Method, system and equipment for planting and monitoring radishes resistant to bolting and capable of preventing insect pests

Abstract

The invention discloses a bolting-resistant and pest-resistant radish planting monitoring method, system and device, and the method comprises the following steps: obtaining a radish plant image of a target region, and recognizing whether there is a radish bolting feature in the radish plant image; if the radish bolting characteristic exists, generating first early warning information; obtaining a radish leaf image of the target area, and identifying whether pest features exist in the radish leaf image; if the insect pest characteristics exist, second early warning information is generated; and sending the first early warning information and / or the second early warning information to a background terminal. The application has the advantages of accurately monitoring and identifying bolting and insect pest conditions in the radish growth process and reducing artificial monitoring errors.

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to a method, system and equipment for monitoring radish planting that is resistant to bolting and resistant to insect pests. Background Art

[0002] Radish is an important vegetable in my country. It is grown all over the country. It can be cultivated in all seasons and supplied all year round. The production and sales volume is also very large. Due to the improvement of people's living standards, changes in consumption habits, and the development of science and technology, off-season cultivation has also developed. Taking advantage of the difference in alpine climate, solar greenhouses and large, medium and small plastic greenhouses are used for cultivation, making radishes available in the market out of season.

[0003] At present, when cultivating radishes in large quantities in greenhouses, in order to ensure that more high-quality radishes are grown, it is necessary to regularly observe the growth status of the radishes, with a focus on the early bolting and insect pests of radishes. However, this mainly relies on regular manual observation and monitoring and timely treatment, which is prone to large errors and poor accuracy in manual monitoring, ultimately leading to untimely post-processing and affecting the yield of high-quality radishes. Summary of the invention

[0004] The main purpose of the present application is to provide a method, system and equipment for monitoring radish planting that is resistant to bolting and pests, aiming to solve the technical problems that the existing radish planting monitoring relies on manual monitoring, which is prone to large manual monitoring errors and poor accuracy.

[0005] To achieve the above objectives, the present application provides a radish planting monitoring method that is resistant to bolting and insect pests, comprising the following steps: Acquire the radish plant image in the target area, and identify whether there is a radish bolting feature in the radish plant image; If there are radish bolting characteristics, generate the first warning information; Obtaining a radish leaf image of a target area, and identifying whether there are pest features in the radish leaf image; If there are pest characteristics, a second warning message is generated; The first warning information and / or the second warning information is sent to the backend terminal.

[0006] Optionally, acquiring the radish plant image in the target area and identifying whether there is a radish bolting feature in the radish plant image includes: Acquire a first image of the radish plant group corresponding to the target area; wherein the first image is an image based on a side perspective of the radish plant group; Obtaining a height characteristic value of the radish plant group corresponding to the first image, and comparing the height characteristic value with a preset height threshold; If the height feature value is less than the height threshold, it is identified that no radish bolting feature exists in the first image.

[0007] Optionally, obtaining a height characteristic value corresponding to the radish plant group in the first image, and comparing the height characteristic value with a preset height threshold, includes: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a first height value of the highest point based on a first reference level; wherein the first reference level is a horizontal plane where the radish plant and the soil layer meet; The first height value is compared with a preset first height threshold.

[0008] Optionally, obtaining a height characteristic value corresponding to the radish plant group in the first image, and comparing the height characteristic value with a preset height threshold, includes: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a second height value of the highest point based on a second reference level; wherein the second reference level is a horizontal plane where the current average height of the radish plant group is located; The second height value is compared with a preset second height threshold.

[0009] Optionally, if the height feature value is greater than or equal to the height threshold, the method further includes: Acquire a second image of the radish plant corresponding to the target area; wherein the second image is an image based on a top-down perspective of the radish plant; Acquire the appearance contour features of the corresponding radish plant in the second image; Extract the central area features of the shape contour features; Identify whether there is an abnormal grayscale value in the central area feature; the abnormal grayscale value is the grayscale value corresponding to the color of the petals of the radish bolting and flowering; If there is an abnormal grayscale value, it is identified that there is a radish bolting feature in the second image.

[0010] Optionally, if there is no abnormal gray value, it also includes: Identify whether there are abnormal contour features in the central area features; wherein the abnormal contour features are the appearance features of the buds or petals of the radish; If there is an abnormal contour feature, it is identified that there is a radish bolting feature in the second image.

[0011] Optionally, acquiring the radish leaf image of the target area and identifying whether there are pest features in the radish leaf image includes: Acquire a radish leaf image of a target area; wherein the radish leaf image is an image based on a top-down perspective of a radish plant; Identify the abnormal shadow area in the radish leaf image; the abnormal shadow area is the area covered by the radish leaves where pests and diseases attach; Compare the abnormal shadow area with a preset area threshold; If the abnormal shadow area is larger than the area threshold, it is recognized that there are pest features in the radish leaf image.

[0012] Optionally, the step of acquiring the radish leaf image of the target area and identifying whether there are pest features in the radish leaf image further includes: Obtaining the leaf missing area in the radish leaf image; wherein the leaf missing area is the area of ​​the missing portion of the radish leaf after being infested by pests and diseases; Obtaining a leaf missing rate; wherein the leaf missing rate is a ratio of a leaf missing area to a leaf complete area; comparing the leaf missing rate with a preset missing rate threshold; If the leaf missing rate is greater than the missing rate threshold, it is recognized that there are pest features in the radish leaf image.

[0013] To achieve the above objectives, the present application also provides a radish planting monitoring system that is resistant to bolting and insect pests, comprising: A bolting feature recognition module is used to obtain a radish plant image in a target area and identify whether there is a radish bolting feature in the radish plant image; A first information generating module, configured to generate a first warning message if the radish bolting feature exists; The pest feature recognition module is used to obtain the radish leaf image of the target area and identify whether there are pest features in the radish leaf image; A second information generating module, used to generate second warning information if there are pest characteristics; The information sending module is used to send the first warning information and / or the second warning information to the background terminal.

[0014] To achieve the above objectives, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.

[0015] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the above method.

[0016] The beneficial effects that this application can achieve are as follows: The present application is based on machine vision recognition technology. By acquiring images of radish plants, it is determined whether there are radish bolting features. If there are radish bolting features, a first warning message can be generated and sent to a background terminal. By acquiring images of radish leaves, it is determined whether there are pest features. If there are pest features, a second warning message can be generated and sent to a background terminal, thereby realizing unattended monitoring of the early bolting and pest status during the growth of radish, and promptly notifying management personnel for processing. The use of machine vision recognition can improve recognition accuracy and reduce human errors, which is conducive to the cultivation of more high-quality radishes that are resistant to bolting and low in pests. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0018] Figure 1 A schematic diagram of a process of a radish planting monitoring method that is resistant to bolting and pests in an embodiment of the present application; Figure 2 Schematic diagram of the principle of obtaining a first height value H1 based on a first image in an embodiment of the present application; Figure 3 Schematic diagram of the principle of obtaining the second height value H2 based on the first image in an embodiment of the present application.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

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

[0022] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0023] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application. Example 1

[0024] Reference Figure 1-Figure 3 This embodiment provides a method for monitoring radish planting that is resistant to bolting and insect pests, comprising the following steps: Acquire the radish plant image in the target area, and identify whether there is a radish bolting feature in the radish plant image; If there are radish bolting characteristics, generate the first warning information; Obtaining a radish leaf image of a target area, and identifying whether there are pest features in the radish leaf image; If there are pest characteristics, a second warning message is generated; The first warning information and / or the second warning information is sent to the backend terminal.

[0025] In this embodiment, based on machine vision recognition technology, by obtaining the image of the radish plant, it is determined whether there are radish bolting features. If there are radish bolting features, a first warning message can be generated and sent to the background terminal. By obtaining the image of the radish leaf, it is determined whether there are pest features. If there are pest features, a second warning message can be generated and sent to the background terminal, thereby realizing unattended monitoring of the early bolting and pest status during the radish growth process, and promptly notifying the management personnel to handle it. The use of machine vision recognition can improve recognition accuracy and reduce human errors, which is conducive to the cultivation of more high-quality radishes that are resistant to bolting and low in pests.

[0026] It should be noted that multiple CCD cameras can be set up here and distributed in corresponding positions. Each CCD camera can monitor multiple radish plants in the corresponding area (i.e., the above-mentioned target area). When image processing software and a communicator are implanted in the CCD camera, the acquired image can be identified and analyzed, and the corresponding first warning information and / or second warning information can be generated through the communicator. The first warning information and the second warning information both contain the coordinate position information of the area to which the radish plants with abnormal conditions (i.e., early bolting or insect infestation) belong, so that the management personnel can promptly and accurately find the radish plants with abnormal conditions and deal with them.

[0027] Since many farmers will experience bolting in the radishes they plant in the spring, the tubers will stop growing after bolting and will not grow larger. The tubers that have already grown will slowly lose water and become hollow, reducing the quality of the radishes. In severe cases, the radishes will become inedible, reducing yields, declining benefits, and even total crop failure. Therefore, it is necessary to detect the early signs of bolting in radishes in time and then take corresponding measures (temperature, light adjustment, etc.) to prevent them. However, since they are currently grown in large quantities in greenhouses, manual observation is a huge workload and has low accuracy.

[0028] Therefore, as an optional implementation manner, the acquiring of the radish plant image in the target area and identifying whether there is a radish bolting feature in the radish plant image includes: Acquire a first image of the radish plant group corresponding to the target area; wherein the first image is an image based on a side perspective of the radish plant group; Obtaining a height characteristic value of the radish plant group corresponding to the first image, and comparing the height characteristic value with a preset height threshold; If the height feature value is less than the height threshold, it is identified that no radish bolting feature exists in the first image.

[0029] In the present embodiment, since the batch planting of radishes is carried out in a greenhouse under the same environmental conditions, the radishes grow at a relatively uniform height. If signs of bolting appear, the stems begin to elongate rapidly and the plants become taller. Therefore, the present embodiment obtains a first image of a radish plant group including multiple radish plants at a side angle, obtains a height feature value, and sets a height threshold, which is the height range of the radishes during normal growth. When it is detected that the height feature value is less than the height threshold, it can be determined that there is no radish bolting phenomenon, and when it is detected that the height feature value is greater than or equal to the height threshold, it can be determined that there is suspected radish bolting phenomenon. The radish bolting characteristics are identified by the height features, which is intuitive and effective and can be quickly identified.

[0030] It should be noted that in order to improve the recognition accuracy, CCD cameras can be set on all four sides of the radish planting area, that is, the first image is obtained from all four sides of the radish planting area and image analysis is performed simultaneously. If the images in at least two directions detect that the height characteristic value is greater than or equal to the height threshold, it can be determined that there is suspected radish bolting phenomenon, thereby improving the detection accuracy and avoiding detection errors.

[0031] As an optional implementation manner, obtaining the height characteristic value of the radish plant group corresponding to the first image and comparing the height characteristic value with a preset height threshold value includes: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a first height value of the highest point based on a first reference level; wherein the first reference level is a horizontal plane where the radish plant and the soil layer meet; The first height value is compared with a preset first height threshold.

[0032] In this embodiment, by identifying the highest point of the outline of the radish plant group and taking the horizontal plane where the radish plant and the soil layer meet as the first reference level, the distance value between the highest point and the first reference level, that is, the first height value H1, can be quickly obtained. Here, the position of the first reference level is fixed, and the first height value H1 can be quickly calculated by only identifying the highest point. The calculation efficiency is high and the recognition can be fast. Then, the first height value is compared with the preset first height threshold. If it is higher than the first height threshold, it can be determined that there is suspected radish bolting.

[0033] As an optional implementation manner, obtaining the height characteristic value of the radish plant group corresponding to the first image and comparing the height characteristic value with a preset height threshold value includes: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a second height value of the highest point based on a second reference level; wherein the second reference level is a horizontal plane where the current average height of the radish plant group is located; The second height value is compared with a preset second height threshold.

[0034] In this embodiment, after the highest point of the outline of the radish plant group is identified, the distance value between the highest point and the second reference level is calculated as the second height value H2, where the second reference level is the horizontal plane where the average height of the current growth state of the radish plant group is located. Due to the influence of radish type, growth cycle, growth conditions, etc., the timing of early bolting of radishes is also uncertain. Therefore, the average height of the current growth state of the radish plant group is not fixed. Therefore, the second height value H2 is a relative value. If bolting occurs, the bolting radish plant will be higher than the normal plant. Therefore, the bolting feature can be effectively characterized by calculating the distance value between the highest point and the second reference level as the second height value H2. Here, based on the second reference level as a reference plane, it can adapt to the changes in radish type and growth cycle for accurate identification, which is more referenceable. When the second height value is greater than the second height threshold, it can be determined that the radish bolting phenomenon is suspected to exist. Here, the second height threshold is the difference in distance between the bolting radish plant and the normal plant.

[0035] As an optional implementation, if the height characteristic value is greater than or equal to the height threshold, the method further includes: Acquire a second image of the radish plant corresponding to the target area; wherein the second image is an image based on a top-down perspective of the radish plant; Acquire the appearance contour features of the corresponding radish plant in the second image; Extract the central area features of the shape contour features; Identify whether there is an abnormal grayscale value in the central area feature; the abnormal grayscale value is the grayscale value corresponding to the color of the petals of the radish bolting and flowering; If there is an abnormal grayscale value, it is identified that there is a radish bolting feature in the second image.

[0036] In this embodiment, when it is detected that the height characteristic value is greater than or equal to the height threshold, that is, when the radish bolting phenomenon is suspected, it may be due to the presence of weeds that are taller than the radish plant, resulting in inaccurate detection results of the first image. Therefore, further detection is performed here. By acquiring the shape contour features of the radish plant from a top-down perspective, the shape features of the entire radish plant can be intuitively identified. Since radish bolting occurs in the center of the entire radish plant, the central area features of the shape contour features are extracted here, and then the image is magnified and grayscale processed. Since radish bolting will bloom, the color of the petals is obviously different from the normal color of the leaves of the radish plant, and there is a large difference in the grayscale values ​​of the two. Therefore, here, by detecting whether there is an abnormal grayscale value corresponding to bolting and flowering in the central area features, it can be further confirmed whether there is a radish bolting feature, thereby improving the detection accuracy of the radish bolting phenomenon.

[0037] It should be noted that, in the above-mentioned implementation, by first obtaining the height feature value of the first image, when the height feature value satisfies the condition of being greater than or equal to the height threshold, the second image is then obtained and it is identified whether there is an abnormal grayscale value in the central area feature. Since the first image is obtained at a side perspective, only a side camera is required to obtain one image, while the second image is obtained at a top-down perspective, and multiple cameras on the top of the shed need to run simultaneously to obtain multiple images, so as to obtain images of all radish plants in the shed. If no bolting feature is identified, there is no need to obtain and analyze the second image, thereby reducing the amount of calculation and the camera consumption. Therefore, when identifying the bolting phenomenon based on machine vision, the sequence of identification steps is reasonably planned, which not only ensures the recognition accuracy but also reduces the recognition operation amount, thereby improving the recognition efficiency.

[0038] As an optional implementation, if there is no abnormal gray value, the method further includes: Identify whether there are abnormal contour features in the central area features; wherein the abnormal contour features are the appearance features of the buds or petals of the radish; If there is an abnormal contour feature, it is identified that there is a radish bolting feature in the second image.

[0039] In this embodiment, due to the difference in radish type and bolting timing, the color of the petals after bolting is not obvious (slightly blue), or the bolting of the bud-shaped radish is not obvious. At this time, there may be missed detections based only on the identification of abnormal grayscale values. Therefore, when the present embodiment identifies that there is no abnormal grayscale value, further detection is performed. By identifying whether there are abnormal contour features with flower bud appearance features or petal appearance features in the central area features, the radish bolting features can be further judged, thereby improving the recognition accuracy of the radish bolting features.

[0040] It should be noted that the above-mentioned implementation method first identifies the abnormal grayscale value, and then further identifies the abnormal contour feature after the abnormal grayscale value is not identified. If the abnormal grayscale value is identified, there is no need for the abnormal contour feature. Moreover, since the abnormal grayscale value corresponding to the petal color can be quickly identified, the feature recognition order is reasonably planned, the recognition calculation amount is reduced, and the recognition efficiency is improved.

[0041] As an optional implementation manner, the acquiring of the radish leaf image of the target area and identifying whether there are pest features in the radish leaf image include: Acquire a radish leaf image of a target area; wherein the radish leaf image is an image based on a top-down perspective of a radish plant; Identify the abnormal shadow area in the radish leaf image; the abnormal shadow area is the area covered by the radish leaves where pests and diseases attach; Compare the abnormal shadow area with a preset area threshold; If the abnormal shadow area is larger than the area threshold, it is recognized that there are pest features in the radish leaf image.

[0042] In this embodiment, when it is necessary to identify pest characteristics, the abnormal shadow area of ​​the acquired radish leaf image can be identified. The abnormal shadow area here mainly refers to the coverage area where small but large-scale pests and diseases such as whiteflies and aphids are attached. Since the color and appearance of these pests and diseases themselves are somewhat different from those of radish leaves, the corresponding abnormal shadows can be clearly identified after processing the radish leaf image. In order to ensure the recognition accuracy and avoid misidentifying abnormal shadows caused by non-pests (such as soil attachment, etc.), an area threshold is set here. When the abnormal shadow area is greater than the area threshold, it can be determined that there are pest characteristics in the radish leaf image, thereby realizing the recognition of pest characteristics with high recognition accuracy.

[0043] As an optional implementation manner, the step of acquiring the radish leaf image of the target area and identifying whether there are pest features in the radish leaf image further includes: Obtaining the leaf missing area in the radish leaf image; wherein the leaf missing area is the area of ​​the missing portion of the radish leaf after being infested by pests and diseases; Obtaining a leaf missing rate; wherein the leaf missing rate is a ratio of a leaf missing area to a leaf complete area; comparing the leaf missing rate with a preset missing rate threshold; If the leaf missing rate is greater than the missing rate threshold, it is recognized that there are pest features in the radish leaf image.

[0044] In this embodiment, since cabbage loopers are also one of the common pest types, cabbage loopers are generally small in number and their color is close to the leaves. If the pest characteristics are identified only in accordance with the above-mentioned method of identifying the abnormal shadow area, it is easy to miss the identification of pest characteristics such as cabbage loopers. Cabbage loopers will erode the leaves, forming a number of irregular missing holes. Therefore, this embodiment calculates the leaf missing area in the radish leaf image. The leaf missing area is calculated based on the complete leaves for comparison, so as to calculate the leaf missing rate. When the leaf missing rate is greater than the missing rate threshold, it indicates that there are pest characteristics in the radish leaf image, and the pest erosion seriously affects the quality of the radish, so that the management personnel are notified in time for processing. This embodiment further improves the accuracy of identifying pest characteristics and can identify multiple types of pests.

[0045] It should be noted that the leaf missing rate here is generally calculated based on each individual leaf. When calculating the missing rate of a single leaf, if a missing leaf is detected, first identify and extract the outer edge contour features of the missing leaf, and then use the existing image restoration algorithm to fill in the missing part of the missing leaf to restore the missing leaf to a complete leaf image. The filled area of ​​the missing part is the missing area of ​​the leaf, and finally the ratio of the missing area of ​​the leaf to the complete area of ​​the leaf after restoration can be calculated. This calculation method requires the calculation of multiple leaf missing rates. Although the amount of calculation is large, the recognition accuracy is high, and it can be used for situations where pests and diseases are concentrated on the same leaf. Example 2

[0046] Based on the same inventive concept as the above-mentioned embodiment, this embodiment provides a radish planting monitoring system that is resistant to bolting and pests, including: A bolting feature recognition module is used to obtain a radish plant image in a target area and identify whether there is a radish bolting feature in the radish plant image; A first information generating module, configured to generate a first warning message if the radish bolting feature exists; The pest feature recognition module is used to obtain the radish leaf image of the target area and identify whether there are pest features in the radish leaf image; A second information generating module, used to generate second warning information if there are pest characteristics; The information sending module is used to send the first warning information and / or the second warning information to the background terminal.

[0047] The relevant explanations and examples of each module in the device of this embodiment can refer to the method of the aforementioned embodiment, and will not be repeated here. Example 3

[0048] Based on the same inventive concept as the above-mentioned embodiment, this embodiment provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned method. Example 4

[0049] Based on the same inventive concept as the aforementioned embodiment, this embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the aforementioned method.

[0050] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for monitoring radish planting with resistance to bolting and insect pests, characterized in that: The following steps are involved: Acquire a radish plant image in a target area, and identify whether there is a radish bolting feature in the radish plant image; If the radish bolting feature exists, generating a first warning message; Acquire a radish leaf image of a target area, and identify whether there are pest features in the radish leaf image; If the pest characteristics exist, generating a second warning message; The first warning information and / or the second warning information are sent to a background terminal.

2. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in claim 1, characterized in that: The acquiring of the radish plant image in the target area and identifying whether there is a radish bolting feature in the radish plant image includes: Acquire a first image of a group of radish plants corresponding to a target area; wherein the first image is an image based on a side perspective of the group of radish plants; Acquire a height characteristic value of the radish plant group corresponding to the first image, and compare the height characteristic value with a preset height threshold; If the height feature value is less than the height threshold, it is identified that no radish bolting feature exists in the first image.

3. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in claim 2, characterized in that: The step of obtaining a height characteristic value of the radish plant group corresponding to the first image and comparing the height characteristic value with a preset height threshold comprises: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a first height value of the highest point based on a first reference level; wherein the first reference level is a horizontal plane where the radish plant and the soil layer meet; The first height value is compared with a preset first height threshold.

4. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in claim 2, characterized in that: The step of obtaining a height characteristic value of the radish plant group corresponding to the first image and comparing the height characteristic value with a preset height threshold comprises: Obtaining the highest point of the outline corresponding to the radish plant group in the first image; Obtaining a second height value of the highest point based on a second reference level; wherein the second reference level is a horizontal plane where the current average height of the radish plant group is located; The second height value is compared with a preset second height threshold.

5. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in any one of claims 2 to 4, characterized in that: If the height characteristic value is greater than or equal to the height threshold, the method further includes: Acquire a second image of the radish plant corresponding to the target area; wherein the second image is an image based on a top-down perspective of the radish plant; Acquire the appearance contour features of the radish plant corresponding to the second image; Extracting the central area features of the outline features; Identify whether there is an abnormal grayscale value in the central area feature; wherein the abnormal grayscale value is the grayscale value corresponding to the color of the petals of the radish bolting and flowering; If the abnormal grayscale value exists, it is identified that a radish bolting feature exists in the second image.

6. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in claim 5, characterized in that: If the abnormal gray value does not exist, the method further includes: Identify whether there is an abnormal contour feature in the central area feature; wherein the abnormal contour feature is a bud shape feature or a petal shape feature of a radish bolting; If the abnormal contour feature exists, it is identified that a radish bolting feature exists in the second image.

7. The method for monitoring radish planting with resistance to bolting and insect pests as claimed in claim 1, characterized in that: The step of acquiring a radish leaf image of a target area and identifying whether there are pest features in the radish leaf image includes: Acquire a radish leaf image of a target area; wherein the radish leaf image is an image based on a top-down perspective of a radish plant; Identify the abnormal shadow area in the radish leaf image; wherein the abnormal shadow area is the coverage area of ​​the radish leaf attached by pests and diseases; Comparing the abnormal shadow area with a preset area threshold; If the abnormal shadow area is greater than the area threshold, it is identified that there are pest features in the radish leaf image.

8. A method for monitoring radish planting that is resistant to bolting and insect pests as claimed in claim 7, characterized in that: The step of acquiring the radish leaf image of the target area and identifying whether there are pest features in the radish leaf image further includes: Obtaining the leaf missing area in the radish leaf image; wherein the leaf missing area is the area of ​​the missing portion of the radish leaf after being infested by pests and diseases; Obtaining a leaf missing rate; wherein the leaf missing rate is a ratio of the leaf missing area to the leaf complete area; comparing the leaf missing rate with a preset missing rate threshold; If the leaf missing rate is greater than the missing rate threshold, it is identified that there are pest features in the radish leaf image.

9. A radish planting monitoring system that is resistant to bolting and insect pests, characterized in that: include: A bolting feature recognition module is used to obtain a radish plant image in a target area and identify whether there is a radish bolting feature in the radish plant image; A first information generating module, configured to generate first warning information if the radish bolting feature exists; An insect pest feature recognition module is used to obtain a radish leaf image of a target area and identify whether there are insect pest features in the radish leaf image; A second information generating module, used for generating second warning information if the pest characteristics exist; An information sending module is used to send the first warning information and / or the second warning information to a background terminal.

10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 8.

Images