the simplified rule-based reasoning method of D-S evidence theory to logically operate and synthesize different evidence and rules in the form of confidence level, and finally obtains the most likely reason for the pine forest turning yellow and its confidence level, achieving the effect of improving the accuracy of analyzing the reasons for the pine forest turning yellow, and further achieving the effect of providing scientific basis for forestry prevention and control and ecological management.

[0052] Step S104, determining the reason for the pine forest turning yellow in the target region according to the confidence level of the first type of reason or the confidence level of the second type of reason.

[0053] In the first embodiment, after determining that the pine forest turning yellow in the target region belongs to the first type of change or the second type of change, the confidence level corresponding to the first type of reason or the second type of reason can be calculated according to the analysis rules stored in the rule base and the obtained growth condition data of the pine forest. This process quantifies and compares the confidence levels of different rules, uses the principles of probability and rule synthesis formula to evaluate various possible reasons. Finally, the reason with the highest confidence level is selected as the main cause of the pine forest turning yellow in the target region.

[0054] In summary, the method for determining the cause of pine forest yellowing provided by the embodiment one of the present application collects image data of the pine forest area, and detects whether there is a target area of pine forest yellowing in the pine forest area according to the image data; in the case of detecting the target area, it is judged whether the pine forest yellowing process of the target area belongs to the first type of change or the second type of change according to the image data of the target area in the preset time period, wherein the change speed of the first type of change is faster than that of the second type of change, the first type of change corresponds to the first type of cause of pine forest yellowing, and the second type of change corresponds to the second type of cause of pine forest yellowing; the growth condition of the pine forest area is obtained, and the confidence of the first type of cause or the confidence of the second type of cause is calculated according to the rule base and the growth condition, wherein the rule base stores analysis rules related to pine forest yellowing; the cause of pine forest yellowing in the target area is determined according to the confidence of the first type of cause or the confidence of the second type of cause, which solves the problem in the related art that when the image data is analyzed by an artificial intelligence algorithm, only a single cause can be used to analyze the cause of pine forest yellowing, resulting in inaccurate analysis of the cause of pine forest yellowing.

[0055] By deploying the pan-tilt camera at a high point to periodically collect image data of the pine forest area, and using advanced image processing technology to detect whether there is a target area of pine forest yellowing, the subtle changes in the health of the pine forest can be captured in time, achieving the technical effects of early warning and timely intervention in the pine forest yellowing process. At the same time, by analyzing the image data of the target area in the preset time period, it is judged whether the pine forest yellowing process belongs to the first type of change with fast change speed or the second type of change with slow change speed, so that the system can not only distinguish between sudden events and long-term problems, but also achieve accurate classification, further achieving the technical effects of improving diagnosis efficiency and accuracy, and shortening response time. In addition, by obtaining the growth environment data of the pine forest area, the confidence of the first type or the second type of cause is calculated according to the rich analysis rules in the rule base and the growth condition, which can consider multiple potential factors, realize complex cause analysis, greatly improve the accuracy of pine forest yellowing cause analysis, and further achieve the technical effects of providing comprehensive and scientific solutions, providing strong support for forestry resource protection and ecological environment construction.

[0056] Optionally, in the method for determining the cause of pine forest yellowing provided in Embodiment One of the present application, before calculating the confidence of the first type of cause or the confidence of the second type of cause according to the rule base and the growth conditions, the above method further comprises: based on expert field knowledge and historical data, extracting the first type of knowledge directly related to the pine forest yellowing in the target area through a semantic analysis model to generate rules; or, based on expert field knowledge and historical data, extracting a plurality of second type of knowledge related to the pine forest yellowing in the target area through semantic network analysis to generate rules, wherein the plurality of second type of knowledge comprises: a preceding event, an actual event, and an association between the preceding event and the actual event; determining the confidence corresponding to the rules, and constructing a rule base according to the rules and the confidence corresponding to the rules.

[0057] In Embodiment One, when constructing the rule base, rules can be refined by single-factor mode, or rules can be generated by multi-factor combination mode.

[0058] In an optional embodiment, the biological characteristics and transmission pathways of the direct pathogen of the discolored sick wood (i.e., the yellowing pine forest in the target area) can be directly analyzed, and the analysis process can be as shown in Figure 2 . Figure 2 is a schematic diagram of the semantic analysis result of the pine line disease insect according to the optional embodiment provided in Embodiment One of the present application. Based on the above semantic analysis result and combined with expert experience, the confidence is directly given as follows: the rules affected by temperature can include but are not limited to: if the temperature is lower than 10℃ or greater than 35℃, the confidence of the active signal of the pine line disease insect appearing is 5%; if the temperature is between [20℃, 30℃], the confidence of the active signal of the pine line disease insect appearing is 90%; if the temperature is between [30℃, 35℃], the confidence of the active signal of the pine line disease insect appearing is 60%. In addition, the temperature indirect cause of the transmission pathway includes but is not limited to: if the temperature is lower than 15℃, the confidence of the pine line insect being active due to the rare reproduction of the pine carpenter bee is 5%; if the temperature is between [20℃-30℃], the confidence of the pine line insect being active due to the rare reproduction of the pine carpenter bee is 85%. The rainfall indirect cause of the transmission pathway includes but is not limited to: if the annual rainfall is lower than 800mm or higher than 1600mm, the confidence of the pine line insect being active due to the rare reproduction of the pine carpenter bee is 5%; if the annual rainfall is between [800mm, 1000mm], the confidence of the pine line insect being active due to the rare reproduction of the pine carpenter bee is 75%.

[0059] Since the pine carpenter bee is the host and transmitter of the pine line disease insect, the occurrence of the discolored sick wood is highly consistent with the activity track of the pine carpenter bee. Therefore, if the target area has a pine carpenter bee trapping device, the number of pine carpenter bees can be directly collected as direct evidence. If the target area does not have a pine carpenter bee trapping device, other indirect evidence or causal relationship of the pine carpenter bee is analyzed to determine the confidence of the pine forest yellowing.Figure 3 is a schematic diagram of reasoning analysis result of the black-tussocked beetle according to the embodiment one of the present application. The process of reasoning analysis according to the direct evidence and indirect evidence of the black-tussocked beetle can be as shown in the following table. Figure 3

[0060] In an alternative embodiment, the pre-event of the black-tussocked beetle causing the occurrence of the pine wood nematode disease can be represented as: when the region has available pine wood nematode insect data trapping devices. The growth of the pine forest in the target region, i.e. the actual event described above, for example, the pine wood nematode disease itself does not spread, but relies on the host pine wood nematode insect for transmission; the temperature (20-30℃) of the needle yellowing starts 1-3 months after infection; the temperature (30-40℃) of the needle yellowing starts 2-4 months after infection; the susceptible tree species such as Pinus massoniana and Pinus thunbergii are susceptible to the disease; the resistant tree species such as Pinus armandii and Cedrus deodara are more resistant, and the disease course can be prolonged. The rules generated according to the pre-event and the actual event can be represented as: if the region captures pine wood nematode insects and the number increases in the previous month, then the gradual change confidence is 95% for the pine wood nematode disease; it is necessary to verify that the yellowing process of the pine forest in the target region in the previous month belongs to the second type of change described above, i.e. gradual change; if the region captures pine wood nematode insects in the previous month and the temperature is (20-30℃), then the confidence is 88%; if the region captures pine wood nematode insects in the previous month and the temperature is (30-40℃), then the confidence is 85%; if the region captures pine wood nematode insects in the previous month and the temperature is (10-20℃), then the confidence is 70%; if the region captures pine wood nematode insects in the previous month and the temperature is (less than 10℃), then the confidence is 55%.

[0061] By integrating expert domain knowledge and historical data, using a semantic analysis model to extract the first type of knowledge directly related to the yellowing of the pine forest in the target region and generate rules, the key factors of the health change of the pine forest can be accurately captured, the experience can be converted into computable rules, and the efficiency and accuracy of the pine forest yellowing detection can be significantly improved, further achieving the technical effects of intelligent diagnosis and prevention.

[0062] At the same time, through semantic network analysis, multiple second type of knowledge related to the yellowing of the pine forest can be deeply mined, including the association between the pre-event and the actual event, a more complex rule system is generated, so that the system can not only understand the meaning of individual events, but also can understand the causal relationship between events, realizing deep analysis and reasoning, further achieving the technical effects of strengthening the problem tracing ability and improving the decision-making scientificity.

[0063] ​Optionally, in the method for determining the cause of pine forest yellowing provided in Embodiment One of the present application, the pine forest yellowing process in the target area belongs to the first type of change, and the confidence level of the first type of cause or the confidence level of the second type of cause is calculated according to the rule base and the growth condition, including: determining the first type of information according to the growth condition, wherein the first type of information includes at least one of the following: the first sub-type of information, the second sub-type of information, the first sub-type of information is information related to human activities, and the second sub-type of information is information related to the natural environment; determining the first type of rule related to the first type of change in the rule base through a semantic analysis model, wherein the first type of rule includes at least one of the following: the first sub-type of rule, the second sub-type of rule, the first sub-type of rule is a rule related to human activities, and the second sub-type of rule is a rule related to the natural environment; and matching the first type of rule with the first type of information to determine the confidence level of the pine forest yellowing cause in the target area belonging to the first type of cause.

[0064] In Embodiment One, when it is detected that the pine forest area yellowing is caused by sudden changes, it is concluded that the pine trees are infected and diseased, and the yellowing of pine leaves is likely not caused by disease and pests or nutrient deficiency, and various rules in the rule base also need to be found to determine the cause of pine forest yellowing.

[0065] In an optional example, the first type of information includes the occurrence of forest fires in the target area within a week. The rule related to the first type of information in the rule base includes: if there is smoke (flame) in the area within the last week and the area is located in the camera coverage area, the confidence level of the fire cause is 80%; if there is smoke (flame) in the area within the last week and other weather factors are normal, the confidence level of the fire cause is 60%. Matching the first type of information with the rule determines that the confidence level of the pine forest yellowing cause in the target area belonging to the first type of cause is 80%.

[0066] In an optional example, the first type of information includes the occurrence of human logging activities in the target area within a week. The rule related to the first type of information in the rule base includes: if there is logging in the yellowing area within the last week and the area is located in the camera coverage area, the confidence level of the logging cause is 80%; if there is logging in the area within the last week and other weather factors are normal, the confidence level of the logging cause is 60%. Matching the first type of information with the rule determines that the confidence level of the pine forest yellowing cause in the target area belonging to the first type of cause is 80%.

[0067] By identifying the first type of information related to human activities or the natural environment according to the growth condition of the pine forest, accurately matching the first type of rule directly related to the first type of change in the rule base, the potential yellowing cause can be screened and focused in advance, ensuring the relevance between data and rules, achieving the technical effect of quickly locating the problem, and significantly improving the monitoring response speed.

[0068] Optionally, in the method for determining the cause of pine forest yellowing provided in Embodiment One of the present application, the pine forest yellowing process of the target area belongs to the second type of change, and the confidence level of the first type of cause or the confidence level of the second type of cause is calculated according to the rule base and the growth condition, including: determining the second type of information in the growth condition, wherein the second type of information includes at least one of the following: third sub-type information, fourth sub-type information, the third sub-type information is information related to the growth environment of the pine forest, and the fourth sub-type information is information related to the disease and pest; determining the second type of rule related to the growth environment of the pine forest in the rule base through a semantic analysis model, wherein the second type of rule includes at least one of the following: third sub-type rule, fourth sub-type rule, the third sub-type rule is a rule related to the growth environment of the pine forest, and the fourth sub-type rule is a rule related to the disease and pest; and matching the second type of rule with the second type of information to determine the confidence level of the cause of the pine forest yellowing in the target area belonging to the second type of cause.

[0069] In an optional embodiment, the second type of information includes that the target area is located in Changting County, Fujian Province. The rule related to the second type of information in the rule base includes: lack of organic matter such as phosphorus and potassium in the southern red soil region, if the target area is located in Changting County, Sanming City, Longyan City in Fujian Province, Ji'an City, Ganzhou City in Jiangxi Province, or Huaihua City, Chenzhou City in Hunan Province, etc., the confidence level of the soil nutrient deficiency is 75%; lack of trace elements such as magnesium in the southwest karst region, if the target area is located in Bijie City, Qianan in Guizhou Province, or Hechi City, Baise City in Guangxi Province, etc., the confidence level of the soil nutrient deficiency is 75%. The second type of information is matched with the rule to determine that the confidence level of the cause of the pine forest yellowing in the target area belonging to the second type of cause is 75%.

[0070] In an optional embodiment, the second type of information includes that the target area has appeared discoloration and epidemic wood phenomenon in the past 3 years, and the target area is located in Changting County, Fujian Province. The rule related to the second type of information in the rule base includes: the confidence coefficient of the region where discoloration and epidemic wood phenomenon has occurred in history is 1.2, and the region where discoloration and epidemic wood phenomenon has occurred in history includes Nanjing City in Jiangsu Province (1982 first discovery place, Zijingshan pine forest), Zhenjiang City (Jianong City), Changzhou City (Liyang City), Wuxi City (Yixing City), Suzhou City (Wuzhong District), Hangzhou City in Zhejiang Province (Xihu District, Lin'an District), Ningbo City (Fenghua District, Yuyao City), Wenzhou City (Yongjia County), Huzhou City (Anji County), Shaoxing City (Zhoushi City), Taizhou City (Tiantai County), etc. The confidence level of the soil nutrient deficiency is 75%. The second type of information is matched with the rule to determine that the confidence level of the cause of the pine forest yellowing in the target area belonging to the second type of cause is 75%*1.2=90%.

[0071] Optionally, in the method for determining the pine forest yellowing reason provided in Embodiment One of the present application, the number of the first type of rules is N, N is an integer greater than 1, the first type of rules are matched with the first type of information to determine the confidence degree of the pine forest yellowing reason in the target region belonging to the first type of reason, which includes: judging whether there is a logical relationship between each rule in the plurality of first type of rules, wherein the logical relationship includes at least one of the following: and, or, and not; in the case that there is a logical relationship between each rule, the confidence degree of the pine forest yellowing reason in the target region belonging to the first type of reason is calculated according to a preset mathematical algorithm and the logical relationship; in the case that there is no correlation between each piece of knowledge, the confidence degree of the pine forest yellowing reason in the target region belonging to the first type of reason is calculated according to a preset mathematical algorithm and a rule combination algorithm.

[0072] In Embodiment One, since there are thousands of rules in the rule base, and the rules related to the first type of information (or the second type of information) in the pine forest growth condition can be more than one, the confidence degree of the pine forest yellowing reason in the target region belonging to the first type of reason can be obtained by mathematical formula calculation through probability and rule combination formula. The D-S theory (Dempster-Shafer Theory, which can be simply referred to as D-S theory, i.e. the above-mentioned preset mathematical algorithm) is a mathematical framework for handling uncertainty and incomplete information. It describes the range of uncertainty by introducing "belief function" and "likelihood function", and is particularly suitable for handling multi-source information fusion, conflict evidence reconciliation and other problems. Let E be the evidence, H be the belief measure of the hypothesis, MB(H, E) represent the belief measure of the hypothesis H obtained from the evidence E, and the calculation formula of the belief measure (i.e. the above-mentioned confidence degree) can be as shown in Formula One.

[0073]

[0074] Wherein, P(H|E) represents the conditional probability that H is true after the appearance of evidence E; max(P(H|E), P(H))-P(H) represents how much the outline of H being true is increased by the appearance of evidence E; 1-P(H) represents the probability of H being false. MD(H, E) represents the disbelief measure of the hypothesis H obtained from the evidence E, and the calculation formula of the disbelief measure can be as shown in Formula Two.

[0075]

[0076] Wherein, P(H|E) represents the conditional probability that H is true after the appearance of evidence E; min(P(H|E), P(H))-P(H) represents how much the outline of H being true is reduced by the appearance of evidence E; -P(H) represents the negative value of the probability of H being true. Confidence degree: CF(H, E) = MB(H, E)-MD(H, E).

[0077] In an optional embodiment, the confidence level of the rule needs to be defined first. For example, CF(A) represents the confidence level that knowledge A is true, and its value range is [-1, 1]. When CF(A) = 1, it means that A is definitely true. When CF(A) = -1, it means that the confidence level that A is true is -1, that is, A is definitely false. CF(A) > 0 means that A is true with a certain confidence level. CF(A) < 0 means that A is false with a certain confidence level, and its confidence level is -CF(A). CF(A) = 0 means that A is unknown.

[0078] Then, the confidence calculation method of the rules of different logical relationships is defined. For example, the logical operations include: "and", "or", and "not". The logical operations of the confidence method include: CF(A and B) = min{CF(A), CF(B)}, CF(Aor B) = max{CF(A), CF(B)}, CF(not A) = -CF(A). Exemplarily, A represents the confidence that cloudy weather is the cause of the yellowing of the pine forest, B represents the confidence that high humidity is the cause of the yellowing of the pine forest, and C represents the confidence that strong wind is the cause of the yellowing of the pine forest. The confidence that cloudy weather, high humidity and strong wind are the causes of the yellowing of the pine forest can be expressed as: CF(cloudy weather and high humidity and strong wind) = CF((cloudy weather and high humidity) and strong wind) = min{min{CF(cloudy weather), CF(high humidity)}, CF(strong wind)}.

[0079] In another example, under the DS theory framework, IF A THEN B CF(A, B) is defined to indicate that when A holds, that is, when CF(A) > 0, conclusion B holds. CF(B, A) is the confidence level of the rule, ranging from -1 to 1. Given that CF(cloudy weather, the pine forest turns yellow) = 0.5, and CF(high humidity, the pine forest turns yellow) = 0.5, A indicates that cloudy weather and high humidity will cause the pine forest to turn yellow, and B indicates that the pine forest turns yellow. IF cloudy weather and high humidity THEN it rains 0.8, that is, CF(B, A) = 0.8, then according to the logical operation rules in DS theory, CF(A) = min(CF(cloudy weather, the pine forest turns yellow), CF(high humidity, the pine forest turns yellow)) = min(0.5, 0.6) = 0.5, and CF(B) = max(0, CF(cloudy weather and high humidity))*0.8 = max(0, 0.5)*0.8 = 0.4.

[0080] In an optional embodiment, when multiple rules support the same conclusion (i.e., the pine forest turns yellow), the confidence level can be calculated according to Formula 3, which can be expressed as follows:

[0081]

[0082] CF(B) = CF1(B) * CF2(B) wherein CF(B) represents the confidence of the pine forest yellowing under different reasons, CF1(B) represents the confidence of the pine forest yellowing according to rule 1, and CF2(B) represents the confidence of the pine forest yellowing according to rule 2.

[0083] By accurately judging the logical relationship between a plurality of first type rules, the logical association such as "and", "or" and "not" between rules can be effectively identified, and the technical effects of optimizing rule combination and enhancing reasoning logic are achieved. Meanwhile, by combining the D-S theory and the logical relationship, the confidence of the pine forest yellowing reason belonging to the first type reason in the target region can be accurately calculated. Meanwhile, when there is no direct logical association between rules, scattered information can still be integrated into overall confidence evaluation according to the D-S theory, ensuring the comprehensiveness and accuracy of the analysis process. Even in a complex environment of information fragmentation, reliable analysis results can still be output, and the technical effects of improving problem identification and solution efficiency are achieved.

[0084] Optionally, in the pine forest yellowing reason determination method provided in Embodiment One of the present application, whether the target region exists in the pine forest region is detected according to the image data, comprising: photographing a preset position in the pine forest region through a camera device to obtain image data; inputting the image data into a target detection model to detect whether the target region exists in the pine forest region through the target detection model for the first time to obtain a detection result; in the case that the detection result indicates that the target region exists, reacquiring image data of the target region by adjusting device parameters of the camera device to obtain twice-acquired image data; and detecting the twice-acquired image data through the target detection model to detect whether the target region exists in the pine forest region for the second time.

[0085] In Embodiment One, the pan-tilt camera device deployed at a high point can automatically photograph the preset key pine forest region, ensuring the coverage and continuity of the monitoring, which is conducive to obtaining rich image data and then accurately analyzing the pine forest yellowing reason.

[0086] Then, the acquired image data is input into the pre-trained target detection model for the first time to check whether the target region, i.e., the pine forest region with yellowing signs, exists in the pine forest region. The target detection model can accurately identify the yellowing region in the image by using deep learning technology to obtain the detection result. If the first detection result shows that the target region indeed exists, the device parameters of the camera device, such as focusing, zooming and the like, will be further automatically adjusted to reacquire image data of the target region, i.e., twice-acquired image data, from a more detailed angle. This step aims to improve the definition and detail richness of the image, provide higher quality input and ensure the accuracy of the analysis result.

[0087] Finally, the target detection model performs a second detection on the secondly collected image data, again checking whether there is a target area within the pine forest area. The second detection not only verifies the accuracy of the first detection, but also, with the support of clearer and more detailed image data, can more accurately define the range and extent of the yellowing area, providing a solid foundation for subsequent in-depth analysis and cause tracing.

[0088] Through the above steps, the efficiency and accuracy of monitoring are significantly improved, the need for manual intervention is reduced, and reliable data support is provided for subsequent in-depth analysis of the causes of pine forest yellowing, further realizing comprehensive monitoring and intelligent diagnosis of the health status of pine forests.

[0089] Optionally, in the method for determining the cause of pine forest yellowing provided in Embodiment One of the present application, determining whether the pine forest yellowing process of the target area belongs to the first type of change or the second type of change according to the image data of the target area within the preset time period comprises: obtaining device identification information of the camera device and coordinate information of the target area; obtaining the image data of the target area within the preset time period according to the device identification information and the coordinate information; segmenting the target area in the image data of the target area within the preset time period through an image segmentation algorithm to obtain a segmentation result sequence within the preset time period; and determining whether the pine forest yellowing process of the target area belongs to the first type of change or the second type of change according to the segmentation results at different times in the segmentation result sequence.

[0090] In Embodiment One, first, the unique device identification information of the camera device and the specific coordinate information of the target area are obtained. The device identification information is used to uniquely identify each camera device, and the coordinate information precisely locates the pine forest area that needs to be focused on. By obtaining the device identification information and the coordinate information, it is beneficial to assist in subsequent identification of the cause of pine forest yellowing.

[0091] Then, according to the device identification information and the coordinate information, the image data of the target area within the preset time period can be selectively accessed from the stored database or through the API interface. This process realizes effective management and rapid retrieval of data, ensuring the timeliness of data in the analysis process.

[0092] Secondly, advanced image segmentation algorithms are used to accurately segment the target area to obtain a segmentation result sequence within the preset time period. These segmentation results not only define the spatial range of the yellowing area, but also provide image information that changes over time, laying a foundation for subsequent trend analysis.

[0093] Finally, according to the segmentation results at different times in the segmentation result sequence, the color change degree and area change trend are analyzed to determine whether the pine forest yellowing of the target area belongs to the first type of sudden change or the second type of gradual change.

[0094] By comparing the segmentation results at different time points, the change type of the yellowing speed can be identified, the specific pine forest yellowing reason can be further speculated, reasonable analysis can be made according to the change trend in the absence of direct evidence, the work efficiency and analysis accuracy are significantly improved, and advanced technical support is further provided for ecological environment protection.

[0095] Optionally, in the first embodiment, Figure 4 is a structural schematic diagram of an optional pine forest yellowing reason determination system provided according to the first embodiment of the present application. First, the high-point pan-tilt camera shoots the pine forest area regularly according to the preset cruise route, ensuring the continuity and comprehensiveness of the monitoring coverage. This process is automatically performed without human intervention, and the pictures taken by the camera become the raw data for subsequent analysis. Then, these picture data are input into the computer vision-based recognition algorithm, which automatically identifies the suspected yellowing area through specific image processing techniques (for example, the target detection algorithm described above). This identification process is based on color change characteristics and can quickly lock the pine forest area that may be yellowing. Secondly, after the suspected yellowing area is identified, the system automatically adjusts the camera to focus and zoom in on the target point for secondary confirmation. This detailed inspection step can reduce false positives and improve the accuracy of yellowing area identification. Finally, after confirming the yellowing state, the system starts the analysis and reasoning service, obtains the image data of the target area in the past 30 days from the database, and uses the image segmentation algorithm to compare the color change degree and area change trend of the yellowing area to determine whether the yellowing state is sudden or gradual. At the same time, combined with the domain knowledge in the rule base, such as environmental factors, pest information, etc., deep analysis is performed, and the confidence of the yellowing reason and the underlying evidence chain are output, for example, "the pine forest in Chengdu Dujiangyan area gradually yellowed with a confidence of 72% caused by pine line pests, reason: the number of pine pitch pests in the area increased, and the temperature and humidity conditions were suitable for breeding". This not only provides reason analysis, but also gives specific supporting evidence, greatly enhancing the reliability and interpretability of the analysis results.

[0096] Optionally, in the first embodiment, Figure 5is a schematic diagram of an optional analysis process of pine forest yellowing reasons according to the first embodiment of the present application. First, through the first identification of the yellowing area, automatic focusing and the method, secondary identification is carried out, focusing on the change history of the yellowing area in the past month, through image sequence comparison, the system can capture the subtle changes of the color and vegetation condition of the area, evaluate and classify the yellowing mode, and determine whether the change belongs to mutation (rapid change in a short period) or gradual change (slow development in a long period). After determining the yellowing mode, according to the preset analysis process and rule base, the specific reasons for the yellowing are further explored. The specific reasons include but are not limited to: human activities (such as deforestation, fire), environmental changes (such as lightning, mudslides), growth environment factors (such as nutrients, humidity), or diseases and pests (especially focusing on pine line diseases and pests), etc. Then, the key knowledge in the field is summarized to build the basis for identifying the color change epidemic wood, the single rule confidence evaluation is applied, the confidence of the possibility of pine line disease and pest activity is adjusted according to the real-time monitored temperature data, for example, when the temperature reaches 25 degrees, the confidence of the disease and pest activity will be significantly improved to 0.8, otherwise it will be reduced, ensuring the scientificity and accuracy of the analysis result. Different knowledge points can be connected through the knowledge graph association to form a more comprehensive analysis perspective, for example, the temperature, humidity and disease and pest transmission are related to each other, and the comprehensiveness of the judgment is improved. Multi-rule synthesis and reasoning can also be carried out, according to the logical relationship of the rules, such as merging inheritance, the confidence of multiple related rules is calculated comprehensively to obtain the final conclusion about the reasons for the yellowing of the pine forest. At the same time, forward reasoning and reverse reasoning are also supported, which can analyze the possible causes of the yellowing area according to the current evidence combined with the conditions in the historical database, output the explanatory result, and provide clear guidance for the subsequent prevention and control measures.

[0097] Optionally, in the first embodiment, Figure 6is a schematic diagram of optional rule hierarchy and priority provided according to Embodiment One of the present application. First, in analyzing the reason for pine forest yellowing, it is divided into "abrupt change" or "gradual change" based on the trend of image features. This initial judgment is the primary step in the entire analysis process, and the identification results of abrupt change and gradual change will directly determine the direction and focus of subsequent analysis, so they are given the highest priority. Then, consider a series of medium-priority environmental variables such as temperature, humidity and rainfall. Although these factors are not direct causes, they can significantly affect the occurrence and development of diseases, so they play a key role in strengthening or weakening the conclusion in the analysis framework. Through continuous monitoring and analysis of these variables, the root cause of yellowing can be more accurately located. Second, for specific yellowing patterns, a series of optional medium-priority variables are evaluated, including the number of pine carpenter beetles caught, the frequency of debris flow, the detection results of smoke or flame, and signs of illegal logging. These variables are directly or indirectly related to the occurrence of disease and are an indispensable part of determining the cause of yellowing. According to the actual situation, select the most relevant variables to the current yellowing pattern for in-depth analysis to enhance the reliability and relevance of the conclusion. Finally, focus on the secondary priority and low-priority variables such as the reference of surrounding historical cases, the consideration of nutrient status and the vegetation type in the area. Although the direct effect of these factors is small, they can provide richer background information for analysis and help improve the reasoning process to ensure the comprehensiveness and depth of the final conclusion. Through layer-by-layer analysis, multiple possible causal relationships can be considered, and finally a pine forest yellowing reason and its confidence level are output, providing scientific basis and precise guidance for forest health management and disease prevention and control, and achieving intelligent guardianship of pine forest ecological health.

[0098] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0099] Embodiment Two

[0100] The pine forest yellowing reason determination device provided in Embodiment Two of the present application can be used to execute the pine forest yellowing reason determination method provided in Embodiment One of the present application. The pine forest yellowing reason determination device provided in Embodiment Two of the present application is introduced as follows.

[0101] Figure 7 is a schematic diagram of the pine forest yellowing reason determination device provided according to Embodiment Two of the present application. As shown in Figure 7 , the device includes a detection unit 701, a judgment unit 702, a calculation unit 703 and a determination unit 704.

[0102] Specifically, the detection unit 701 is configured to collect image data of the pine forest region, and detect whether a target region of pine forest yellowing exists in the pine forest region according to the image data.

[0103] The judgment unit 702 is configured to, in the case that the target region is detected, judge whether the pine forest yellowing process of the target region belongs to a first type of change or a second type of change according to image data of the target region in a preset time period, wherein the change speed of the first type of change is faster than that of the second type of change, the first type of change corresponds to a first type of reason of pine forest yellowing, and the second type of change corresponds to a second type of reason of pine forest yellowing.

[0104] The calculation unit 703 is configured to acquire a growth condition of the pine forest region, and calculate a confidence degree of the first type of reason or a confidence degree of the second type of reason according to a rule base and the growth condition, wherein the rule base stores analysis rules related to pine forest yellowing.

[0105] The determination unit 704 is configured to determine the reason of pine forest yellowing in the target region according to the confidence degree of the first type of reason or the confidence degree of the second type of reason.

[0106] The pine forest yellowing reason determination device provided in the second embodiment of the present application collects image data of the pine forest region through the detection unit 701, and detects whether a target region of pine forest yellowing exists in the pine forest region according to the image data; the judgment unit 702 judges whether the pine forest yellowing process of the target region belongs to a first type of change or a second type of change according to image data of the target region in a preset time period in the case that the target region is detected, wherein the change speed of the first type of change is faster than that of the second type of change, the first type of change corresponds to a first type of reason of pine forest yellowing, and the second type of change corresponds to a second type of reason of pine forest yellowing; the calculation unit 703 acquires a growth condition of the pine forest region, and calculates a confidence degree of the first type of reason or a confidence degree of the second type of reason according to a rule base and the growth condition, wherein the rule base stores analysis rules related to pine forest yellowing; and the determination unit 704 determines the reason of pine forest yellowing in the target region according to the confidence degree of the first type of reason or the confidence degree of the second type of reason, thereby solving the problem in the related art that only a single reason can be used to analyze the reason of pine forest yellowing when image data is analyzed through an artificial intelligence algorithm, and the reason of pine forest yellowing obtained through analysis is inaccurate.

[0107] The image data of the pine forest area is periodically collected by the pan-tilt camera deployed at a high point, and whether there is a target area of pine forest yellowing is detected by using advanced image processing technology, so that the subtle changes of the pine forest health can be captured in time, and the technical effects of early warning and timely intervention of the pine forest yellowing process are achieved. At the same time, by analyzing the image data of the target area in a preset time period, it is determined whether the pine forest yellowing process belongs to the first type of change with fast change speed or the second type of change with slow change speed, so that the system can distinguish between sudden events and long-term problems, realize accurate classification, and further achieve the technical effects of improving the diagnosis efficiency and accuracy and shortening the response time. In addition, by obtaining the growth environment data of the pine forest area, the confidence of the first type or the second type of reason is calculated according to the rich analysis rules in the rule base and the growth conditions, so that multiple potential factors can be considered comprehensively, the complex reason analysis is realized, and the accuracy of the pine forest yellowing reason analysis is greatly improved, and further technical effects of providing comprehensive and scientific solutions are achieved, providing strong support for forestry resource protection and ecological environment construction.

[0108] Optionally, in the pine forest yellowing reason determination apparatus provided in Embodiment Two of the present application, the apparatus further includes: a first generation unit, configured to generate rules by extracting first type of knowledge directly related to pine forest yellowing in the target area based on expert field knowledge and historical data through a semantic analysis model before calculating the confidence of the first type of reason or the confidence of the second type of reason according to the rule base and the growth conditions; or a second generation unit, configured to generate rules by extracting a plurality of second type of knowledge related to pine forest yellowing in the target area based on expert field knowledge and historical data through a semantic network analysis, wherein the plurality of second type of knowledge includes: a preceding event, an actual event, and an association relationship between the preceding event and the actual event; and a construction unit, configured to determine the confidence corresponding to the rules, and construct the rule base according to the rules and the confidence corresponding to the rules.

[0109] Optionally, in the pine forest yellowing reason determination apparatus provided in Embodiment Two of the present application, the pine forest yellowing process of the target area is the first type of change, and the calculation unit 703 includes: a first determination sub-unit, configured to determine first type of information according to the growth conditions, wherein the first type of information includes at least one of: first sub-type of information and second sub-type of information, the first sub-type of information is information related to human activities, and the second sub-type of information is information related to natural environment; a second determination sub-unit, configured to determine first type of rules related to the first type of change in the rule base through a semantic analysis model, wherein the first type of rules include at least one of: first sub-type of rules and second sub-type of rules, the first sub-type of rules are rules related to human activities, and the second sub-type of rules are rules related to natural environment; and a matching sub-unit, configured to match the first type of rules with the first type of information, and determine the confidence that the pine forest yellowing reason in the target area belongs to the first type of reason.

[0110] Optionally, in the pine forest yellowing reason determination apparatus provided in Embodiment Two of the present application, the pine forest yellowing process of the target area belongs to the second type of change, the calculation unit 703 comprises: a third determination sub-unit, configured to determine second type information according to the growth condition, wherein the second type information comprises at least one of: third sub-type information and fourth sub-type information, the third sub-type information is information related to the pine forest growth environment, and the fourth sub-type information is information related to the disease and insect pests; a fourth determination sub-unit, configured to determine second type rules related to the pine forest growth environment in the rule base through a semantic analysis model, wherein the second type rules comprise at least one of: third sub-type rules and fourth sub-type rules, the third sub-type rules are rules related to the pine forest growth environment, and the fourth sub-type rules are rules related to the disease and insect pests; and a fifth matching sub-unit, configured to match the second type rules with the second type information to determine the confidence degree that the pine forest yellowing reason in the target area belongs to the second type of reason.

[0111] Optionally, in the pine forest yellowing reason determination apparatus provided in Embodiment Two of the present application, the number of the first type of rules is N, N is an integer greater than 1, and the matching sub-unit comprises: a judgment module, configured to judge whether there is a logical relationship between each rule in the plurality of first type rules, wherein the logical relationship comprises at least one of: AND, OR, and NOT; a first calculation module, configured to, in the case that there is a logical relationship between each rule, calculate the confidence degree that the pine forest yellowing reason in the target area belongs to the first type of reason according to a preset mathematical algorithm and the logical relationship; and a second calculation module, configured to, in the case that there is no logical relationship between each rule, calculate the confidence degree that the pine forest yellowing reason in the target area belongs to the first type of reason according to a preset mathematical algorithm and a rule merging algorithm.

[0112] Optionally, in the pine forest yellowing reason determination apparatus provided in Embodiment Two of the present application, the detection unit 701 comprises: a first acquisition sub-unit, configured to capture a preset position in the pine forest area through a camera device to obtain image data; a first detection sub-unit, configured to input the image data into a target detection model to first detect whether there is a target area in the pine forest area through the target detection model to obtain a detection result; a second acquisition sub-unit, configured to, in the case that the detection result indicates that the target area exists, re-acquire image data of the target area by adjusting device parameters of the camera device to obtain twice-acquired image data; and a second detection sub-unit, configured to detect the twice-acquired image data through the target detection model to second detect whether there is a target area in the pine forest area.

[0113] Optionally, in the pine forest yellowing reason determination device provided in Embodiment Two of the present application, the determination unit 702 comprises: a first acquisition subunit configured to acquire device identification information of the camera device and coordinate information of the target region; a second acquisition subunit configured to acquire image data of the target region in a preset time period according to the device identification information and the coordinate information; a segmentation subunit configured to segment the target region in the image data of the target region in the preset time period by using an image segmentation algorithm to obtain a segmentation result sequence in the preset time period; and a judgment subunit configured to determine whether the pine forest yellowing process of the target region belongs to the first type of change or the second type of change according to segmentation results at different times in the segmentation result sequence.

[0114] The pine forest yellowing reason determination device comprises a processor and a memory, and the detection unit 701, the determination unit 702, the calculation unit 703 and the determination unit 704 are stored in the memory as program units, and the corresponding functions are realized by the processor executing the program units stored in the memory.

[0115] The processor comprises a core, and the core is used to call the corresponding program units from the memory. One or more than one core can be set, and the accuracy of the pine forest yellowing reason analysis result can be improved by adjusting the core parameters.

[0116] The memory can comprise a non-permanent memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory comprises at least one memory chip.

[0117] Embodiment Three of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the pine forest yellowing reason determination method.

[0118] Embodiment Four of the present application provides a processor, which is used to run a program, and the program is executed to realize the pine forest yellowing reason determination method.

[0119] Figure 8 is a schematic diagram of the pine forest yellowing reason determination electronic device provided in Embodiment Five of the present application. As shown in Figure 8As shown, embodiment 5 of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and capable of running on the processor, and when the processor executes the program, the following steps are implemented: collecting image data of a pine forest area, and detecting whether there is a target area where the pine forest turns yellow in the pine forest area based on the image data; when the target area is detected, judging whether the yellowing process of the pine forest in the target area belongs to the first type of change or the second type of change based on the image data of the target area within a preset time period, wherein the change speed of the first type of change is faster than the change speed of the second type of change, the first type of change corresponds to the first type of cause of the yellowing of the pine forest, and the second type of change corresponds to the second type of cause of the yellowing of the pine forest; obtaining the growth condition of the pine forest area, and calculating the confidence of the first type of cause or the confidence of the second type of cause based on the rule base and the growth condition, wherein the rule base stores analysis rules related to the yellowing of the pine forest; determining the cause of the yellowing of the pine forest in the target area based on the confidence of the first type of cause or the confidence of the second type of cause.

[0120] When the processor executes the program, the following steps are also implemented: before calculating the confidence of the first type of cause or the confidence of the second type of cause based on the rule base and growth conditions, the above method also includes: based on expert domain knowledge and historical data, extracting the first type of knowledge directly related to the yellowing of pine forests in the target area through a semantic analysis model to generate rules; or, based on expert domain knowledge and historical data, extracting multiple second type of knowledge related to the yellowing of pine forests in the target area through semantic network analysis to generate rules, wherein the multiple second type of knowledge includes: preceding events, actual events, and there is a correlation between the preceding events and the actual events; determining the confidence corresponding to the rules, and constructing a rule base based on the rules and the confidence corresponding to the rules.

[0121] When the processor executes the program, the following steps are also implemented: the yellowing process of the pine forest in the target area belongs to the first type of change, and the confidence of the first type of cause or the confidence of the second type of cause is calculated based on the rule base and the growth situation, including: determining the first type of information based on the growth situation, wherein the first type of information includes at least one of the following: first sub-category information, second sub-category information, the first sub-category information is information related to human activities, and the second sub-category information is information related to the natural environment; determining the first type of rules related to the first type of change in the rule base through a semantic analysis model, wherein the first type of rules includes at least one of the following: first sub-category rules, second sub-category rules, the first sub-category rules are rules related to human activities, and the second sub-category rules are rules related to the natural environment; matching the first type of rules with the first type of information to determine the confidence that the cause of the yellowing of the pine forest in the target area belongs to the first type of cause.

[0122] The processor further implements the following steps when executing the program: the pine forest yellowing process of the target area belongs to the second type of change, and the confidence of the first type of reason or the confidence of the second type of reason is calculated according to the rule base and the growth condition, including: determining the second type of information in the growth condition, wherein the second type of information includes at least one of the third sub-type information and the fourth sub-type information, the third sub-type information is information related to the growth environment of the pine forest, and the fourth sub-type information is information related to the disease and insect pests; determining the second type of rule related to the growth environment of the pine forest in the rule base through the semantic analysis model, wherein the second type of rule includes at least one of the third sub-type rule and the fourth sub-type rule, the third sub-type rule is a rule related to the growth environment of the pine forest, and the fourth sub-type rule is a rule related to the disease and insect pests; and matching the second type of rule with the second type of information to determine the confidence of the pine forest yellowing reason in the target area belonging to the second type of reason.

[0123] The processor further implements the following steps when executing the program: the number of the first type of rules is N, N is an integer greater than 1, the first type of rules are matched with the first type of information to determine the confidence of the pine forest yellowing reason in the target area belonging to the first type of reason, including: judging whether there is a logical relationship between each rule in the plurality of first type of rules, wherein the logical relationship includes at least one of and, or, and not; in the case that there is a logical relationship between each rule, the confidence of the pine forest yellowing reason in the target area belonging to the first type of reason is calculated according to a preset mathematical algorithm and the logical relationship; and in the case that there is no association relationship between each rule, the confidence of the pine forest yellowing reason in the target area belonging to the first type of reason is calculated according to a preset mathematical algorithm and a rule merging algorithm.

[0124] The processor further implements the following steps when executing the program: whether there is a target area of pine forest yellowing in the pine forest area is detected according to the image data, including: capturing the preset position in the pine forest area through the camera device to obtain the image data; inputting the image data into the target detection model, and detecting whether there is a target area in the pine forest area through the target detection model for the first time to obtain a detection result; in the case that the detection result indicates that the target area exists, reacquiring the image data of the target area by adjusting the device parameters of the camera device to obtain the image data acquired for the second time; and detecting the image data acquired for the second time through the target detection model to detect whether there is a target area in the pine forest area for the second time.

[0125] The processor further implements the following steps when executing the program: judging, according to image data of the target region in a preset time period, whether the yellowing process of the target region belongs to the first type of change or the second type of change, including: obtaining device identification information of the camera device, and obtaining coordinate information of the target region; obtaining the image data of the target region in the preset time period according to the device identification information and the coordinate information; segmenting the target region in the image data of the target region in the preset time period through an image segmentation algorithm to obtain a segmentation result sequence in the preset time period; and judging, according to segmentation results at different moments in the segmentation result sequence, whether the yellowing process of the target region belongs to the first type of change or the second type of change.

[0126] The device herein can be a server, a PC, a PAD, a mobile phone, etc.

[0127] Those skilled in the art should understand that embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0128] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0129] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0130] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1 Figure 1

[0131] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0132] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory can also include a compact disk read only memory (CD-ROM), digital versatile disk (DVD), Blu-ray, or another non-transitory computer readable medium, which is non-volatile and non-transitory in nature, but volatile in that it can lose its content if the power to the computer is turned off or if the computer crashes. The memory is an example of a computer readable medium.

[0133] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD), or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media such as modulated data signals and carriers.

[0134] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0135] ​​Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining the cause of yellowing of pine forests, characterized in that: include: Collecting image data of a pine forest area, and detecting whether there is a target area of ​​yellowing pine trees in the pine forest area based on the image data; When the target area is detected, determining whether the yellowing process of the pine forest in the target area belongs to the first type of change or the second type of change based on image data of the target area within a preset time period, wherein a change rate of the first type of change is faster than a change rate of the second type of change, the first type of change corresponds to the first type of cause of the yellowing of the pine forest, and the second type of change corresponds to the second type of cause of the yellowing of the pine forest; Acquiring growth conditions of the pine forest area, and calculating the confidence level of the first type of cause or the confidence level of the second type of cause based on a rule base and the growth conditions, wherein the rule base stores analysis rules related to yellowing of pine forests; The cause of the yellowing of the pine forest in the target area is determined based on the confidence level of the first type of cause or the confidence level of the second type of cause.

2. The method according to claim 1, characterized in that Before calculating the confidence level of the first-category cause or the confidence level of the second-category cause based on the rule base and the growth situation, the method further includes: Based on expert domain knowledge and historical data, a semantic analysis model is used to extract first-category knowledge directly related to the yellowing of pine forests in the target area and generate rules; or Based on expert domain knowledge and historical data, multiple second-category knowledge related to the yellowing of pine forests in the target area is extracted through semantic network analysis to generate rules, wherein the multiple second-category knowledge includes: a preceding event and an actual event, and there is an association relationship between the preceding event and the actual event; The confidence levels corresponding to the rules are determined, and the rule base is constructed according to the rules and the confidence levels corresponding to the rules.

3. The method according to claim 1, characterized in that The yellowing process of the pine forest in the target area belongs to the first type of change, and the confidence of the first type of cause or the confidence of the second type of cause is calculated based on the rule base and the growth situation, including: Determining first-category information based on the growth condition, wherein the first-category information includes at least one of the following: first subcategory information and second subcategory information, the first subcategory information being information related to human activities, and the second subcategory information being information related to the natural environment; Determining, by using a semantic analysis model, first-category rules in the rule base that are related to the first-category change, wherein the first-category rules include at least one of the following: first-subcategory rules and second-subcategory rules, wherein the first-subcategory rules are rules related to human activities, and the second-subcategory rules are rules related to the natural environment; The first type of rules are matched with the first type of information to determine the confidence level that the cause of the yellowing of the pine forests in the target area belongs to the first type of causes.

4. The method according to claim 1, wherein The yellowing process of the pine forest in the target area belongs to the second type of change. The confidence of the first type of cause or the confidence of the second type of cause is calculated based on the rule base and the growth situation, including: Determining second-category information based on the growth conditions, wherein the second-category information includes at least one of the following: third subcategory information and fourth subcategory information, wherein the third subcategory information is information related to the pine forest growth environment, and the fourth subcategory information is information related to pests and diseases; Determining, by using a semantic analysis model, a second category of rules related to the pine forest growth environment in the rule base, wherein the second category of rules includes at least one of the following: a third subcategory of rules and a fourth subcategory of rules, wherein the third subcategory of rules is related to the pine forest growth environment, and the fourth subcategory of rules is related to pests and diseases; The second type of rules are matched with the second type of information to determine the confidence level that the cause of the yellowing of the pine forests in the target area belongs to the second type of causes.

5. The method according to claim 3, characterized in that The number of the first-category rules is N, where N is an integer greater than 1. Matching the first-category rules with the first-category information to determine the confidence level that the cause of yellowing of pine forests in the target area belongs to the first-category cause includes: Determining whether there is a logical relationship between each of the plurality of first-category rules, wherein the logical relationship includes at least one of the following: AND, OR, NOT; In the case where there is a logical relationship between each rule, the confidence level that the cause of the yellowing of the pine forest in the target area belongs to the first category of causes is calculated according to a preset mathematical algorithm and the logical relationship; In the case that there is no correlation between each piece of knowledge, the confidence that the cause of the yellowing of the pine forest in the target area belongs to the first category of causes is calculated based on the preset mathematical algorithm and the rule merging algorithm.

6. The method according to claim 1, characterized in that Detecting whether there is a target area where the pine forest turns yellow within the pine forest area based on the image data includes: photographing a preset position in the pine forest area using a camera device to obtain the image data; Inputting the image data into a target detection model, and detecting for the first time whether the target area exists in the pine forest area by the target detection model to obtain a detection result; When the detection result indicates that the target area exists, re-collecting image data of the target area by adjusting device parameters of the imaging device to obtain secondary collected image data; The target detection model is used to detect the second-collected image data, and a second detection is performed to determine whether the target area exists in the pine forest area.

7. The method according to claim 1, characterized in that Determining whether the yellowing process of the pine forest in the target area belongs to the first type of change or the second type of change based on the image data of the target area within a preset time period includes: Obtaining device identification information of the camera device and obtaining coordinate information of the target area; Acquiring image data of the target area within the preset time period based on the device identification information and the coordinate information; Segmenting the target area from the image data of the target area within the preset time period using an image segmentation algorithm to obtain a sequence of segmentation results within the preset time period; It is determined whether the yellowing process of the pine forest in the target area belongs to the first type of change or the second type of change according to the segmentation results at different moments in the segmentation result sequence.

8. A device for determining the cause of yellowing of pine forests, characterized in that: include: a detection unit, configured to collect image data of a pine forest area, and detect whether there is a target area where the pine forest turns yellow in the pine forest area based on the image data; a judgment unit configured to, when the target area is detected, judge whether the yellowing process of the pine forest in the target area belongs to the first type of change or the second type of change based on image data of the target area within a preset time period, wherein a change rate of the first type of change is faster than a change rate of the second type of change, the first type of change corresponds to the first type of cause of the yellowing of the pine forest, and the second type of change corresponds to the second type of cause of the yellowing of the pine forest; a calculation unit, configured to obtain a growth condition of the pine forest area, and calculate a confidence level of the first type of cause or a confidence level of the second type of cause based on a rule base and the growth condition, wherein the rule base stores analysis rules related to yellowing of pine forests; A determination unit is used to determine the cause of the yellowing of the pine forest in the target area based on the confidence level of the first type of cause or the confidence level of the second type of cause.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes stored computer instructions, wherein when the computer instructions are executed by a processor, the method for determining the cause of yellowing of a pine forest according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the cause of yellowing of pine forests as described in any one of claims 1 to 7.

Images