Greenhouse strawberry crop water stress information detection method and system

Abstract

The invention relates to the technical field of crop water stress detection, and discloses a greenhouse strawberry crop water stress information detection method and system.The greenhouse strawberry crop water stress information detection method comprises the steps that S1, an inspection robot, a thermal imaging camera, a track and a client are included, the inspection robot is installed on the rear wall of a greenhouse, and the thermal imaging camera is installed on the track; strawberry crops are planted in the greenhouse. According to the greenhouse strawberry crop water stress information detection method, the water stress information is obtained through a simplified water stress index formula based on the canopy temperature, and compared with a traditional method that canopy temperature measurement is only limited to point or local areas, canopy temperature data lacks enough representativeness, and the measurement accuracy is improved. With the reduction of the cost of the inspection robot and the continuous improvement of the thermal infrared image temperature extraction technology, the thermal infrared image of the canopy of the crop can be quickly captured in real time in a large range by utilizing the thermal infrared sensor carried by the inspection robot, and the technology provides powerful support for accurately monitoring the moisture condition of the crop.

Description

Technical Field

[0001] The present invention relates to the technical field of crop water stress detection, and in particular to a method and system for detecting water stress information of greenhouse strawberry crops. Background Art

[0002] Greenhouse strawberries refer to strawberries grown in artificial controlled environments such as greenhouses or sheds. Strawberries are easy to be widely cultivated because of their strong adaptability. The economic benefits of planting have always been high and relatively stable, with obvious development advantages. The cultivated area shows a stable growth trend. In addition to fresh consumption, strawberries can also be processed into canned food, dried strawberries and other leisure foods. It is also one of the preferred industries for the integration of agriculture and tourism, so it has broad market prospects. In order to increase the yield of strawberries, the production usually adopts a one-year planting method. Fresh fruit cultivation is planted at the end of August and early September each year, and is put on the market in mid-November. It is harvested continuously until May of the following year. During this period, it experiences festivals such as Christmas, New Year's Day, and the Spring Festival. It is a seasonal fruit that is put on the market in winter. Among many facility horticulture industries, the economic benefits of strawberry planting are obvious. In addition, high-quality seedlings are the key link in the high yield of strawberries, and seedling breeding is also a new economic growth point for the strawberry industry.

[0003] Water stress is an important factor affecting the growth of greenhouse strawberry crops. Water stress refers to the phenomenon that the normal physiological functions of plants are disturbed or damaged when the water supply is insufficient or excessive. For greenhouse strawberries, water stress mainly occurs when the soil moisture content is lower or higher than the moisture range required for their normal growth.

[0004] Accurate and efficient diagnosis of crop water stress and maximizing the efficiency of agricultural water use are the basis for achieving scientific agricultural irrigation. Canopy temperature is determined by the transfer and conversion of heat in the soil-plant-atmosphere continuum. Canopy temperature and its related indices can indicate the state of crop water stress, among which the crop water stress index is the most widely used.

[0005] The traditional method of measuring canopy temperature is limited to "point" or "local" areas, which makes it difficult to fully reflect the overall distribution of canopy temperature in the crop area, resulting in the canopy temperature data lacking sufficient representativeness. Summary of the invention

[0006] In view of the fact that the above-mentioned existing traditional methods of measuring canopy temperature are limited to "points" or "local" areas, it is difficult to fully reflect the overall distribution of canopy temperature in the crop area, resulting in the problem that canopy temperature data lacks sufficient representativeness, the present invention is proposed.

[0007] Therefore, the purpose of the present invention is to provide a method for detecting water stress information of greenhouse strawberry crops, the purpose of which is: with the decrease in the cost of inspection robots and the continuous improvement of thermal infrared image temperature extraction technology, the inspection robots are equipped with thermal infrared sensors to quickly, real-time and capture thermal infrared images of crop canopies over a large range. This technology provides strong support for accurately monitoring the moisture status of crops.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a method for detecting water stress information of greenhouse strawberry crops, comprising S1, which is composed of a patrol robot, a thermal imaging camera, a track and a client, wherein the patrol robot is installed on the rear wall of a greenhouse, and strawberry crops are planted in the greenhouse;

[0009] S2, the thermal imaging camera carried by the rail-mounted inspection robot moves to the target canopy position along the track, and the camera takes pictures of canopies at different positions by rotating the angle until all target canopies are collected;

[0010] S3, using a self-made temperature calibration device, obtain the grayscale and temperature conversion function formula and perform temperature correction;

[0011] S4, threshold segmentation of canopy thermal images using the improved GA-Otsu algorithm;

[0012] S5, adding the original canopy thermal image and the image after threshold segmentation by image addition, thereby generating a canopy mask carrying temperature information;

[0013] S6, based on the screened strongly correlated environmental factor data, a dry and wet reference surface temperature prediction equation is constructed to achieve contactless acquisition of the dry and wet reference surface temperature;

[0014] S7, according to the water stress index formula, the water stress index at each location is calculated using the obtained canopy temperature and dry and wet reference surface temperature;

[0015] S8, based on the water stress index of each location obtained, a bilinear interpolation algorithm is used to construct a greenhouse global water stress information heat map to visualize the water status.

[0016] As a preferred solution described in the present invention, it includes thermal infrared image acquisition. The accurate acquisition of canopy temperature is at the core of the water stress information detection solution, but the accuracy of infrared thermal imaging cameras will be affected by shooting angle and distance.

[0017] As a preferred solution described in the present invention, the temperature information of the original thermal infrared image obtained by the thermal infrared imager has a certain deviation. In order to improve the accuracy of the image temperature information, the temperature information needs to be calibrated.

[0018] As a preferred solution described in the present invention, the GA-Otsu threshold segmentation algorithm includes: the core idea is to calculate the inter-class variance after the image is divided into two regions. However, in practical applications, when the grayscale level of the image to be segmented is high, the time required to find the optimal threshold will increase accordingly, resulting in a decrease in the efficiency of image segmentation. In order to solve this problem, the genetic algorithm can be used in combination with the Otsu algorithm by utilizing its global optimization and nonlinear fast convergence characteristics.

[0019] As a preferred solution described in the present invention, the genetic algorithm is a search heuristic algorithm for the biological evolution process based on natural selection and genetic mechanisms of Darwin's theory of biological evolution, which is used to simulate the natural evolution process to find the optimal solution. The essence of the genetic algorithm is to produce more adaptable offspring by randomly exchanging excellent parent information. This is a cyclic screening process, which is not limited by specific problems. The solution process is stable and has the advantages of strong robustness and suitability for parallel processing. When using a genetic algorithm to solve a problem, it is generally necessary to go through the steps of parameter encoding, initializing the population, selecting a fitness function, designing genetic operations, and setting control parameters.

[0020] As a preferred solution described in the present invention, the canopy area mask extraction includes obtaining a canopy area binary image by a threshold segmentation algorithm, but the binary image only segments the canopy area and does not carry temperature information. Therefore, extracting the canopy mask carrying temperature information is a key step in obtaining the canopy temperature.

[0021] As a preferred solution of the present invention, the acquisition of the dry-wet reference surface temperature includes accurately determining the dry-wet reference surface temperature, which is the basis for determining the CWSI.

[0022] The beneficial effects of the present invention are as follows: the simplified water stress index formula based on canopy temperature is used to obtain water stress information. Compared with the traditional method of measuring canopy temperature, which is limited to "points" or "local" areas, it is difficult to fully reflect the overall distribution of canopy temperature in the crop area, resulting in the lack of sufficient representativeness of canopy temperature data. With the reduction in the cost of inspection robots and the continuous improvement of thermal infrared image temperature extraction technology, inspection robots equipped with thermal infrared sensors can quickly, in real time and over a large area capture thermal infrared images of crop canopies. This technology provides strong support for the accurate monitoring of crop moisture conditions. However, thermal infrared images contain a large amount of interfering background, greenhouse structure and other ground object information, resulting in a large number of ground object mixed pixels in the extracted canopy temperature information, which interferes with the extraction of canopy temperature. Therefore, eliminating the interfering background in thermal infrared images is crucial to improving the accuracy of crop canopy temperature extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 labor. Among them:

[0024] Figure 1 This is the experimental partition diagram of the present invention.

[0025] Figure 2 It is a schematic diagram of the structure of the temperature calibration device of the present invention.

[0026] Figure 3 This is the first partition temperature grayscale conversion diagram of the present invention.

[0027] Figure 4 This is the second partition temperature grayscale conversion diagram of the present invention.

[0028] Figure 5 This is the third sub-area temperature grayscale conversion diagram of the present invention.

[0029] Figure 6 This is the first partition temperature correction diagram of the present invention.

[0030] Figure 7 This is the second zone temperature correction diagram of the present invention.

[0031] Figure 8 This is the third zone temperature correction diagram of the present invention.

[0032] Fig. 9 This is the image segmentation flow chart of the GA-Otsu method of the present invention.

[0033] Fig.10 This is the image algorithm diagram of the present invention.

[0034] Fig.11 This is the dry and wet reference temperature difference diagram of the present invention.

[0035] Fig.12 This is the CWSI thermogram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0038] Reference Figure 1-12 , is an embodiment of the present invention, providing a method and system for detecting water stress information of greenhouse strawberry crops, the method for detecting water stress information of greenhouse strawberry crops comprising S1, consisting of a patrol robot, a thermal imaging camera, a track and a client, the patrol robot being installed on the rear wall of a greenhouse, and strawberry crops being planted in the greenhouse;

[0039] S2, the thermal imaging camera carried by the rail-mounted inspection robot moves to the target canopy position along the track, and the camera takes pictures of canopies at different positions by rotating the angle until all target canopies are collected;

[0040] S3, using a self-made temperature calibration device, obtain the grayscale and temperature conversion function formula and perform temperature correction;

[0041] S4, threshold segmentation of canopy thermal images using the improved GA-Otsu algorithm;

[0042] S5, adding the original canopy thermal image and the image after threshold segmentation by image addition, thereby generating a canopy mask carrying temperature information;

[0043] S6, based on the screened strongly correlated environmental factor data, a dry and wet reference surface temperature prediction equation is constructed to achieve contactless acquisition of the dry and wet reference surface temperature;

[0044] S7, according to the water stress index formula, the water stress index at each location is calculated using the obtained canopy temperature and dry and wet reference surface temperature;

[0045] S8, based on the water stress index of each location obtained, a bilinear interpolation algorithm is used to construct a greenhouse global water stress information heat map to visualize the water status.

[0046] The system of the greenhouse strawberry crop water stress information detection method includes thermal infrared image acquisition. The accurate acquisition of canopy temperature is at the core of the water stress information detection scheme, but the accuracy of the infrared thermal imaging camera will be affected by the shooting angle and distance;

[0047] In order to reduce the impact on the acquisition of temperature data, this experiment will divide each line into the following when taking images: Figure 1For the three areas shown, area one was photographed when the camera was at an angle of 40° to the horizontal, area two was photographed when the angle was 30°, and area three was photographed when the angle was 25°. This is to facilitate temperature correction by partition in the following analysis, thereby improving the accuracy of canopy temperature extraction. The acquisition time was 09:00-15:00 (Beijing time), and it took about 15 minutes to collect the entire test area.

[0048] The temperature information of the original thermal infrared image obtained by the thermal infrared imager has a certain deviation. In order to improve the accuracy of the image temperature information, the temperature information needs to be calibrated.

[0049] like Figure 2 The temperature calibration device shown in the figure has a dry-bulb and wet-bulb temperature sensor placed in the water, and a thermal imaging sensor captures the thermal image of the water. The temperature of the water is measured using a temperature sensor, and the grayscale of the water in the thermal infrared image is extracted. The water temperature of each partition is measured 20 times from 20 to 40°C. The conversion function formula between the grayscale and temperature of each partition is constructed by extracting the measured temperature and grayscale of the water. In order to reduce the temperature error, the image temperature needs to be calibrated. In this paper, a portable handheld thermometer is used to measure the temperature of the water, and a calibration function between the measured temperature and the image temperature is established with the temperature of the water in the extracted image. The temperature conversion of each group is shown in Figure 3 , Figure 4 , Figure 5 , temperature correction is shown in Figure 6 , Figure 7 , Figure 8 .

[0050] The GA-Otsu threshold segmentation algorithm includes: the core idea is to calculate the inter-class variance after the image is segmented into two regions. However, in practical applications, when the grayscale level of the image to be segmented is high, the time required to find the optimal threshold will increase accordingly, resulting in a decrease in the efficiency of image segmentation. In order to solve this problem, the genetic algorithm can be used in combination with the Otsu algorithm by utilizing its global optimization and nonlinear fast convergence characteristics.

[0051] The genetic algorithm is a search heuristic algorithm based on the biological evolution process of natural selection and genetics mechanism of Darwin's theory of biological evolution. It is used to simulate the natural evolution process to find the optimal solution. The essence of the genetic algorithm is to produce more adaptable offspring by randomly exchanging excellent parent information. This is a cyclic screening process that is not limited by specific problems. The solution process is stable and has the advantages of strong robustness and suitability for parallel processing. When using genetic algorithms to solve problems, it is generally necessary to go through the steps of parameter encoding, initializing the population, selecting the fitness function, designing genetic operations, and setting control parameters. Fig. 9 The figure shows the basic optimization process of GA in practical problems;

[0052] Genetic algorithms can optimize Otsu's threshold selection process. The combined GA-Otsu algorithm can perform nonlinear and rapid iteration and adjustment of the optimal threshold parameters. This method can significantly improve the efficiency and performance of the Otsu algorithm when processing high-resolution images, thereby being able to more efficiently handle complex image segmentation tasks, especially in cases where the contrast between the target and the background is high, and can be more accurate.

[0053] The canopy area mask extraction includes obtaining a canopy area binary image by a threshold segmentation algorithm, but the binary image only segments the canopy area and does not carry temperature information. Therefore, it is necessary to extract the canopy mask carrying temperature information, which is a key step in obtaining the canopy temperature.

[0054] The mask part of the canopy area is extracted by adding the original thermal imaging image to the segmented image. Each pixel in the image has a pixel value represented by an integer. The addition of two images is to add the pixel values ​​at the same position. The final calculation result is reassembled into a new image according to the original position. The principle is as follows Fig.10 As shown;

[0055] In actual program development, the "+" operator is not used directly to perform addition operations on images, because if the calculation result of the "+" operator exceeds 255, the remainder of the addition and division by 255 will be taken. The pixel value may become smaller after addition, which will affect the accuracy of mask pixel extraction. The add() method provided by OpenCV, when the sum of the pixel values ​​of two pixels is greater than 255, will calculate the result equal to the saturation value 255 (maximum value) of the pixel. The syntax definition of this method is as follows:

[0056] dst=cv2.add(src1,src2,mask,dtype)

[0057] Return value description:

[0058] dst: The image after addition. If the added value is greater than 255, 255 is used.

[0059] Parameter Description:

[0060] src1: The first image.

[0061] src2: The first image.

[0062] mask: Optional parameter, mask, generally use the default value.

[0063] dtype: optional parameter, image depth, generally use the default value.

[0064] The dry-wet reference surface temperature acquisition includes accurately determining the dry-wet reference surface temperature, which is the basis for determining CWSI. The wet reference surface temperature is determined by spraying water on the crop canopy leaves under sufficient irrigation conditions. The dry reference surface temperature is equal to the temperature of non-transpiration leaves with completely closed stomata, which is measured by applying vaseline on the front and back of the crop canopy leaves under water stress conditions. The temperature difference is as follows: Fig.11 As shown;

[0065] The dry and wet reference surface temperature depends largely on the environmental conditions of the measurement process, such as air temperature and humidity, carbon dioxide concentration and other environmental climate factors. In this study, a handheld thermal imager was used to measure wet canopy leaves and leaves coated with vaseline. As shown in the figure, the treated leaves showed a huge color difference in the thermal image. At the same time, the atmospheric and greenhouse environmental factors were measured and a total of 500 sets of data were collected. Based on the correlation between these environmental data and the dry and wet reference surface temperature, a multivariate regression fitting formula was determined to predict the dry and wet reference surface temperature without any reference surface.

[0066] Based on the screened data of strongly correlated environmental factors, the dry and wet reference surface temperature prediction equation is constructed as follows:

[0067] T wet =0.729T ro -0.270H ro -0.958T air +0.108H air +0.404T box +0.188H box +10.156

[0068] T dry =0.894T ro -0.326H ro -0.855T air +0.073H air +0.540T box +0.236H box +6.773

[0070] Where: T wet - wet reference surface temperature;

[0071] T dry - dry reference surface temperature;

[0072] T ro -Sensor temperature on the robot;

[0073] H ro - Sensor temperature and atmospheric humidity on the robot;

[0074] T air - atmospheric temperature;

[0075] H air - atmospheric humidity;

[0076] T box -Greenhouse wet bulb sensor temperature;

[0077] H box -Greenhouse wet bulb sensor humidity.

[0078] According to actual production experience, strawberry crop stress less than or equal to 0.6 is defined as mild stress, 0.6-0.8 is moderate stress, and greater than or equal to 0.8 is severe stress. In order to facilitate users to intuitively view the distribution of greenhouse water stress, the client reads the predicted dry and wet reference surface temperature and the canopy temperature obtained from the thermal image from the sensor database to calculate the water stress index, but single-point data is difficult to fully reflect the overall water status of the greenhouse. To this end, the bicubic interpolation algorithm is introduced to visualize the water stress data, thereby generating a global thermal map of greenhouse water stress, such as Fig.12 Shown is a heat map of greenhouse water stress distribution at 09:00 am on May 21, 2024, which visually displays the severity of water stress in different areas in a color gradient. Through this innovative method, greenhouse managers can quickly and intuitively grasp the distribution and changing trends of water stress, providing strong support for precision irrigation.

[0079] Accurate and efficient diagnosis of crop water stress and maximizing the efficiency of agricultural water use are the basis for achieving scientific agricultural irrigation. Canopy temperature is determined by the transfer and conversion of heat in the soil-plant-atmosphere continuum. Canopy temperature and its related indexes can indicate the state of crop water stress, among which the crop water stress index (Crop Water Stress Index, CWSI) is the most widely used. This study uses a simplified water stress index formula based on canopy temperature to obtain water stress information. The formula is:

[0080]

[0081] Where: T C —Current average canopy temperature;

[0082] T wet —The canopy temperature of the crop when the stomata are fully open and the transpiration rate reaches the maximum, also known as the wet reference surface temperature;

[0083] T dry —The canopy temperature of the crop when the stomata are completely closed and no transpiration occurs, also known as the dry reference surface temperature;

[0084] The traditional method of measuring canopy temperature is limited to "points" or "local" areas, which makes it difficult to fully reflect the overall distribution of canopy temperature in the crop area, resulting in a lack of sufficient representativeness of canopy temperature data. With the reduction in the cost of inspection robots and the continuous improvement of thermal infrared image temperature extraction technology, inspection robots equipped with thermal infrared sensors can quickly, in real time and over a large area capture thermal infrared images of crop canopies. This technology provides strong support for the accurate monitoring of crop moisture conditions. However, thermal infrared images contain a large amount of interfering background, greenhouse structure and other ground object information, resulting in a large number of ground object mixed pixels in the extracted canopy temperature information, which interferes with the extraction of canopy temperature. Therefore, removing the interfering background in thermal infrared images is crucial to improving the accuracy of crop canopy temperature extraction.

[0085] Accurate acquisition of canopy temperature and dry-wet reference surface temperature is the basis for obtaining water stress information of greenhouse strawberries. Accurate acquisition of canopy temperature mainly involves accurately eliminating background interference in thermal infrared images and temperature correction formulas, and accurate acquisition of dry-wet reference surface temperature mainly involves screening strongly correlated environmental factors for prediction.

[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting water stress information of greenhouse strawberry crops, characterized in that: include: S1, consists of a patrol robot, a thermal imaging camera, a track, and a client. The patrol robot is installed on the back wall of the greenhouse where strawberry crops are grown; S2, the thermal imaging camera carried by the rail-mounted inspection robot moves to the target canopy position along the track, and the camera takes pictures of canopies at different positions by rotating the angle until all target canopies are collected; S3, using a self-made temperature calibration device, obtain the grayscale and temperature conversion function formula and perform temperature correction; S4, threshold segmentation of canopy thermal images using the improved GA-Otsu algorithm; S5, adding the original canopy thermal image and the image after threshold segmentation by image addition, thereby generating a canopy mask carrying temperature information; S6, based on the screened strongly correlated environmental factor data, a dry and wet reference surface temperature prediction equation is constructed to achieve contactless acquisition of the dry and wet reference surface temperature; S7, according to the water stress index formula, the water stress index at each location is calculated using the obtained canopy temperature and dry and wet reference surface temperature; S8, based on the water stress index of each location obtained, a bilinear interpolation algorithm is used to construct a greenhouse global water stress information heat map to visualize the water status.

2. A system for detecting water stress information of greenhouse strawberry crops, which is applied to the method for detecting water stress information of greenhouse strawberry crops described in claim 1, characterized in that: Including thermal infrared image acquisition, the accurate acquisition of canopy temperature is at the core of the water stress information detection scheme, but the accuracy of infrared thermal imaging cameras will be affected by the shooting angle and distance.

3. The greenhouse strawberry crop water stress information detection system according to claim 2, characterized in that: The temperature information of the original thermal infrared image obtained by the thermal infrared imager has a certain deviation. In order to improve the accuracy of the temperature information of the image, the temperature information needs to be calibrated.

4. The greenhouse strawberry crop water stress information detection system according to claim 3, characterized in that: The GA-Otsu threshold segmentation algorithm includes: the core idea is to calculate the inter-class variance after the image is segmented into two regions. However, in practical applications, when the grayscale level of the image to be segmented is high, the time required to find the optimal threshold will increase accordingly, resulting in a decrease in the efficiency of image segmentation. In order to solve this problem, the genetic algorithm can be used in combination with the Otsu algorithm by utilizing its global optimization and nonlinear fast convergence characteristics.

5. The greenhouse strawberry crop water stress information detection system according to claim 4, characterized in that: The genetic algorithm is a search heuristic algorithm based on the biological evolution process of natural selection and genetics mechanism of Darwin's theory of biological evolution. It is used to simulate the natural evolution process to find the optimal solution. The essence of the genetic algorithm is to produce more adaptable offspring by randomly exchanging excellent parent information. This is a cyclic screening process that is not limited by specific problems. The solution process is stable and has the advantages of strong robustness and suitability for parallel processing. When using genetic algorithms to solve problems, it is generally necessary to go through steps such as parameter encoding, initializing the population, selecting fitness functions, designing genetic operations, and setting control parameters.

6. The greenhouse strawberry crop water stress information detection system according to claim 5, characterized in that: The canopy area mask extraction includes obtaining a canopy area binary image by a threshold segmentation algorithm, but the binary image only segments the canopy area and does not carry temperature information. Therefore, extracting the canopy mask carrying temperature information is a key step in obtaining the canopy temperature.

7. The greenhouse strawberry crop water stress information detection system according to claim 6, characterized in that: The dry-wet reference surface temperature acquisition includes accurately determining the dry-wet reference surface temperature, which is the basis for determining the CWSI.

Images