TW202123152A - Fruits and vegetables monitoring system and method thereof - Google Patents

Abstract

A fruits and vegetables monitoring system and a method thereof are provided. In the method, the positions of the fruitage and the stem can be detected, and the maturity of the fruits and vegetables can be identified. In addition, the empirical rule from the farmer can be used to determine the controlling rule of the environment. Accordingly, the farmer without experience can dive right in quickly. The production can be predicted accurately, and the growth situation can be recorded, so that the farmer can prepare a sale plan in advance and establish production history quickly. In addition, by applying hydrogen-water sparkling machines on the farm, the pesticide can be reduced or abandoned.

Description

Vegetable and fruit monitoring system and method

The present invention relates to a smart agricultural technology, and particularly relates to a vegetable and fruit monitoring system and method.

In recent years, the government has assisted young people to return to their hometowns to work in agriculture. However, young farmers who are beginning to enter usually do not have any farm experience. Even if the cost of learning for 2 to 3 years is invested, there may not be good results (for example, poor harvest, high cost, etc.).

On the other hand, different types of fruits and vegetables have their own suitable growth environment. However, environmental factors vary greatly. Factors such as temperature difference between day and night, drought, pests and diseases, etc. are usually difficult to improve immediately with manpower alone.

In view of this, the embodiments of the present invention provide a vegetable and fruit monitoring system and a method thereof, which use the Internet of Things (IoT) architecture and artificial intelligence (AI) technology to monitor the growth environment of the vegetable and fruit, so that farmers can easily manage the farm.

The vegetable and fruit monitoring system of the embodiment of the present invention is suitable for monitoring the vegetable and fruit grown in the farm. The vegetable and fruit monitoring system includes but is not limited to image capture devices and control devices. The image capturing device is used to capture fruits and vegetables to obtain images. The control device judges the maturity and location information of the fruits and vegetables based on the images. The position information includes the position of the fruit and the harvest position of the stalk, and the position of the fruit includes the top position and the bottom position of the fruit corresponding to the vegetable and fruit. The control device estimates the picking position of the stalk based on the relative position relationship. This relative positional relationship is obtained based on the corresponding top position and bottom position, and the stalk harvesting position is the position for cutting external objects.

On the other hand, the method for monitoring fruits and vegetables according to embodiments of the present invention is suitable for monitoring fruits and vegetables grown in farms, and includes the following steps: photographing fruits and vegetables to obtain images. Judge the maturity and location information of fruits and vegetables based on images. Estimate the picking position of the stalk based on the relative position relationship. The position information includes the position of the fruit and the harvesting position of the stalk. The position of the fruit includes the top and bottom positions of the fruit corresponding to the fruits and vegetables. The relative position relationship is based on the corresponding top and bottom positions. The harvesting position of the stalk is for the outside The location where the object is cut.

Based on the above, the vegetable and fruit monitoring system and method of the embodiments of the present invention judge the maturity and location of the vegetable and fruit through image recognition technology, and estimate the stalk harvesting position based on the relative positional relationship between the fruit and the stalk. In this way, it is convenient for farmers to understand the growth situation of fruits and vegetables at the remote end, and can further plan harvesting operations.

In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

FIG. 1 is a block diagram of a vegetable and fruit monitoring system 100 according to an embodiment of the present invention. Please refer to FIG. 1, the vegetable and fruit monitoring system 100 includes, but is not limited to, a sensing device 110, an image capturing device 130, an environment adjusting device 150, a harvesting device 170 and a control device 190. The vegetable and fruit monitoring system 100 is suitable for monitoring at least one or at least one vegetable and fruit grown in at least one farm (for example, a net house, a greenhouse, or an open farmland). It should be noted that the number of devices in the vegetable and fruit monitoring system 100 can be adjusted according to actual needs.

The sensing device 110 may be a thermometer, a hygrometer, a visible light meter (or an illuminance meter, and used to measure sunlight), other types of environmental sensors, or a combination thereof. The thermometer may include sensing elements such as a thermocouple, a thermistor, and a thermal resistor. In one embodiment, in an agricultural environment (for example, the temperature is about 0-50°C), the resistance of the metal material used in the resistance thermometer has a good linear relationship with the temperature change. Therefore, the resistance temperature sensor can be used to obtain the farm (For example, greenhouse) temperature data. In another embodiment, since the humidity in the subtropical region where Taiwan is located is relatively high, a resistive relative humidity meter can be used to obtain the humidity data of the greenhouse.

The image capturing device 130 may be various types of cameras, video recorders, closed-circuit cameras, smart phones, or tablet computers. The image capture device 130 may be fixed on a farm or a mobile device (for example, a robot, an unmanned aircraft, a remote control machine, or a rail car, etc.), and can be used for specific areas (limited by field of view (FOV)) or controlled by Instruct to change the field of view to shoot.

The environmental adjustment device 150 may be a fan, a dehumidifier, a sprinkler, an air conditioner, a fill light, or a combination thereof.

The harvesting device 170 may be a robotic arm or a robot. In an embodiment, the harvesting device 170 includes automated mechanical components capable of grasping, cutting, and/or pushing and pulling. In the embodiment of the present invention, the harvesting device 170 is used for harvesting fruits and vegetables. Since different types of fruits and vegetables have different harvesting behaviors, the user can adjust the mechanical components of the harvesting device 170 according to requirements.

The control device 190 can be a desktop computer, a notebook computer, a server, a workstation, a smart phone, a tablet computer, an intelligent assistant, etc., and has at least a processor such as a CPU or a chip to perform image processing and image analysis. , Image recognition, sensing data collection and analysis, remote control instructions and other operations.

It should be noted that the aforementioned devices 110 to 190 further include communication transceivers with compatible communication technologies (for example, Wi-Fi, Bluetooth, infrared, etc.), so that they can communicate with each other. In some embodiments, some devices are more likely to be integrated into a single device. For example, the image capturing device 130 is integrated with the harvesting device 170 and the control device 190.

In order to facilitate the understanding of the operation process of the embodiment of the present invention, a number of embodiments will be given below to describe in detail the monitoring process of the fruits and vegetables grown on the farm in the embodiment of the present invention. Hereinafter, various devices, components, and modules in the vegetable and fruit monitoring system 1 will be used to illustrate the method described in the embodiment of the present invention. Each process of the method can be adjusted accordingly according to the implementation situation, and it is not limited to this.

Fig. 2 is a flowchart of a method for monitoring fruits and vegetables according to an embodiment of the present invention. Please refer to FIG. 2, the image capturing device 130 photographs fruits and vegetables to obtain images (step S210). Take a tomato garden as an example of farmland (ie, take tomatoes as an example for vegetables and fruits). The control device 190 can drive a moving device to move the image capturing device 130 to a designated position (for example, about 30-50 cm away from the tomato), and perform Shooting operations to obtain images. For another example, the image capturing device 130 is fixed around the tomato planting place, and records or shoots images of the tomato. It should be noted that the embodiment of the present invention does not limit the image acquisition method. In addition, the types of fruits and vegetables are not limited to tomatoes. For example, bananas, strawberries and other fruits and vegetables.

Then, the control device 190 obtains images from the image capturing device 130, and judges the maturity and location information of the fruits and vegetables based on one or more images (step S230). Specifically, the control device 190 judges the maturity and location information based on the image recognition technology. In one embodiment, the image recognition technology is based on a machine learning algorithm. The machine learning algorithm may be Region-based Convolutional Neural Network (RCNN), Fast Region-based Convolutional Neural Network (Fast R-CNN), or faster Regional-based Convolutional Neural Network (Faster Region-based Convolutional Neural Network, Faster R-CNN) and other architectures. These neural network training architectures are widely used in target detection methods.

In another embodiment, the machine learning algorithm is a Mask Region-based Convolutional Neural Network (Mask RCNN) architecture. Simply put, Mask RCNN is based on Faster R-CNN to increase the regression of the mask to output the result of semantic segmentation (for example, segmentation mask). Mask R-CNN includes a two-stage program. The first stage scans the image and generates the target area, and the second stage classifies and generates bounding boxes and masks.

Figure 3 is an example illustrating the results of fruit identification. Referring to FIG. 3, taking tomato as an example, the control device 190 can not only detect the fruit, but also further determine the contour of the fruit in the image (the darker mask in the figure indicates the detection result of the object).

It should be noted that the embodiment of the present invention does not limit the type of machine learning technology. It is worth noting that in the CNN architecture, the convolution layer and the pooling layer enhance the relationship between image recognition and data neighbors, so that CNN can be used in image, sound and other signal types. Data types can get very good results. The biggest difference from the traditional multilayer perceptron (MLP) network is that CNN adds two layers: convolutional layer and pooling layer to maintain shape information and avoid significant increase in parameters. In addition, the architecture includes a full connection layer (Full connection), and finally outputs the result for the classifier. The classifier is generated by inputting training samples, and these training samples are, for example, images including different types of fruits and vegetables.

In some embodiments, the activation function can be ReLU, Leaky ReLU, or Swish, but it is not limited to this.

In addition to detecting the specified fruits and vegetables from the images, the control device 190 can also predict the boundaries of the fruits and vegetables (for example, a frame of a specific shape, or the outline of the fruits and vegetables) based on a machine learning algorithm, so as to obtain the position information of the fruits and vegetables. This position information may be the coordinates in a space coordinate system or the relative position of other reference objects. If the contours of the fruits and vegetables can be recognized, the control device 190 can further determine the position information of the contours/surfaces of the fruits and vegetables.

In one embodiment, the position information of the fruits and vegetables includes the position of the fruit and the harvesting position of the stalk, and the position of the fruits includes the top position and the bottom position of the fruit corresponding to the fruits and vegetables. Specifically, the position of the fruit can be any point or more points on the boundary, the center position, or any position on the fruit. The top position of the fruit is the junction of the fruit and the pedicle, and the bottom position represents the bottom position of the fruit. On the other hand, the stalk harvesting position is a position for cutting by external objects (for example, hands, harvesting device 170, scissors, etc.). It is worth noting that, for the Yunv tomato, today's consumers usually think that "tomatoes with pedicels are fresh." Compared with the method of directly twisting the fruit in general automatic harvesting farms, the embodiment of the present invention judges the position of the tomato stalks, and cuts the stalks when harvesting, so as to retain the stalks and let consumers understand The products obtained from these harvesting methods can be called "fresh tomatoes".

In one embodiment, the control device 190 estimates the picking position of the stalk based on the relative position relationship (step S231). Specifically, the relative position relationship is derived based on the top position and bottom position of the corresponding fruit. Based on the analysis results, it can be concluded that the stalk harvest position is located at the extension of the top position and the bottom position, and the distance from the stalk harvest position to the top position has a specific proportional relationship with the distance from the top position to the bottom position (for example, 1: 5. Or 1:3, etc.).

In one embodiment, the relative position relationship includes length information and an extension line from the bottom position to the top position. After the control device 190 determines the top position and bottom position of the corresponding fruits and vegetables (for example, based on image recognition technology), the length information of the corresponding fruit can be obtained according to the top position and bottom position. That is, the length information is related to the distance from the top position to the bottom position. Then, the control device 190 can estimate the harvest position of the stalk based on the length information and the aforementioned extension line. The retention length of the stalk can be obtained based on the aforementioned proportional relationship and length information. In other words, the picking position of the stalk is the position on the extension line and away from the top position by the reserved length of the stalk.

…(1) 假設比例關係為1/5，則蒂頭保留長度Green_d可由公式(2)得出：

…(2) 假設蒂頭13上的蒂頭採收位置CP位於由底部位置BP至頂部位置TP之延伸線，且設有比例關係。因此，蒂頭採收位置CP至頂部位置TP的距離與頂部位置TP至底部位置BP的距離之間的比例關係將相同於蒂頭採收位置CP至虛擬點VP2(蒂頭採收位置CP垂直延伸線與頂部位置TP水平延伸線之交點)的距離與頂部位置TP至虛擬點VP(頂部位置TP垂直延伸線與底部位置BP水平延伸線之交點)的距離之間的比例關係、或頂部位置TP至虛擬點VP2的距離與底部位置BP至虛擬點VP的距離之間的比例關係。此外，蒂頭採收位置CP對應夾角θ相同於頂部位置TP對應夾角θ。For example, FIG. 4 is a schematic diagram of the relative position relationship according to an embodiment of the present invention. 4, taking tomato 10 as an example, suppose the coordinates of the top position TP of the fruit 11 are (Xm, Ym), and the coordinates of the bottom position BP of the fruit 11 are (Xd, Yd). The length information Red_d can be obtained by formula (1):

…(1) Assuming that the proportional relationship is 1/5, the remaining length of the stalk Green_d can be obtained by formula (2):

...(2) Assume that the stalk harvest position CP on the stalk 13 is located on the extension line from the bottom position BP to the top position TP, and there is a proportional relationship. Therefore, the proportional relationship between the distance from the pedicle harvest position CP to the top position TP and the distance from the top position TP to the bottom position BP will be the same as the pedicle harvest position CP to the virtual point VP2 (the pedicle harvest position CP is vertical The proportional relationship between the distance between the extension line and the intersection of the horizontal extension line of the top position TP and the distance from the top position TP to the virtual point VP (the intersection of the vertical extension line of the top position TP and the horizontal extension line of the bottom position BP), or the top position The proportional relationship between the distance from TP to the virtual point VP2 and the distance from the bottom position BP to the virtual point VP. In addition, the angle θ corresponding to the pedicle harvest position CP is the same as the angle θ corresponding to the top position TP.

…(3) ，且蒂頭採收位置的座標(Xt, Yt)可由公式(4)得出：

…(4)The angle θ can be obtained by formula (3):

…(3), and the coordinates (Xt, Yt) of the stalk harvest position can be obtained by formula (4):

…(4)

It should be noted that in other embodiments, the control device 170 may also directly obtain the stalk harvesting position based on image recognition technology, or estimate the stalk harvesting position based on a machine learning algorithm, and it is not limited to this.

In addition, with regard to the degree of maturity, in one embodiment, the control device 190 may determine the degree of maturity according to the location information and the color distribution of the corresponding fruit in the image (step S233). Taking FIG. 5 as an example, FIG. 5 is a schematic diagram of maturity recognition according to an embodiment of the present invention. Referring to FIG. 5, the control device 190 obtains the boundary/contour of the fruit 11 corresponding to the fruit and vegetable (tomato 10 in the figure) in the image from the position information, and uses the boundary as the region of interest ROI. Then, the control device 190 can determine the ripe color corresponding to the fruits and vegetables (for example, tomato corresponds to red, or banana corresponds to yellow, etc.), and determines the distribution of the ripe color. This distribution situation can be related to the proportion of pixels (that is, the proportion of the number of pixels corresponding to the ripe color to the number of pixels of all fruits). This ratio can correspond to the maturity of the fruits and vegetables.

It should be noted that the distribution situation is not limited to the ratio. In other embodiments, the color corresponding to the median and the color corresponding to the mode can be used to determine the degree of maturity, and it is not limited thereto. In some embodiments, the control device 190 can recognize the size of the fruit and determine the degree of maturity accordingly. For example, the larger the fruit, the more mature, and the smaller the fruit is immature.

In one embodiment, the control device 190 may divide the farm into several areas, and estimate the yield information of each area according to the maturity of the fruits and vegetables (step S235). Specifically, the control device 190 may set the area according to location, type, planting time, or other rules. In addition, the control device 190 can respectively count the corresponding numbers of different maturity levels in each region. For example, area A includes 50 fruits and vegetables that mature after three days, and 5 fruits and vegetables that have matured. It is worth noting that the control device 190 may also estimate the ripening time of the fruits and vegetables based on the ripeness degree. For example, the proportion of the number of pixels of the aforementioned mature color corresponds to a specific expected mature time. The control device 190 can estimate the output information of each region based on the estimated maturity time and the mature quantity. This production information is related to the current mature quantity, the quantity that will mature in a specific number of days in the future, or a combination thereof. This yield information can be used by farmers to formulate harvesting, sales, or distribution strategies. For example, farmers can decide whether to carry out harvesting operations currently, schedule harvesting operations in a certain number of days in the future, or designate some areas for harvesting operations based on the amount of maturity or estimated maturity time. In addition, the control device 190 can record the growth log of each vegetable and fruit (for example, the time corresponding to the degree of maturity, the amount of mature in the region, etc.) to grasp the production process and compare the difference with the expected situation.

In one embodiment, the control device 190 can control the harvesting device 170 to move according to the position information, and harvest the corresponding fruits and vegetables according to the stalk harvesting position. In addition to obtaining the two-dimensional position information from the image, if the image capturing device 130 is equipped with a depth sensor (for example, based on infrared, radar, or stereo camera, etc.), the control device 190 can further determine the three-dimensional position information. Then, the harvesting device 170 can be moved to the vicinity of the harvestable fruits and vegetables (that is, within a specific range around the location information of the fruits and vegetables) according to the instructions of the control device 190, and the harvesting device 170 can be harvested through a cutting component (for example, a robotic arm, scissors, or a clip) Claws, etc.) are harvested at the stalk harvesting position to harvest the fruits and vegetables.

In one embodiment, the control device 190 can sense the temperature, humidity, and illuminance in the farm through the sensing device 110, and obtain the rotation speed and dehumidification switch indication from the rule database according to the temperature, humidity, and illuminance. Specifically, the suitable growth environment for different types of fruits and vegetables is different. For example, the female tomato loves warm sex, and its suitable growth temperature is 19-24 Celsius. If the temperature is too high (especially if the temperature is too high during the day), it will easily cause severe flower falling, which will result in poor results, or even incomplete results or unsatisfactory fruits. If the temperature is too low, the fruit will grow slowly and will not be resistant to frost damage. The optimum temperature for the development of the red "lycopene" of the virgin tomato fruit is around 19-24 Celsius. If the temperature exceeds 30 degrees Celsius, it will result in poor growth of the tomato and poor coloration of the fruit (for example, not red but orange-yellow). On the other hand, although the length of sunlight has no significant relationship with the differentiation of tomato flower buds, the intensity of light has an effect on the development of flower buds. For example, if the light intensity is low (below the set threshold), it is easy to cause overgrowth or flower falling, disease is also easy to occur, and the fruit is not easy to become hypertrophic. It can be seen that temperature, humidity and illumination are important factors for the growth of fruits and vegetables.

For example, during the growth process of Yunv tomato, the growth environment is extremely important for subsequent sales. If the relationship between the growth environment of Yunv tomato and its maturity and yield is not recorded, the supply of orders may fall short of demand and it is easy to anger consumers. In addition, if there is no analysis for each of the virgin tomatoes in the field, it may also lead to excessive growth differences in some areas.

In one embodiment, the rule database is based on fuzzy logic. The structure of the fuzzy control system is shown in FIG. 6, which is a schematic diagram of environmental monitoring according to an embodiment of the present invention. Please refer to FIG. 6, the control device 190 uses the temperature, humidity and illuminance data obtained by the three sensing devices 130 as the input of the fuzzy system, and sets the output to control the fan speed and the dehumidifier switch (assuming that the environmental regulation device 150 is a fan and dehumidifier Machine), and then define the corresponding attribution function for each input, thereby establishing a rule database. For example, if the temperature is low, the humidity is dry and the illuminance is low, the corresponding attribution function is that the fan speed is low and the dehumidification switch is off; the temperature is medium, the humidity is dry and the illuminance is low, and the corresponding attribution function is the fan speed and the dehumidification switch The indication is off.

Through the fuzzy inference of the embodiment of the present invention, farmers’ experience can be used as a reference for the establishment of a rule database to achieve precise environmental control. These methods are no longer simply switching the fan on and off, but can control the fan through fuzzy rules to infer the optimal air volume required by the actual situation, and the control of the dehumidifier is also the same. In addition, in other embodiments, the control device 190 can also make decisions based on the irrigation schedule or other growth conditions, and is not limited thereto.

In one embodiment, the control device 190 uses data mining technology to find hidden special associations and features. For example, in the growth process of each jade girl tomato, the big data exploration method is used for the jade girl tomato, and the result rate of each plant is recorded, such as the number of blossoms, the number of tomatoes that have been set, and the number of tomatoes that have been harvested. The control device 190 can record the location information, the maturity level, and the harvestable quantity (for example, the mature quantity) of the fruits and vegetables in each area through one-dimensional code, two-dimensional code or other codes, and then send it to other servers for Perform big data analysis (may also be executed by the control device 190) to estimate the maturity time, output and other information.

In some embodiments, preprocessing (preprocessing) may be performed before data exploration to eliminate errors, missing, or incomplete data. Then, algorithms such as C4.5, decision tree (decision tree), frequent pattern tree (Frequent Pattern Tree, FP tree), ID3, or classification and regression tree (Classification And Regression Tree, CART) can be used to construct a decision tree model. , And finally substitute the test data for verification. This decision tree model can be used for the evaluation of yield and/or maturity time.

In one embodiment, the control device 190 may provide a user interface for the user to view environmental sensing information (e.g., temperature, humidity, and/or illuminance, etc.) in a specific area, and the current operation status of the environmental adjustment device 150 (e.g., rotation speed). , Switch situation, etc.), fruit and vegetable identification results (for example, fruit location, stalk harvest location, maturity, etc.) and estimated harvest time.

In one embodiment, the environmental adjustment device 150 further includes a hydrogen water bubbler to suppress the occurrence of pests by spraying hydrogen water, thereby reducing or avoiding pesticide spraying.

In summary, the fruit and vegetable monitoring system and method of the embodiments of the present invention detect the harvesting position of the fruit and the stalk, and identify the ripeness of the fruit and vegetable. In addition, the embodiment of the present invention uses the rule of thumb as the control principle of environmental regulation. In this way, farmers without farm experience can get started quickly, and it can also help all farmers predict yields and record growth conditions, so as to formulate sales strategies early and quickly build production resumes. In addition, by using the hydrogen water bubble machine in the farm, pesticide spraying can be reduced or avoided.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the relevant technical field can make some changes and modifications without departing from the spirit and scope of the present invention. The protection scope of the present invention shall be subject to those defined by the attached patent application scope.

100: Vegetable and Fruit Monitoring System 110: sensing device 130: Image capture device 150: Environmental regulation device 170: Harvesting device 190: control device S210~S235: steps 10: Tomato 11: Fruit 13: pedicle TP: Top position BP: bottom position CP: Picking position of stalk VP, VP2: virtual point θ: included angle ROI: region of interest

Fig. 1 is a block diagram of a vegetable and fruit monitoring system according to an embodiment of the present invention. Fig. 2 is a flowchart of a method for monitoring fruits and vegetables according to an embodiment of the present invention. Figure 3 is an example illustrating the results of fruit identification. Fig. 4 is a schematic diagram of a relative position relationship according to an embodiment of the present invention. FIG. 5 is a schematic diagram of maturity recognition according to an embodiment of the present invention. Fig. 6 is a schematic diagram of environmental monitoring according to an embodiment of the present invention.

S210~S235: steps

Claims (10)

A vegetable and fruit monitoring system is suitable for monitoring at least one vegetable and fruit grown in a farm. The vegetable and fruit monitoring system also includes: At least one image capturing device for capturing the at least one fruit and vegetable to obtain at least one image; and A control device for judging a maturity level and a location information of the at least one fruit and vegetable according to the at least one image, wherein The position information includes a fruit position and a stalk harvest position, the fruit position includes a top position and a bottom position of a fruit corresponding to the vegetable and fruit, and The control device estimates the picking position of the stalk based on a relative position relationship, wherein the relative position relationship is obtained based on the top position and the bottom position, and the picking position of the stalk is for cutting an external object position. Such as the vegetable and fruit monitoring system described in item 1 of the scope of patent application, wherein the relative position relationship includes a length information and an extension line from the bottom position to the top position, and the control device obtains according to the top position and the bottom position Corresponding to the length information of the fruit, and estimate the picking position of the stalk based on the length information and the extension line. For example, the vegetable and fruit monitoring system described in item 1 of the scope of patent application, wherein the control device determines the maturity level according to the location information and the color distribution of the corresponding fruit in the at least one image, and the control device divides the farm into a plurality of Region, and estimate the yield information of each region based on the ripeness of the at least one fruit and vegetable. For example, the vegetable and fruit monitoring system described in item 1 of the scope of patent application includes: A harvesting device is controlled by the control device to move according to the position information, and harvest corresponding fruits and vegetables according to the stalk harvesting position. For example, the vegetable and fruit monitoring system described in item 1 of the scope of patent application includes: At least one sensing device for sensing the temperature, humidity and illuminance in the farm; and At least one environmental regulation device includes at least one fan and at least one dehumidifier, wherein the control device obtains a rotation speed and a dehumidification switch instruction from a rule database according to the temperature, the humidity and the illuminance, and according to the rotation speed and The dehumidification switch instructs to control the at least one fan and the at least one dehumidifier respectively, wherein the rule database is based on fuzzy logic. A method for monitoring fruits and vegetables is suitable for monitoring at least one fruits and vegetables grown in a farm. The method for monitoring fruits and vegetables includes: Shoot the at least one fruit and vegetable to obtain at least one image; and Determining a maturity level and a location information of the at least one fruit and vegetable based on the at least one image includes: Estimate a stalk harvest position based on a relative position relationship, where the position information includes a fruit position and the stalk harvest position, the fruit position includes a top position and a bottom position of a fruit corresponding to the vegetable and fruit, and the relative position The relationship is based on the correspondence between the top position and the bottom position, and the stalk harvest position is a position for cutting an external object. For example, the vegetable and fruit monitoring method described in item 6 of the scope of patent application, wherein the relative position relationship includes length information and an extension line from the bottom position to the top position, and the stalk harvest is estimated based on the relative position relationship The location steps include: Obtain the length information corresponding to the fruit based on the top position and the bottom position; and Estimate the harvest position of the stalk based on the length information and the extension line. For the vegetable and fruit monitoring method described in item 6 of the scope of patent application, the step of judging the ripeness of the at least one vegetable and fruit according to the at least one image includes: Determine the maturity level according to the location information and the color distribution of the corresponding fruit in the at least one image; Divide the farm into multiple areas; and The yield information of each region is estimated based on the ripeness of the at least one fruit and vegetable. For example, the vegetable and fruit monitoring method described in item 6 of the scope of patent application includes: Controlling a harvesting device to move according to the position information; and The harvesting device is controlled to harvest the corresponding fruits and vegetables according to the harvesting position of the stalk. For example, the vegetable and fruit monitoring method described in item 6 of the scope of patent application includes: Sensing the temperature, humidity and illuminance in the farm; Deriving a rotation speed and a dehumidification switch instruction from a rule database based on the temperature, the humidity and the illuminance, wherein the rule database is based on fuzzy logic; and At least one fan and at least one dehumidifier are respectively controlled according to the rotation speed and the instruction of the dehumidification switch.

Images