Intelligent garden management system based on image processing

Abstract

The invention relates to the technical field of image processing, in particular to an intelligent garden management system based on image processing, which comprises an image data acquisition module for acquiring garden area images and plant leaf images in a monitoring period and further acquiring garden plant positioning coordinates, and a real-time data acquisition module for acquiring garden monitoring data and displaying the garden monitoring data. The first image analysis module is used for analyzing the growth deviation state of each garden plant, the garden environment analysis module is used for adjusting the analysis process of the growth deviation state of each garden plant, the second image analysis module is used for analyzing the leaf color state of each garden plant, and the transpiration analysis module is used for analyzing the leaf color state of each garden plant. The transpiration abnormality analysis module is used for analyzing transpiration abnormality of each garden plant, the health state analysis module is used for analyzing the health state of each garden plant, and the garden plant management module is used for generating a management scheme of each garden plant. According to the invention, the garden management efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an intelligent garden management system based on image processing. Background Art

[0002] With the acceleration of urbanization, the role of landscaping in beautifying the environment and improving the quality of life of residents has become increasingly important. However, traditional garden management methods have problems such as inefficiency and waste of resources. In recent years, the development of computer vision technology and the Internet of Things has provided new solutions for intelligent garden management. Although existing systems can identify plant diseases and pests, they lack comprehensive solutions and are difficult to cope with complex and changing actual needs. Therefore, there is an urgent need for a more efficient, accurate and easy-to-use smart garden management system.

[0003] Chinese patent publication number CN118470578A discloses a method for refined garden management and automatic detection, which relates to the field of image processing technology. The method specifically includes: using drone equipment to inspect the garden, and collecting inspection videos to obtain a key frame image set; inputting the key frame image set into a plant category detection network to obtain plant categories and plant areas in each key frame image; segmenting the plant area in each key frame image to obtain an upper plant area image and a lower plant area image, and inputting them into a leaf segmentation model respectively to obtain leaf position information of the upper plant area image and leaf position information of the lower plant area image; performing water shortage detection based on the leaf position information of the upper plant area image and the leaf position information of the lower plant area image, and generating maintenance information of each plant; it can be seen that the invention only monitors and analyzes plant leaves to determine whether the plants are water-deficient, and does not analyze the growth deviation of branches and leaves of garden plants, resulting in low garden management efficiency. Summary of the invention

[0004] The object of the present invention is to provide a smart garden management system based on image processing to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An intelligent garden management system based on image processing, characterized by comprising: An image data acquisition module is used to acquire images of the garden area and plant leaves within the monitoring period, and is also used to acquire the positioning coordinates of the garden plants; Real-time data collection module, used to collect garden monitoring data within the monitoring period; A first image analysis module is used to analyze the growth deviation state of each garden plant according to the garden area image; The garden environment analysis module is used to adjust the analysis process of the growth deviation state of each garden plant according to the garden monitoring data; The second image analysis module is used to analyze the leaf color status of each garden plant according to the plant leaf image; A transpiration analysis module is used to analyze the abnormality of transpiration of each garden plant according to the transpiration intensity of each garden plant; A health status analysis module is used to analyze the health status of each garden plant based on the leaf color status analysis results and transpiration abnormality analysis results of each garden plant; The garden plant management module is used to generate a management plan for each garden plant in the next monitoring period based on the growth deviation status analysis results and health status analysis results of each garden plant.

[0006] Furthermore, the first image analysis module includes an image processing unit, which is used to cluster the garden area image according to the grayscale values ​​of the pixels of the garden area image to obtain each first cluster D1(i); The image processing unit performs secondary clustering on each first cluster D1(i) according to the coordinates of the pixel points in each first cluster to obtain each plant cluster D2(j); The image processing unit is used to calculate the center coordinates DZ2(j) of each plant in the monitoring period according to each plant cluster D2(j).

[0007] Furthermore, the first image analysis module also includes an image recognition unit, which is used to calculate the matching degree α(j, k) between the plant center coordinates and the garden plant positioning coordinates, and compare α(j, k) with the first preset matching degree A1, and identify the garden plant according to the comparison result, and the recognition result includes recognition success and recognition failure, and when the recognition is successful, the growth offset state of the kth garden plant is analyzed, and the analysis results of the growth offset state include normal and abnormal.

[0008] Furthermore, the garden environment analysis module is provided with a density analysis unit, which is used to compare the garden plant density ρ with each preset garden density to determine the garden plant density state, the plant density state includes normal, low and high, and when the garden plant density is low, the second preset matching degree is adjusted to A2', and when the garden plant density is high, the second preset matching degree is adjusted to A2".

[0009] Furthermore, the garden environment analysis module is also provided with a climate analysis unit, which is used to calculate the growth equivalence index β based on the garden monitoring data within the monitoring period, and compare the growth equivalence index β with the preset equivalence index B to determine the abnormality of plant growth rate, the abnormality of plant growth rate includes normal and abnormal, and when the abnormality of plant growth rate is abnormal, the second preset garden plant density is optimized to P2'.

[0010] Furthermore, the second image analysis module is used to extract the boundary curve of the plant leaf image and calculate the average gray value Gray (k, z) of each leaf pixel, Gray (k, z) represents the average gray value of the zth leaf pixel in the plant leaf image of the kth garden plant; The second image processing module counts the average pixel value PJ(k) of the leaves of each garden plant, and compares the average pixel value PJ(k) of the leaves of each garden plant with the preset average grayscale value GRAY of the pixels to determine the leaf color status of each garden plant. The leaf color status of each garden plant includes normal and abnormal.

[0011] Furthermore, the transpiration analysis module is used to compare the transpiration intensity et(k) of each garden plant during the monitoring period with each preset transpiration intensity ET(k) to determine the transpiration abnormality of each garden plant, and the transpiration abnormality of each garden plant includes normal and abnormal.

[0012] Further, the health status analysis module is used to analyze the health status of each garden plant according to the leaf color status analysis results and transpiration abnormality analysis results of each garden plant during the monitoring period: if the leaf color status of the garden plant is normal and the transpiration is normal, the health status analysis module determines that the health status of the garden plant is normal during the monitoring period; If the leaf color state of the garden plant is abnormal and the transpiration is normal, the health state analysis module determines that the health state of the garden plant is abnormal soil condition; If the color state of the leaves of the garden plant is normal and the transpiration is abnormal, the health state analysis module determines that the health state of the garden plant is abnormal water shortage; If the color state of the leaves of the garden plant is abnormal and the transpiration is abnormal, the health state analysis module determines that the health state of the garden plant is abnormal water shortage.

[0013] Furthermore, the garden plant management module includes a solution generation unit, which is used to generate a management solution for each garden plant according to the growth deviation state analysis result and health state analysis result of each garden plant within the monitoring period: If the growth deviation state of the garden plant is normal and the health state of the garden plant is normal, the solution generation unit does not change the maintenance process of the garden plant in the next detection cycle; if the health state of the garden plant is abnormal soil conditions, the solution generation unit sends a fertilizer shortage alarm to the user; if the health state of the garden plant is abnormal water shortage, the solution generation unit sets the irrigation cycle of the garden plant in the next monitoring cycle to ZT1(k), sets ZT1(k)=ZT(k)×{1-[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, ZT(k) represents the irrigation cycle of the kth garden plant in the current monitoring cycle, and sets the irrigation amount of the garden plant in the next monitoring cycle to LT1(k), sets LT1(k)=LT(k)×exp{[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, LT(k) represents the irrigation amount of the kth garden plant in the current monitoring cycle; If the growth deviation state of the garden plant is abnormal, the solution generating unit sends a pruning suggestion for the garden plant to the user.

[0014] Furthermore, the garden plant management module also includes a machine learning unit, which is used to count the number of garden fertilizer deficiency alarms and pruning alarms pn within the management cycle, and compare pn with the preset alarm number PN, and when pn exceeds the preset alarm number PN, the average grayscale value of the preset pixel points in the next management cycle is corrected to GRAY'.

[0015] Compared with the prior art, the beneficial effects of the present invention are: through image processing of the entire garden area, it is determined whether the growth of plants in the garden deviates from the set area; through analysis of the leaf color status and transpiration intensity abnormalities of the garden plants, the health status of each garden plant is analyzed, and efficient judgment of the health status of a single garden plant is achieved. Then, through comprehensive analysis of the health status and growth deviation status, the management plan for the next management cycle is determined, thereby effectively improving the efficiency of garden management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of the structure of the smart garden management system based on image processing in this embodiment.

[0018] Figure 2FIG. 4 is a schematic diagram of the structure of the first image analysis module of this embodiment.

[0019] Figure 3 Schematic diagram of the structure of the garden environment analysis module in this embodiment.

[0020] Figure 4 This is a schematic diagram of the structure of the garden plant management module of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] Specifically, the image processing-based smart garden management system described in this embodiment is applied to a garden real-time monitoring and control platform to perform intelligent management of the garden; the garden real-time monitoring and control platform is composed of various monitoring devices and data processing equipment, the monitoring equipment specifically includes unmanned cameras and intelligent sensors, the data processing equipment is a server, and the plants in the garden are mainly trees; the garden described in this embodiment is an ornamental small and medium-sized garden in a humid or tropical climate.

[0024] See also Figure 1 As shown, it is a structural diagram of the smart garden management system based on image processing described in this embodiment, including: The image data acquisition module is used to collect garden area images and plant leaf images within the monitoring period, and is also used to collect garden plant positioning coordinates; the garden area image is an RGB image, and the plant leaf image is a grayscale image; the garden plant positioning coordinates are the position coordinates of the vegetation planted in the garden; the garden area image described in this embodiment is collected by an unmanned camera in the air to take images of all areas of the garden, and the images of all areas of the garden are spliced ​​and combined into a garden area image, and the garden area image is a rectangular RGB image; it can be understood that when the image is taken by the unmanned camera in this embodiment, the shooting height is unified, and the shooting height is set by the user, and this embodiment does not limit it; this embodiment uses any horizontal direction of the garden area image as the horizontal axis of the coordinate, any vertical direction as the vertical axis of the coordinate, and any image vertex as the coordinate origin to establish a plane rectangular coordinate system, and its garden vegetation positioning data is the coordinate point in the plane rectangular coordinate system, and the format of the coordinate point is (X, Y).

[0025] Specifically, the process of collecting images of garden areas within the monitoring period in this embodiment is periodic collection according to the monitoring period. This embodiment does not specifically limit the value of the duration of the monitoring period. Technical personnel in this field can set it freely as long as the value requirement of the duration of the monitoring period is met. In this embodiment, the duration of the monitoring period is 2 days.

[0026] The real-time data acquisition module is used to collect garden monitoring data within the monitoring period; the garden monitoring data includes garden plant density, garden temperature, garden soil moisture, garden carbon dioxide concentration and transpiration intensity of garden plants.

[0027] Specifically, in this embodiment, the method for obtaining the garden monitoring data is not specifically limited, and technical personnel in this field can freely set it as long as the method for obtaining the garden monitoring data is satisfied. For example, in this embodiment, the garden plant density is collected through a server, the garden temperature is obtained through a temperature sensor, the garden soil temperature is obtained through a temperature sensor, and the garden carbon dioxide concentration is obtained through a carbon dioxide concentration monitoring instrument.

[0028] See Continue Figure 1 As shown, the system also includes a first image analysis module, which is connected to the image data acquisition module. The first image analysis module is used to identify garden plants based on the garden area images within a monitoring period, and analyze the growth offset status of each garden plant based on the identification results of the garden plants.

[0029] See also Figure 2 As shown, the first image analysis module includes an image processing unit, which is used to analyze the plant center coordinates of each garden plant according to the garden area image; Clustering the garden area image once based on the grayscale values ​​of the pixels in the garden area image to obtain first clusters D1(i); The image processing unit performs secondary clustering on each first cluster D1(i) according to the coordinates of the pixel points in each first cluster to obtain each plant cluster D2(j); The image processing unit is used to calculate the center coordinates DZ2(j) of each plant in the monitoring period according to each plant cluster D2(j), and set ; ; ; Among them, Xj represents the horizontal coordinate in the j-th plant cluster, Yj represents the vertical coordinate in the j-th plant cluster, jn represents the n-th pixel in the j-th plant cluster, y(jn) represents the vertical coordinate of the n-th pixel in the j-th plant cluster, x(jn) represents the horizontal coordinate of the n-th pixel in the j-th plant cluster, and jN represents the number of pixels in the j-th plant cluster. By clustering the garden area image, the garden plants in the area image are divided, and then the growth center coordinates of each garden plant (the center coordinates of each plant DZ2(j)) are confirmed, so as to realize efficient and accurate positioning of each plant in the garden area image.

[0030] It can be understood that the purpose of the first clustering in this embodiment is to distinguish the pixel points of plants in the garden area image from the pixel points of the plant edges, and it is impossible to distinguish one plant from another; the purpose of the second clustering is to distinguish plants from plants based on the first clustering; at the same time, the clustering process described in this embodiment is K-means clustering, and its specific process is disclosed in the prior art and will not be repeated in this embodiment.

[0031] Please continue reading Figure 2 As shown, the first image analysis module also includes an image recognition unit, which is connected to the image processing unit, and is used to identify the garden plants according to the center coordinates of each plant and the positioning coordinates of the garden plants, and analyze the growth offset state of each garden plant according to the recognition result to distinguish the offset state of the center coordinates of each plant from the position when it was planted; The image recognition unit is used to calculate the matching degree α(j, k) between the plant center coordinates and the garden plant positioning coordinates, and set α(j, k)=|DZ2(j)-ZB(k)|; wherein ZB(k) represents the positioning coordinates of the kth garden plant; The image recognition unit is used to compare α(j,k) with the first preset matching degree A1, and identify the garden plant according to the comparison result: when α(j,k)<A1, the image recognition unit determines that the recognition of the center coordinates of the jth plant and the positioning coordinates of the kth garden plant is successful. At this time, if α(j,k)<A2, the image recognition unit determines that the growth offset state of the kth garden plant is normal; if α(j,k)≥A2, the image recognition unit determines that the growth offset state of the kth garden plant is abnormal; when α(j,k)≥A1, the image recognition unit determines that the recognition of the center coordinates of the jth plant and the positioning coordinates of the kth garden plant fails; wherein A2 is the second preset matching degree, A2<A1; by identifying the center coordinates of each plant and the positioning coordinates of the garden plant, the recognition and matching of the plant in the image and the position at the time of planting is realized, and then by analyzing the growth offset state, it is realized to accurately judge whether the plant growth is offset from the position at the time of planting, thereby improving the accuracy of the analysis of the plant pruning suggestion.

[0032] Specifically, this embodiment does not impose any specific limitation on the values ​​of the first preset matching degree A1 and the second preset matching degree A2. Those skilled in the art can set them freely as long as the value requirements of the first preset matching degree A1 and the second preset matching degree A2 are met. In this embodiment, the first preset matching degree A1 is set to 0.6m, and the second preset matching degree A2 is set to 0.3m; it can be understood that the calculation process of "|DZ2(j)-ZB(k)|" in this embodiment is to calculate the distance between the coordinate "DZ2(j)" and the coordinate "ZB(k)".

[0033] See also Figure 3 As shown, the system also includes a garden environment analysis module, which is connected to the first image analysis module. The garden environment analysis module is used to analyze the density status of garden plants according to the garden monitoring data within the monitoring period, and adjust the analysis process of the growth offset status of each garden plant according to the analysis results.

[0034] Please continue reading Figure 2As shown, the garden environment analysis module is provided with a density analysis unit, which is used to compare the garden plant density ρ with each preset garden density, and adjust the analysis process of the growth offset state of each garden plant according to the comparison result to control the growth offset state analysis error caused by the garden density: if ρ<P1, the density analysis unit determines that the garden plant density is low, and adjusts the second preset matching degree to A2', setting A2'=A2×[1-(P1-ρ) / P1]; if P1≤ρ<P2, the density analysis unit determines that the garden plant density is normal and does not make any adjustment; if ρ≥P2, the density analysis unit determines that the garden plant density is normal. The plant density is high, and the second preset matching degree is adjusted to A2", setting A2"=A2×[1+(ρ-P2) / P2]; wherein P1 is the first preset garden plant density, P2 is the second preset garden plant density, and P1<P2; by comparing and analyzing the garden plant density, and adjusting the analysis process of the growth offset state of each garden plant according to the analysis results, so as to numerically control the phenomenon that "when the garden plant density is high, a slight deviation in plant growth will lead to restricted growth of other plants; when the garden plant density is low, a slight deviation in plant growth has little effect on the growth of other plants", thereby improving the accuracy of the analysis of plant pruning suggestions.

[0035] Specifically, this embodiment does not specifically limit the values ​​of the first preset garden plant density P1 and the second preset garden plant density P2. Those skilled in the art can set them freely as long as the value requirements of the first preset garden plant density P1 and the second preset garden plant density P2 are met. In this embodiment, the first preset garden plant density P1 is set to 0.1 per square meter, and the second preset garden plant density P2 is set to 1 per square meter.

[0036] Please continue reading Figure 3 As shown, the garden environment analysis module is further provided with a climate analysis unit, which is connected to the density analysis unit, and the climate analysis unit is used to analyze the abnormality of plant growth rate according to the garden monitoring data within the monitoring period, and optimize the adjustment process of the growth deviation state according to the abnormality analysis result of the plant growth rate; The climate analysis unit calculates the growth equivalent index β according to the garden monitoring data within the monitoring period, and sets β=(tT) / T×s×[ρ(CO2)-P(CO2)] / P(CO2); wherein t is the garden temperature, s is the garden soil moisture, ρ(CO2) is the garden carbon dioxide concentration, T is the preset garden growth temperature, and P(CO2) is the preset carbon dioxide concentration; The climate analysis unit compares the growth equivalence index β with the preset equivalence index B, analyzes the abnormality of the plant growth rate according to the comparison result, and optimizes the adjustment process of the growth offset state according to the analysis result of the abnormality of the plant growth rate: if 0<β<B, the climate analysis unit determines that the plant growth rate is normal during the monitoring period; if β≥B, the climate analysis unit determines that the plant growth rate is abnormal during the monitoring period, and optimizes the second preset garden plant density to P2', setting P2'=P2×exp{-(β-B) / B}; by calculating the growth equivalence index of the area where the garden is located, it is determined whether the growth of the garden plants exceeds expectations, and because the garden described in this embodiment is in a humid or tropical climate, its growth rate particularly affects the judgment result of the garden plant density state, and the accurate analysis of the abnormality of the plant growth rate improves the accuracy of the analysis of the plant pruning suggestion.

[0037] Specifically, this embodiment does not make any specific limitation on the value of the preset equivalence index B. Those skilled in the art can set it freely as long as the value requirement of the preset equivalence index B is met. In this embodiment, the preset equivalence index B can be set to 0.5; at the same time, the values ​​of the preset garden growth temperature T and the preset carbon dioxide concentration P (CO2) are determined by the optimal growth parameters of the garden plants. In this embodiment, the values ​​of the preset garden growth temperature T and the preset carbon dioxide concentration P (CO2) are obtained by user interactive input.

[0038] Please continue reading Figure 1 As shown, the system is further provided with a second image analysis module, which is connected to the image data acquisition module, and the second image analysis module is used to analyze the leaf color status of each garden plant according to the plant leaf image, so as to realize the judgment of the leaf health of the garden plant based on the image; The second image processing module extracts the boundary curve of the plant leaf image and calculates the average grayscale value Gray(k,z) of each leaf pixel, where Gray(k,z) represents the average grayscale value of the zth leaf pixel in the plant leaf image of the kth garden plant; The second image processing module counts the average pixel value PJ(k) of the leaves of each garden plant and sets ; Wherein, PJ(k) represents the average grayscale value of the leaf pixels of the kth garden plant, and Z is the number of leaves in the plant leaf image; The second image processing module is used to compare the average pixel value PJ(k) of the leaves of each garden plant with the preset average pixel grayscale value GRAY, and analyze the leaf color status of each garden plant according to the comparison result: if PJ(k)<GRAY, the second image processing module determines that the leaf color status of the kth garden plant is abnormal; if PJ(k)≥GRAY, the second image processing module determines that the leaf color status of the kth garden plant is normal; by judging the color of the plant leaf image, accurate analysis of the leaf color status of each garden plant is achieved, thereby improving the accurate judgment of the health status of the garden plants.

[0039] Specifically, this embodiment does not make any specific limitation on the value of the preset pixel average grayscale value GRAY. Those skilled in the art can set it freely as long as the value requirement of the preset pixel average grayscale value GRAY is met. In this embodiment, the value of the preset pixel average grayscale value GRAY is 150, and the leaves of the plant leaf image with a grayscale value exceeding 150 in this embodiment appear to lack water; it can be understood that the process of "extracting the boundary curve of the plant leaf image" in this embodiment is to find the boundary of the object through the Canny edge detection operator. This technology is an existing public technology, and those skilled in the art do not make any specific limitation on its implementation process; it can be understood that the plant leaf image described in this embodiment contains multiple leaf images on the same plant.

[0040] Please continue reading Figure 1 As shown, the system is also provided with a transpiration analysis module, which is connected to the real-time data acquisition module. The transpiration analysis module is used to compare the transpiration intensity et(k) of each garden plant in the monitoring period with each preset transpiration intensity ET(k), and analyze the abnormality of the transpiration of each garden plant according to the comparison result: if et(k)<ET(k), the transpiration analysis unit determines that the transpiration of the kth garden plant is normal; if et(k)≥ET(k), the transpiration analysis unit determines that the transpiration of the kth garden plant is abnormal; by analyzing the transpiration intensity of each garden plant, it is possible to judge whether the garden plant lacks water in another dimension, thereby improving the accurate judgment of the health status of each garden plant.

[0041] Specifically, this embodiment does not impose any specific restrictions on the values ​​of each preset transpiration intensity ET(k), and those skilled in the art can set them freely as long as the value requirements of the preset transpiration intensity ET(k) are met. In this embodiment, the value of each preset transpiration intensity ET(k) is the average value of the historical transpiration intensity of each garden plant; the average value of the historical transpiration intensity of each garden plant is obtained through a server, and the historical transpiration intensity of each garden plant can be measured by a portable photosynthetic meter.

[0042] Please continue reading Figure 1 As shown, the system further includes a health status analysis module, which is connected to the second image processing module and the transpiration analysis module, and is used to analyze the health status of each garden plant according to the leaf color status analysis results and transpiration abnormality analysis results of each garden plant within the monitoring period, so as to determine a comprehensive judgment on the health status of each garden plant: if the leaf color status of the garden plant is normal and the transpiration is normal, the health status analysis module determines that the health status of the garden plant within the monitoring period is normal; If the leaf color state of the garden plant is abnormal and the transpiration is normal, the health state analysis module determines that the health state of the garden plant is abnormal soil condition; If the transpiration of the garden plant is abnormal, the health status analysis module determines that the health status of the garden plant is abnormal water shortage; the health status analysis module comprehensively analyzes the health status of each garden plant based on the leaf color status and transpiration abnormality to determine the health status of each garden plant, and points out the reason when the health status is abnormal, thereby improving the accurate judgment of the health status of each garden plant, and further improving the accuracy of irrigation analysis of garden plants.

[0043] Please continue reading Figure 1 As shown, the system also includes a garden plant management module, which is connected to the health status analysis module and the first image analysis module. The garden plant management module is used to generate a management plan for each garden plant in the next monitoring period according to the growth offset state analysis results and the health status analysis results of each garden plant in the monitoring period, and output the management plan for each garden plant in the next monitoring period to the user.

[0044] See also Figure 4 As shown, the garden plant management module includes a solution generation unit, which is used to generate a management solution for each garden plant according to the growth deviation state analysis result and health state analysis result of each garden plant within the monitoring period: If the growth deviation state of the garden plant is normal and the health state of the garden plant is normal, the solution generation unit does not change the maintenance process of the garden plant in the next detection cycle; if the health state of the garden plant is abnormal soil conditions, the solution generation unit sends a fertilizer shortage alarm to the user; if the health state of the garden plant is abnormal water shortage, the solution generation unit sets the irrigation cycle of the garden plant in the next monitoring cycle to ZT1(k), sets ZT1(k)=ZT(k)×{1-[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, ZT(k) represents the irrigation cycle of the kth garden plant in the current monitoring cycle, and sets the irrigation amount of the garden plant in the next monitoring cycle to LT1(k), sets LT1(k)=LT(k)×exp{[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, LT(k) represents the irrigation amount of the kth garden plant in the current monitoring cycle; If the growth deviation state of the garden plant is abnormal, the solution generation unit sends a pruning suggestion for the garden plant to the user; through a comprehensive analysis of the growth deviation state analysis results and different health states of each garden plant, efficient management of the garden plants in the garden is achieved.

[0045] It can be understood that, in this embodiment, the irrigation amount LT(k) of the kth garden plant in the current monitoring period and the irrigation period ZT(k) of the kth garden plant in the current monitoring period are obtained through the server.

[0046] Please continue reading Figure 4 As shown, the garden plant management module also includes a plan output unit, which is connected to the plan generation unit. The plan output unit is used to send the management plan of each garden plant to the user.

[0047] Please continue reading Figure 4 As shown, the garden plant management module also includes a machine learning unit, which is connected to the scheme generation unit. The machine learning unit is used to count the number of garden fertilizer deficiency alarms and pruning alarms pn within the management cycle, and compare pn with the preset alarm number PN. The machine learning unit also corrects the analysis process of the leaf color status of each garden plant according to the comparison result: if pn<PN, the machine learning unit determines that the number of alarms within the management cycle is normal and no correction is performed; if pn≥PN, the machine learning unit determines that the number of alarms within the management cycle is abnormal, and corrects the average grayscale value of the preset pixel points in the next management cycle to GRAY', setting GRAY'=GRAY×ln[e+(pn-PN) / PN], where e is the natural logarithm.

[0048] Specifically, this embodiment does not impose any specific limitation on the value of the preset alarm number PN. Those skilled in the art can set it freely as long as the value requirement of the preset alarm number PN is met. In this embodiment, the value of the preset alarm number PN is 10% of the number of plants in the garden.

[0049] It is understandable that this embodiment does not specifically limit the value of the duration of the management cycle, and those skilled in the art can freely set it as long as the value requirement of the duration of the management cycle is met. This embodiment sets the value of the duration of the management cycle to 10 days.

[0050] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A smart garden management system based on image processing, characterized in that: include: An image data acquisition module is used to acquire images of the garden area and plant leaves within the monitoring period, and is also used to acquire the positioning coordinates of the garden plants; Real-time data collection module, used to collect garden monitoring data within the monitoring period; A first image analysis module is used to analyze the growth deviation state of each garden plant according to the garden area image; The garden environment analysis module is used to adjust the analysis process of the growth deviation state of each garden plant according to the garden monitoring data; The second image analysis module is used to analyze the leaf color status of each garden plant according to the plant leaf image; A transpiration analysis module is used to analyze the abnormality of transpiration of each garden plant according to the transpiration intensity of each garden plant; A health status analysis module is used to analyze the health status of each garden plant based on the leaf color status analysis results and transpiration abnormality analysis results of each garden plant; The garden plant management module is used to generate a management plan for each garden plant in the next monitoring period based on the growth deviation status analysis results and health status analysis results of each garden plant.

2. The intelligent garden management system based on image processing according to claim 1 is characterized in that: The first image analysis module includes an image processing unit, which is used to cluster the garden area image according to the grayscale values ​​of the pixels of the garden area image to obtain each first cluster D1(i); The image processing unit performs secondary clustering on each first cluster D1(i) according to the coordinates of the pixel points in each first cluster to obtain each plant cluster D2(j); The image processing unit is used to calculate the center coordinates DZ2(j) of each plant in the monitoring period according to each plant cluster D2(j).

3. The intelligent garden management system based on image processing according to claim 2 is characterized in that: The first image analysis module also includes an image recognition unit, which is used to calculate the matching degree α(j, k) between the plant center coordinates and the garden plant positioning coordinates, and compare α(j, k) with the first preset matching degree A1, and identify the garden plant according to the comparison result, and the recognition result includes recognition success and recognition failure, and when the recognition is successful, the growth offset state of the kth garden plant is analyzed, and the analysis results of the growth offset state include normal and abnormal.

4. The intelligent garden management system based on image processing according to claim 3 is characterized in that: The garden environment analysis module is provided with a density analysis unit, which is used to compare the garden plant density ρ with each preset garden density to determine the garden plant density state, the plant density state includes normal, low and high, and when the garden plant density is low, the second preset matching degree is adjusted to A2', and when the garden plant density is high, the second preset matching degree is adjusted to A2".

5. The intelligent garden management system based on image processing according to claim 4 is characterized in that: The garden environment analysis module is also provided with a climate analysis unit, which is used to calculate the growth equivalence index β based on the garden monitoring data within the monitoring period, and compare the growth equivalence index β with the preset equivalence index B to determine the abnormality of plant growth rate, which includes normal and abnormal. When the abnormality of plant growth rate is abnormal, the second preset garden plant density is optimized to P2'.

6. The intelligent garden management system based on image processing according to claim 5 is characterized in that: The second image analysis module is used to extract the boundary curve of the plant leaf image and calculate the average gray value Gray (k, z) of each leaf pixel, Gray (k, z) represents the average gray value of the zth leaf pixel in the plant leaf image of the kth garden plant; The second image processing module counts the average pixel value PJ(k) of the leaves of each garden plant, and compares the average pixel value PJ(k) of the leaves of each garden plant with the preset average grayscale value GRAY of the pixels to determine the leaf color status of each garden plant. The leaf color status of each garden plant includes normal and abnormal.

7. The intelligent garden management system based on image processing according to claim 6 is characterized in that: The transpiration analysis module is used to compare the transpiration intensity et(k) of each garden plant in the monitoring period with each preset transpiration intensity ET(k) to determine the transpiration abnormality of each garden plant, and the transpiration abnormality of each garden plant includes normal and abnormal.

8. The intelligent garden management system based on image processing according to claim 7 is characterized in that: The health status analysis module is used to analyze the health status of each garden plant according to the leaf color status analysis results and transpiration abnormality analysis results of each garden plant during the monitoring period: if the leaf color status of the garden plant is normal and the transpiration is normal, the health status analysis module determines that the health status of the garden plant is normal during the monitoring period; If the leaf color state of the garden plant is abnormal and the transpiration is normal, the health state analysis module determines that the health state of the garden plant is abnormal soil condition; If the color state of the leaves of the garden plant is normal and the transpiration is abnormal, the health state analysis module determines that the health state of the garden plant is abnormal water shortage; If the color state of the leaves of the garden plant is abnormal and the transpiration is abnormal, the health state analysis module determines that the health state of the garden plant is abnormal water shortage.

9. The intelligent garden management system based on image processing according to claim 8 is characterized in that: The garden plant management module includes a solution generation unit, which is used to generate a management solution for each garden plant according to the growth deviation state analysis results and health state analysis results of each garden plant within the monitoring period: If the growth deviation state of the garden plant is normal and the health state of the garden plant is normal, the solution generation unit does not change the maintenance process of the garden plant in the next detection cycle; if the health state of the garden plant is abnormal soil conditions, the solution generation unit sends a fertilizer shortage alarm to the user; if the health state of the garden plant is abnormal water shortage, the solution generation unit sets the irrigation cycle of the garden plant in the next monitoring cycle to ZT1(k), sets ZT1(k)=ZT(k)×{1-[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, ZT(k) represents the irrigation cycle of the kth garden plant in the current monitoring cycle, and sets the irrigation amount of the garden plant in the next monitoring cycle to LT1(k), sets LT1(k)=LT(k)×exp{[ET(k)-et(k)] / ET(k)×[PJ(k)-GRAY] / GRAY}, LT(k) represents the irrigation amount of the kth garden plant in the current monitoring cycle; If the growth deviation state of the garden plant is abnormal, the solution generating unit sends a pruning suggestion for the garden plant to the user.

10. The intelligent garden management system based on image processing according to claim 9 is characterized in that: The garden plant management module also includes a machine learning unit, which is used to count the number of garden fertilizer deficiency alarms and pruning alarms pn within the management cycle, and compare pn with the preset alarm number PN, and when pn exceeds the preset alarm number PN, the average grayscale value of the preset pixel points in the next management cycle is corrected to GRAY'.

Images