Vegetable and fruit growth and development regulation and control method, device and equipment and storage medium

Abstract

The invention relates to the technical field of agricultural production, and discloses a vegetable and fruit growth and development regulation and control method, device and equipment and a storage medium. The method comprises the steps of obtaining a target vegetable and fruit image; inputting the target vegetable and fruit image into a vegetable and fruit recognition model to obtain a vegetable and fruit recognition result; performing growth cycle statistical analysis on the target vegetables and fruits according to the vegetable and fruit recognition result to obtain growth cycle distribution of the target vegetables and fruits; according to the growth cycle distribution of the target vegetables and fruits, target environment parameters of the environment where the target vegetables and fruits are located are regulated and controlled, and the target environment parameters are made to be matched with the growth cycle distribution of the target vegetables and fruits. According to the embodiment of the invention, the accuracy of identifying the growth cycle of vegetables and fruits can be improved, and the vegetables and fruits can grow and develop in a required environment.

Description

Technical Field

[0001] The present application relates to the field of agricultural production technology, and in particular to a method, device, equipment and storage medium for regulating the growth and development of fruits and vegetables. Background Art

[0002] There are many influencing factors in the growth and development of fruits and vegetables, which can be divided into external environmental factors and internal genetic factors. External environmental factors can be regulated to improve the yield or quality of fruits and vegetables.

[0003] In the related art, the regulation of external environmental factors that affect the growth and development of fruits and vegetables only stays at the use of corresponding sensors for detection and relies on manual observation and adjustment. It is too dependent on experience and inefficient. It is impossible to efficiently and accurately identify the growth cycle of fruits and vegetables and enable them to grow and develop in the required environment. Summary of the invention

[0004] The purpose of the present application is to provide a method, device, equipment and storage medium for regulating the growth and development of fruits and vegetables, which can improve the accuracy of identifying the growth cycle of fruits and vegetables and enable fruits and vegetables to grow and develop in a desired environment.

[0005] The present application provides a method for regulating the growth and development of fruits and vegetables, comprising:

[0006] Acquire target fruit and vegetable images;

[0007] Inputting the target fruit and vegetable image into a fruit and vegetable recognition model to obtain a fruit and vegetable recognition result; the fruit and vegetable recognition result includes category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and the fruit and vegetable recognition model is obtained by training a neural network model based on a YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information;

[0008] According to the vegetable and fruit identification results, statistical analysis is performed on the growth cycles of the target vegetables and fruits to obtain the growth cycle distribution of the target vegetables and fruits;

[0009] According to the growth cycle distribution of the target fruits and vegetables, the target environmental parameters of the environment where the target fruits and vegetables are located are regulated so that the target environmental parameters match the growth cycle distribution of the target fruits and vegetables.

[0010] In some embodiments, inputting the target fruit and vegetable image into a fruit and vegetable recognition model to obtain a fruit and vegetable recognition result includes:

[0011] Performing a convolution operation on the target fruit and vegetable image to obtain a first feature map, a second feature map, and a third feature map; the first feature map includes quantity information of the target fruit and vegetable, the second feature map includes morphological information of the target fruit and vegetable, and the third feature map includes size information of the target fruit and vegetable;

[0012] Performing feature fusion on the first feature map, the second feature map, and the third feature map to obtain a first fused feature map, a second fused feature map, and a third fused feature map;

[0013] The first fusion feature map, the second fusion feature map, and the third fusion feature map are normalized, and the category and growth cycle of the target fruit and vegetable are predicted according to the normalization results to obtain the fruit and vegetable recognition results.

[0014] In some embodiments, the performing feature fusion on the first feature map, the second feature map, and the third feature map to obtain a first fused feature map, a second fused feature map, and a third fused feature map includes:

[0015] After performing a convolution operation and upsampling on the first feature map, performing feature map fusion with the second feature map to obtain an intermediate fused feature map, and after performing a convolution operation and upsampling on the intermediate fused feature map, performing feature map fusion with the third feature map to obtain the first fused feature map;

[0016] Performing a convolution operation and downsampling on the first fused feature map, and then performing feature map fusion with the intermediate fused feature map to obtain the second fused feature map;

[0017] The second fused feature map is convolved and down-sampled, and then fused with the first feature map to obtain the third fused feature map.

[0018] In some embodiments, performing a growth cycle statistical analysis on the target fruits and vegetables based on the fruit and vegetable identification results to obtain a growth cycle distribution of the target fruits and vegetables includes:

[0019] Determining the growth cycle of the target fruit and vegetable according to the category information and the growth cycle information;

[0020] The growth cycles of the target fruits and vegetables are summarized, and the proportions of the target fruits and vegetables in the same growth cycle are calculated to obtain the growth cycle distribution of the target fruits and vegetables.

[0021] In some embodiments, the target environmental parameters of the environment where the target fruits and vegetables are located are regulated according to the growth cycle distribution of the target fruits and vegetables so that the target environmental parameters match the growth cycle distribution of the target fruits and vegetables, including:

[0022] Determine whether the proportion of target fruits and vegetables in the same growth cycle exceeds a preset proportion threshold;

[0023] If it exceeds, adjusting the target environmental parameter so that the target environmental parameter is configured as the environmental parameter reference value of the target fruit or vegetable in the growth cycle;

[0024] If not, the target environmental parameter is adjusted so that the target environmental parameter is configured as the environmental parameter reference value of the target fruit or vegetable in the currently measured growth cycle.

[0025] In some embodiments, the target environmental parameters include carbon dioxide concentration parameters, environmental temperature and humidity parameters, and light intensity parameters, and regulating the target environmental parameters includes:

[0026] When the carbon dioxide concentration parameter and the temperature and humidity parameters are both higher than the corresponding environmental parameter reference values, the exhaust device is started, and the exhaust device is stopped until the carbon dioxide concentration parameter and the environmental temperature and humidity parameters are both no higher than the corresponding environmental parameter reference values, and the humidifier or carbon dioxide generator is started and controlled;

[0027] When the carbon dioxide concentration parameter or the ambient temperature and humidity parameter is higher than the corresponding environmental parameter reference value, start the exhaust device, and when both the carbon dioxide concentration parameter and the ambient temperature and humidity parameter are no higher than the corresponding environmental parameter reference value, start the humidifier or the carbon dioxide generator;

[0028] When the carbon dioxide concentration parameter, the environmental temperature and humidity parameter and / or the light intensity parameter are lower than the corresponding environmental parameter reference values, the humidifier, the carbon dioxide generator and / or the lighting device are started.

[0029] In some embodiments, before inputting the target fruit and vegetable image into the fruit and vegetable recognition model to obtain the fruit and vegetable recognition result, the method further includes:

[0030] Acquire multiple groups of sample vegetable and fruit images;

[0031] Performing data enhancement processing on the sample vegetable and fruit images to obtain multiple groups of sample enhanced images;

[0032] The neural network model is trained using the sample enhanced image, and when the neural network model meets the training end condition, the fruit and vegetable recognition model is obtained.

[0033] The present application also provides a device for regulating the growth and development of fruits and vegetables, comprising:

[0034] The first module is used to obtain the target fruit and vegetable image;

[0035] The second module is used to input the target fruit and vegetable image into the fruit and vegetable recognition model to obtain a fruit and vegetable recognition result; the fruit and vegetable recognition result includes the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and the fruit and vegetable recognition model is obtained by training a neural network model based on the YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information;

[0036] The third module is used to perform a growth cycle statistical analysis on the target fruits and vegetables according to the fruit and vegetable identification results to obtain the growth cycle distribution of the target fruits and vegetables;

[0037] The fourth module is used to adjust the target environmental parameters of the environment where the target vegetables and fruits are located according to the growth cycle distribution of the target vegetables and fruits, so that the target environmental parameters match the growth cycle distribution of the target vegetables and fruits.

[0038] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned method for regulating the growth and development of fruits and vegetables when executing the computer program.

[0039] The embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for regulating the growth and development of fruits and vegetables is implemented.

[0040] The beneficial effects of the present application are as follows: the target fruit and vegetable images are identified using a pre-trained fruit and vegetable recognition model, and a fruit and vegetable recognition result including the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image is obtained, and then the growth cycle statistical analysis of the target fruit and vegetable recognition result is performed, and according to the growth cycle distribution of the target fruit and vegetable, the target environmental parameters of the environment where the target fruit and vegetable are located are regulated, so that the target environmental parameters match the growth cycle distribution of the target fruit and vegetable. Since the category and growth cycle of the target fruit and vegetable are first predicted by the pre-trained fruit and vegetable recognition model, the accuracy of identifying the growth cycle of the fruit and vegetable can be improved, and then the growth cycle distribution of the target fruit and vegetable is determined by the growth cycle statistical analysis, and then the target environmental parameters of the environment where the target fruit and vegetable are located are regulated, so that the regulated target environmental parameters are suitable for the growth and development of most of the target fruit and vegetable in the same growth cycle, so that the fruit and vegetable can grow and develop in the required environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of the method for regulating the growth and development of fruits and vegetables provided in the embodiments of the present application.

[0042] Figure 2 It is a flowchart of the specific method of step S102 provided in an embodiment of the present application.

[0043] Figure 3 It is a flowchart of the specific method of step S104 provided in an embodiment of the present application.

[0044] Figure 4 It is a flowchart of the method before step S102 provided in an embodiment of the present application.

[0045] Figure 5 It is a schematic diagram of the structure of the device for regulating the growth and development of fruits and vegetables provided in an embodiment of the present application.

[0046] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown can be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second" and the like in the specification, claims and drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0050] See also Figure 1 , Figure 1 is a flow chart of the method for regulating the growth and development of fruits and vegetables provided in the embodiments of the present application. In some embodiments of the present application, Figure 1 The method may specifically include but is not limited to steps S101 to S104. Figure 1 These four steps are introduced in detail.

[0051] Step S101, obtaining target vegetable and fruit images.

[0052] The target fruit and vegetable image can be transmitted to the electronic device by the image acquisition device.

[0053] After the electronic device acquires the target vegetable and fruit image, it saves the target vegetable and fruit image.

[0054] The target fruit and vegetable images can be obtained by taking multi-angle shots of fruits and vegetables grown in a target area by an image acquisition device and stitching the images together. The target area is a monitored planting area, such as a planting area in a greenhouse.

[0055] Step S102: input the target fruit and vegetable image into the fruit and vegetable recognition model to obtain the fruit and vegetable recognition result.

[0056] Among them, the fruit and vegetable recognition results include the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image. The fruit and vegetable recognition model is obtained by training a neural network model based on the YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information.

[0057] In the specific implementation, the target fruit and vegetable images are input into the fruit and vegetable recognition model, and the fruit and vegetable recognition model is used to extract the quantity characteristics, morphological characteristics and size characteristics of the target fruits and vegetables in the target fruit and vegetable images. According to the extracted quantity characteristics, morphological characteristics and size characteristics, each target fruit and vegetable is classified respectively to predict the category information and growth cycle information of the target fruit and vegetable, and obtain the fruit and vegetable recognition results.

[0058] See also Figure 2 , Figure 2 is a flowchart of a specific method of step S102 provided in an embodiment of the present application. In some embodiments of the present application, step S102 includes but is not limited to steps S201 to S203. Figure 2 These three steps are introduced in detail.

[0059] Step S201, performing a convolution operation on the target fruit and vegetable image to obtain a first feature map, a second feature map, and a third feature map.

[0060] The first feature map includes quantity information of target fruits and vegetables, the second feature map includes shape information of target fruits and vegetables, and the third feature map includes size information of target fruits and vegetables.

[0061] Step S202, performing feature fusion on the first feature map, the second feature map and the third feature map to obtain a first fused feature map, a second fused feature map and a third fused feature map.

[0062] Step S203, normalizing the first fused feature map, the second fused feature map, and the third fused feature map, and predicting the category and growth cycle of the target fruit and vegetable based on the normalization result to obtain a fruit and vegetable recognition result.

[0063] In the embodiment of the present application, the fruit and vegetable recognition model includes a convolution layer, a feature fusion layer and a normalization layer.

[0064] Step S201 is executed by calling the convolution layer of the fruit and vegetable recognition model, and the convolution layer of the fruit and vegetable recognition model has three convolution branches. In the specific implementation, the target fruit and vegetable images are respectively input into each convolution branch of the convolution layer, and the convolution operation is performed layer by layer. The last hidden layer of each convolution branch is connected to an activation module, and the activation module uses an activation function to activate the result of the last convolution operation of the convolution branch, thereby obtaining a first fusion feature map, a second fusion feature map or a third fusion feature map. In the training process of the fruit and vegetable recognition model, by adjusting the weight parameters of the convolution layer, the three convolution branches of the convolution layer respectively learn the quantity information, morphological information or size information of the target fruits and vegetables in the sample fruit and vegetable images, thereby the three convolution branches of the convolution layer can be used to perform convolution operations on the target fruit and vegetable images respectively, so as to extract local features of the target fruit and vegetable images, and obtain a first feature map containing the quantity information of the target fruits and vegetables, a second feature map containing the morphological information of the target fruits and vegetables, and a third feature map containing the size information of the target fruits and vegetables.

[0065] Step S202 is executed by calling the feature fusion layer of the fruit and vegetable recognition model. In the specific implementation, the first feature map, the second feature map and the third feature map are input into the feature fusion layer, and the first feature map, the second feature map and the third feature map are fused by combining upsampling and downsampling. Figure 3 The feature information in the two is fused at different scales to obtain a first fused feature map, a second fused feature map, and a third fused feature map.

[0066] In a specific embodiment, step S202 specifically includes: performing a convolution operation and upsampling on the first feature map, and then performing feature map fusion with the second feature map to obtain an intermediate fused feature map; performing a convolution operation and upsampling on the intermediate fused feature map, and then performing feature map fusion with the third feature map to obtain a first fused feature map; performing a convolution operation and downsampling on the first fused feature map, and then performing feature map fusion with the intermediate fused feature map to obtain a second fused feature map; performing a convolution operation and downsampling on the second fused feature map, and then performing feature map fusion with the first feature map to obtain a third fused feature map.

[0067] In the specific implementation, convolution operation, upsampling and downsampling are used to adjust the number of channels of the feature map. First, through convolution operation and upsampling, the first feature map, the second feature map and the third feature map are fused in turn to obtain a first fused feature map. Then, through convolution operation and downsampling, the first fused feature map and the intermediate fused feature map obtained by fusion of the first feature map and the second feature map are fused to obtain a second fused feature map. Then, through convolution operation and downsampling, the second fused feature map and the first feature map are fused to obtain a third fused feature map. The feature fusion layer outputs the first fused feature map, the second fused feature map and the third fused feature map. The first fused feature map, the second fused feature map and the third fused feature map have different scales and channel numbers, and contain the quantity information, morphological information and size information of the target fruits and vegetables, respectively, which can increase the receptive field of the fruit and vegetable recognition model.

[0068] Step S203 is executed by calling the normalization layer of the fruit and vegetable recognition model. In the specific implementation, the first fusion feature map, the second fusion feature map and the third fusion feature map are input into the normalization layer, and the first fusion feature map, the second fusion feature map and the third fusion feature map are normalized by using the softmax function. Figure 3 The categories and growth cycles of the target fruits and vegetables are converted into probability forms to obtain the first fusion feature map, the second fusion feature map and the third fusion feature map. Figure 3 The corresponding pre-recognition results are then weighted fitting processed to obtain the fruit and vegetable recognition results.

[0069] Step S103, performing growth cycle statistics analysis on the target fruits and vegetables according to the fruit and vegetable identification results to obtain growth cycle distribution of the target fruits and vegetables.

[0070] In a specific implementation, based on the fruit and vegetable recognition results, the current growth cycle of each target fruit and vegetable in the target fruit and vegetable image is determined, and a growth cycle statistical analysis is performed on the target fruits and vegetables to determine the proportion of the target fruits and vegetables in each growth cycle, thereby obtaining the growth cycle distribution of the target fruits and vegetables.

[0071] In a specific embodiment, step S103 specifically includes: determining the growth cycle of the target fruits and vegetables according to the category information and the growth cycle information; summarizing the growth cycle of each target fruit and vegetable, calculating the proportion of the target fruits and vegetables in the same growth cycle, and obtaining the growth cycle distribution of the target fruits and vegetables.

[0072] In a specific implementation, the types and growth cycles of target fruits and vegetables are determined based on the category information and growth cycle information in the fruit and vegetable identification results, the growth cycles of the same target fruits and vegetables are summarized, and the proportion of target fruits and vegetables in the same growth cycle is calculated to obtain the growth cycle distribution of the target fruits and vegetables. For example, the growth cycle of Chinese cabbage includes the germination period, seedling period, rosette period, fruiting period and harvest period. The number of Chinese cabbages in each growth cycle is calculated respectively, thereby determining the growth cycle distribution of Chinese cabbage.

[0073] Step S104, according to the growth cycle distribution of the target fruits and vegetables, the target environmental parameters of the environment where the target fruits and vegetables are located are adjusted to match the growth cycle distribution of the target fruits and vegetables.

[0074] In a specific implementation, based on the growth cycle distribution of target fruits and vegetables, if the proportion of target fruits and vegetables in the same growth cycle reaches a certain level, the target environmental parameters of the environment in which the target fruits and vegetables are located are adjusted so that the target environmental parameters are configured as the environmental parameter reference values ​​of the target fruits and vegetables in the growth cycle, so that most of the target fruits and vegetables grow and develop within the optimal target environmental parameters. Conversely, the target environmental parameters are configured as the environmental parameter reference values ​​of the target fruits and vegetables in the currently measured growth cycle, so that most of the target fruits and vegetables grow and develop within the preset target environmental parameters, which complies with the growth and development laws of fruits and vegetables.

[0075] See also Figure 3 , Figure 3 is a flowchart of a specific method of step S104 provided in an embodiment of the present application. In some embodiments of the present application, step S104 includes but is not limited to steps S301 to S303. Figure 3 These three steps are introduced in detail.

[0076] Step S301, determining whether the ratio of target fruits and vegetables in the same growth cycle exceeds a preset ratio threshold. If so, executing step S302; if not, executing step S303.

[0077] Step S302, regulating the target environmental parameters so that the target environmental parameters are configured as reference values ​​of the environmental parameters of the target fruits and vegetables in the growth cycle.

[0078] Step S303, regulating the target environmental parameters so that the target environmental parameters are configured as reference values ​​of the environmental parameters of the target fruits and vegetables in the currently measured growth cycle.

[0079] Optionally, the preset ratio threshold is set to 80%.

[0080] In a specific implementation, according to the growth cycle distribution of the target fruits and vegetables, the proportion of the target fruits and vegetables in each growth cycle is compared with the preset proportion threshold. If the proportion of the target fruits and vegetables in the same growth cycle exceeds the preset proportion threshold, it means that the growth cycles of most of the target fruits and vegetables are concentrated. By regulating the target environmental parameters of the environment in which the target fruits and vegetables are located, the target environmental parameters are configured as the reference values ​​of the environmental parameters of the target fruits and vegetables in the growth cycle, so that most of the target fruits and vegetables grow and develop within the optimal target environmental parameters. On the contrary, if the proportion of the target fruits and vegetables in the same growth cycle does not exceed the preset proportion threshold, it means that the growth cycle of the target fruits and vegetables is not concentrated. The target environmental parameters should be regulated according to the predetermined cultivation plan, so that the target environmental parameters are configured as the reference values ​​of the environmental parameters of the target fruits and vegetables in the currently measured growth cycle, so that most of the target fruits and vegetables grow and develop within the preset target environmental parameters, which conforms to the growth and development laws of fruits and vegetables.

[0081] In a specific embodiment, the target environmental parameters include carbon dioxide concentration parameters, environmental temperature and humidity parameters, and light intensity parameters, and regulating the target environmental parameters specifically includes:

[0082] When the carbon dioxide concentration parameter and the temperature and humidity parameters are higher than the corresponding environmental parameter reference values, the exhaust device is started, and it stops when the carbon dioxide concentration parameter and the environmental temperature and humidity parameters are no higher than the corresponding environmental parameter reference values, and the humidifier or carbon dioxide generator is started and controlled;

[0083] When the carbon dioxide concentration parameter or the ambient temperature and humidity parameter is higher than the corresponding environmental parameter reference value, the exhaust device is started, and when both the carbon dioxide concentration parameter and the ambient temperature and humidity parameter are no higher than the corresponding environmental parameter reference value, the humidifier or carbon dioxide generator is started;

[0084] When the carbon dioxide concentration parameter, the ambient temperature and humidity parameter and / or the light intensity parameter are lower than the corresponding ambient parameter reference value, the humidifier, the carbon dioxide generator and / or the lighting device are started.

[0085] See also Figure 4 , Figure 4 is a flowchart of the method before step S102 provided in the embodiment of the present application. In some embodiments of the present application, the method includes but is not limited to steps S401 to S403. Figure 4 These three steps are introduced in detail.

[0086] Step S401, obtaining multiple groups of sample vegetable and fruit images.

[0087] Step S402, performing data enhancement processing on the sample vegetable and fruit images to obtain multiple groups of sample enhanced images.

[0088] Step S403, using the sample enhanced image to train the neural network model, when the neural network model meets the training end condition, a fruit and vegetable recognition model is obtained.

[0089] In step S401, the fruits and vegetables grown in multiple areas are photographed from multiple angles by an image acquisition device and multiple groups of sample fruit and vegetable images are obtained after image stitching. After the multiple groups of sample fruit and vegetable images are obtained, the categories and growth cycles of the fruits and vegetables in the sample fruit and vegetable images are marked, for example, by using the LabelImg tool.

[0090] In step S402, data enhancement processing is performed on the sample vegetable and fruit images, which may be random rotation processing, random scaling processing, adding noise and / or symmetry processing to obtain multiple groups of sample enhanced images, thereby forming a constructed data set.

[0091] In step S403, 70% of the sample enhanced images are used as training images, 20% of the sample enhanced images are used as verification images, and 10% of the sample enhanced images are used as test images. The training images are then input into the neural network model to train the neural network model. It is determined whether the neural network model meets the training end condition based on the model loss information of the neural network model, and the weight parameters of the neural network model are updated using the gradient descent method. Specifically, the gradient of the model loss information with respect to the weight parameters of the neural network model is calculated, and the weight parameters of the neural network model are iteratively updated according to the preset learning rate and the calculated gradient until the model loss information meets the loss condition (the loss value no longer decreases significantly) or the number of iterations reaches the threshold number, and the training is terminated to obtain a fruit and vegetable recognition model.

[0092] See also Figure 5 The embodiment of the present application also provides a device for regulating the growth and development of fruits and vegetables, which can implement the above-mentioned method for regulating the growth and development of fruits and vegetables, and the device comprises:

[0093] The first module 501 is used to obtain target fruit and vegetable images;

[0094] The second module 502 is used to input the target fruit and vegetable image into the fruit and vegetable recognition model to obtain the fruit and vegetable recognition result; the fruit and vegetable recognition result includes the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and the fruit and vegetable recognition model is obtained by training a neural network model based on the YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information;

[0095] The third module 503 is used to perform growth cycle statistical analysis on the target fruits and vegetables according to the fruit and vegetable identification results to obtain the growth cycle distribution of the target fruits and vegetables;

[0096] The fourth module 504 is used to adjust the target environmental parameters of the environment where the target fruits and vegetables are located according to the growth cycle distribution of the target fruits and vegetables, so that the target environmental parameters match the growth cycle distribution of the target fruits and vegetables.

[0097] The specific implementation of the vegetable and fruit growth and development regulating device is basically the same as the specific implementation of the vegetable and fruit growth and development regulating method described above, and will not be repeated here.

[0098] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment.

[0099] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0100] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0101] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned vegetable and fruit growth and development regulation method part of this specification.

[0102] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0103] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0104] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0105] The electronic device 600 may also communicate with one or more external devices 600' (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for regulating the growth and development of fruits and vegetables is implemented.

[0107] The fruit and vegetable growth and development control method, device, equipment and storage medium provided in the embodiment of the present application use a pre-trained fruit and vegetable recognition model to identify the target fruit and vegetable image, obtain a fruit and vegetable recognition result containing the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and then perform a growth cycle statistical analysis on the target fruit and vegetable recognition result, and according to the growth cycle distribution of the target fruit and vegetable, control the target environmental parameters of the environment where the target fruit and vegetable are located, so that the target environmental parameters match the growth cycle distribution of the target fruit and vegetable. Since the category and growth cycle of the target fruit and vegetable are first predicted by the pre-trained fruit and vegetable recognition model, the accuracy of identifying the growth cycle of the fruit and vegetable can be improved, and then the growth cycle distribution of the target fruit and vegetable is determined by the growth cycle statistical analysis, and then the target environmental parameters of the environment where the target fruit and vegetable are located are controlled, so that the regulated target environmental parameters are suitable for the growth and development of most of the target fruit and vegetable in the same growth cycle, so that the fruit and vegetable grow and develop in the required environment.

[0108] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the implementation of the present disclosure.

[0109] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0110] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0111] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0112] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0113] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A method for regulating the growth and development of fruits and vegetables, characterized in that: include: Acquire target fruit and vegetable images; Inputting the target fruit and vegetable image into a fruit and vegetable recognition model to obtain a fruit and vegetable recognition result; The fruit and vegetable recognition result includes the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and the fruit and vegetable recognition model is obtained by training a neural network model based on a YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information; According to the vegetable and fruit identification results, statistical analysis is performed on the growth cycles of the target vegetables and fruits to obtain the growth cycle distribution of the target vegetables and fruits; According to the growth cycle distribution of the target fruits and vegetables, the target environmental parameters of the environment where the target fruits and vegetables are located are regulated so that the target environmental parameters match the growth cycle distribution of the target fruits and vegetables.

2. The method for regulating the growth and development of fruits and vegetables according to claim 1, characterized in that: The step of inputting the target fruit and vegetable image into a fruit and vegetable recognition model to obtain a fruit and vegetable recognition result includes: Performing a convolution operation on the target fruit and vegetable image to obtain a first feature map, a second feature map, and a third feature map; the first feature map includes quantity information of the target fruit and vegetable, the second feature map includes morphological information of the target fruit and vegetable, and the third feature map includes size information of the target fruit and vegetable; Performing feature fusion on the first feature map, the second feature map, and the third feature map to obtain a first fused feature map, a second fused feature map, and a third fused feature map; The first fusion feature map, the second fusion feature map, and the third fusion feature map are normalized, and the category and growth cycle of the target fruit and vegetable are predicted according to the normalization results to obtain the fruit and vegetable recognition results.

3. The method for regulating the growth and development of fruits and vegetables according to claim 2, characterized in that: The step of fusing the first feature map, the second feature map, and the third feature map to obtain a first fused feature map, a second fused feature map, and a third fused feature map includes: After performing a convolution operation and upsampling on the first feature map, performing feature map fusion with the second feature map to obtain an intermediate fused feature map, and after performing a convolution operation and upsampling on the intermediate fused feature map, performing feature map fusion with the third feature map to obtain the first fused feature map; Performing a convolution operation and downsampling on the first fused feature map, and then performing feature map fusion with the intermediate fused feature map to obtain the second fused feature map; The second fused feature map is convolved and down-sampled, and then fused with the first feature map to obtain the third fused feature map.

4. The method for regulating the growth and development of fruits and vegetables according to claim 1, characterized in that: The step of performing a growth cycle statistical analysis on the target fruits and vegetables according to the fruit and vegetable identification results to obtain a growth cycle distribution of the target fruits and vegetables includes: Determining the growth cycle of the target fruit and vegetable according to the category information and the growth cycle information; The growth cycles of the target fruits and vegetables are summarized, and the proportions of the target fruits and vegetables in the same growth cycle are calculated to obtain the growth cycle distribution of the target fruits and vegetables.

5. The method for regulating the growth and development of fruits and vegetables according to claim 1, characterized in that: According to the growth cycle distribution of the target fruits and vegetables, the target environmental parameters of the environment where the target fruits and vegetables are located are adjusted so that the target environmental parameters match the growth cycle distribution of the target fruits and vegetables, including: Determine whether the proportion of target fruits and vegetables in the same growth cycle exceeds a preset proportion threshold; If it exceeds, adjusting the target environmental parameter so that the target environmental parameter is configured as the environmental parameter reference value of the target fruit or vegetable in the growth cycle; If not, the target environmental parameter is adjusted so that the target environmental parameter is configured as the environmental parameter reference value of the target fruit or vegetable in the currently measured growth cycle.

6. The method for regulating the growth and development of fruits and vegetables according to claim 5, characterized in that: The target environmental parameters include a carbon dioxide concentration parameter, an environmental temperature and humidity parameter, and a light intensity parameter. The regulating the target environmental parameters includes: When the carbon dioxide concentration parameter and the temperature and humidity parameters are both higher than the corresponding environmental parameter reference values, the exhaust device is started, and the exhaust device is stopped until the carbon dioxide concentration parameter and the environmental temperature and humidity parameters are both no higher than the corresponding environmental parameter reference values, and the humidifier or carbon dioxide generator is started and controlled; When the carbon dioxide concentration parameter or the ambient temperature and humidity parameter is higher than the corresponding environmental parameter reference value, start the exhaust device, and when both the carbon dioxide concentration parameter and the ambient temperature and humidity parameter are no higher than the corresponding environmental parameter reference value, start the humidifier or the carbon dioxide generator; When the carbon dioxide concentration parameter, the environmental temperature and humidity parameter and / or the light intensity parameter are lower than the corresponding environmental parameter reference values, the humidifier, the carbon dioxide generator and / or the lighting device are started.

7. The method for regulating the growth and development of fruits and vegetables according to any one of claims 1 to 6, characterized in that: Before inputting the target fruit and vegetable image into the fruit and vegetable recognition model to obtain the fruit and vegetable recognition result, the method further includes: Acquire multiple groups of sample vegetable and fruit images; Performing data enhancement processing on the sample vegetable and fruit images to obtain multiple groups of sample enhanced images; The neural network model is trained using the sample enhanced image, and when the neural network model meets the training end condition, the fruit and vegetable recognition model is obtained.

8. A device for regulating the growth and development of fruits and vegetables, characterized in that: include: The first module is used to obtain the target fruit and vegetable image; The second module is used to input the target fruit and vegetable image into the fruit and vegetable recognition model to obtain a fruit and vegetable recognition result; the fruit and vegetable recognition result includes the category information and growth cycle information of each target fruit and vegetable in the target fruit and vegetable image, and the fruit and vegetable recognition model is obtained by training a neural network model based on the YOLO architecture using multiple groups of sample fruit and vegetable images of target fruits and vegetables containing different category information and / or different growth cycle information; The third module is used to perform a growth cycle statistical analysis on the target fruits and vegetables according to the fruit and vegetable identification results to obtain the growth cycle distribution of the target fruits and vegetables; The fourth module is used to adjust the target environmental parameters of the environment where the target vegetables and fruits are located according to the growth cycle distribution of the target vegetables and fruits, so that the target environmental parameters match the growth cycle distribution of the target vegetables and fruits.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method for regulating the growth and development of fruits and vegetables according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for regulating the growth and development of fruits and vegetables according to any one of claims 1 to 7 is implemented.

Images