Rhododendron pulchrum phenological period automatic identification method and device, terminal and storage medium

Abstract

The invention provides an automatic identification method and device for the phenological period of rhododendron pulchrum, a terminal and a storage medium. The rhododendron pink phenological period automatic identification method comprises the following steps: using a phenological camera to shoot images of rhododendron pink at fixed time and fixed point every day; representative images under different weather and different illumination conditions are screened out from the images, and the representative images are marked; dividing the marked images into training set images and verification set images; performing data enhancement processing on the training set image to obtain a processed training set image; performing model training on a YOLO model by using the processed training set image to obtain a trained model; and detecting the images of the Rhododendron pink by using the trained model, and outputting the target label, the confidence coefficient and the position coordinate of the detection frame detected on each image. According to the method, the consumption of manpower and material resources can be greatly reduced, automatic observation of the phenological period of the Rhododendron pulchrum can still be realized under the condition of severe weather, and the observation standard is relatively unified in long-time-sequence observation.

Description

Technical Field

[0001] The present disclosure relates to the fields of computer vision and ecology, and in particular to a method and device, a terminal and a storage medium for automatically identifying the phenological period of azalea. Background Art

[0002] At present, the individual phenological monitoring of the pink and white azalea is mainly carried out through manual field observation, which is time-consuming and labor-intensive. In addition, the subjective judgment of different monitors will lead to deviations in the phenological period, resulting in unstable observation periods for the phenological detection of the pink and white azalea and inconsistent judgments on the phenological period due to different observers from year to year. Summary of the invention

[0003] In order to solve the existing problems, the present invention provides a method and device, a terminal and a storage medium for automatically identifying the phenological period of pink and white azalea.

[0004] The present disclosure adopts the following technical solutions.

[0005] An embodiment of the present disclosure provides a method for automatically identifying the phenological period of pink and white azalea, and the method comprises: using a phenological camera to take images of pink and white azalea at a fixed time and point every day; selecting representative images under different weather and different lighting conditions from the images, annotating the representative images, and annotating the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image; dividing the annotated images into training set images and verification set images; performing data enhancement processing on the training set images to obtain processed training set images; using the processed training set images to perform model training on a YOLO model to obtain a trained model; using the trained model to detect the images of pink and white azalea, and outputting the target label, confidence and position coordinates of the detection box detected on each image.

[0006] Another embodiment of the present disclosure provides an automatic recognition device for the phenological period of pink and white azalea, and the processing device includes: an image acquisition module, configured to use a phenological camera to take images of pink and white azalea at a fixed time and point every day; a screening and annotation module, configured to screen representative images under different weather and different lighting conditions from the images, annotate the representative images, and annotate the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of pink and white azalea in each image; an image classification module, configured to divide the annotated images into training set images and verification set images; an image processing module, configured to perform data enhancement processing on the training set images to obtain processed training set images; a model training module, configured to perform model training on a YOLO model using the processed training set images to obtain a trained model; a detection module, configured to use the trained model to detect the images of pink and white azalea, and output the target label, confidence and position coordinates of the detection box detected on each image.

[0007] In some embodiments, the present disclosure provides a terminal, comprising: at least one memory and at least one processor; wherein the memory is used to store program codes, and the processor is used to call the program codes stored in the memory to execute the above-mentioned method for automatically identifying the phenological period of pink and white azalea.

[0008] In some embodiments, the present disclosure provides a storage medium, wherein the storage medium is used to store program code, and the program code is used to execute the above-mentioned method for automatically identifying the phenological period of pink and white azalea.

[0009] Compared with traditional manual observation, the automatic identification method disclosed in the present invention greatly reduces the consumption of manpower and material resources, and can still realize automatic observation of the phenological period of pink and white azalea under severe weather conditions. The observation standard is relatively unified in long-term observations, and the model calculation is relatively rapid. It can well complete the automatic observation of the phenology of pink and white azalea, and further analyze its relationship with environmental meteorological factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0011] Figure 1 It is a flow chart of the method for automatically identifying the phenological period of pink and white azalea according to an embodiment of the present disclosure.

[0012] Figure 2 is a schematic diagram of a labeled pink and white azalea image according to an embodiment of the present disclosure.

[0013] Figure 3A schematic diagram of a validation set confusion matrix according to some embodiments is shown.

[0014] Figure 4 A schematic diagram showing an image output by a model according to some embodiments.

[0015] Figure 5 A schematic diagram showing the growth and development changes of a Rhododendron australis throughout a year according to some embodiments.

[0016] Figure 6 It is a partial module of the automatic identification device for the phenological period of pink and white azalea of ​​another embodiment of the present disclosure.

[0017] Figure 7 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in sequence and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0020] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modification of “one” mentioned in the present disclosure is illustrative rather than restrictive, and those skilled in the art should understand that it should be understood as “one or more” unless otherwise clearly indicated in the context.

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] YOLO (You Only Look Once) is an image-based artificial intelligence computer model that can be used to perform tasks such as target detection, semantic segmentation, and instance segmentation. The present invention uses YOLO11n for model training, and automatically recognizes the phenological period of Rhododendron rubra by identifying key objects of Rhododendron rubra (such as flowers, fruits, buds, etc.).

[0025] Figure 1 A flow chart of the method for automatically identifying the phenological period of azalea of ​​the embodiment of the present disclosure is provided. The method for automatically identifying the phenological period of azalea of ​​the present disclosure may include step S101, using a phenological camera to take images of azalea at a fixed time and point every day. In a specific embodiment, a phenological camera is used to take high-resolution images of azalea at a fixed time and point every day, and a total of 1813 images are obtained, with a time span from October 1, 2023 to September 30, 2024. In some embodiments, the phenological camera may be a commonly used RGB camera.

[0026] In some embodiments, the method of the present disclosure may further include step S102, screening out representative images under different weather and different lighting conditions from the acquired images, annotating the representative images, and marking the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers, and flower buds of the pink and white azalea in each image. In some embodiments, marking the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers, and flower buds of the pink and white azalea in each image includes: marking the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers, and flower buds of the pink and white azalea in each image as 0, 1, 2, 3, 4, 5, 6, and 7, respectively. In a specific embodiment, a total of 434 images with strong representativeness under different weather and different lighting conditions are screened out from the acquired pink and white azalea images, and these images are annotated, such as Figure 2 As shown in the figure, labelimg is used to annotate the yellow leaves, buds (in the early stages of development when it is impossible to distinguish whether they are flower buds or leaf buds), flower buds, fruits, leaf buds, new leaves, flowers, and flower buds of the pink-white azalea in each image, and they are recorded as 0, 1, 2, 3, 4, 5, 6, and 7 respectively.

[0027] In some embodiments, the method of the present disclosure may further include step S103, dividing the labeled images into training set images and verification set images. In some specific embodiments, the labeled images are divided into two parts: training set images and verification set images, wherein the training set images include 334 images and the verification set images include 100 images.

[0028] In some embodiments, the method disclosed herein may further include step S104, performing data enhancement processing on the training set images to obtain processed training set images. In some embodiments, performing data enhancement processing on the training set images to obtain processed training set images includes: using five methods to randomly process the training set images, repeating four times, and obtaining a total of five times the number of processed training set images of the training set images. In some embodiments, the five methods include flipping, rotation, affine transformation, color jittering, and grayscale conversion. Flipping means that the left and right sides of the image are swapped; rotation means randomly rotating the image by multiples of 0 degrees, 90 degrees, 180 degrees, and 270 degrees; affine transformation means randomly scaling, rotating, and shearing the image; color jittering means randomly changing the brightness, contrast, and saturation of the image; and grayscale conversion means converting the image into a grayscale image. In some specific embodiments, data enhancement is performed on the training set images, and the above five methods are used to randomly process the images, repeating four times, and a total of 1,670 images for training are obtained. The data enhancement method is shown in Table 1 below.

[0029] Table 1

[0030]

[0031]

[0032] In some embodiments, the method disclosed herein may further include step S105, using the processed training set images to perform model training on the YOLO model to obtain a trained model. In some embodiments, YOLO11n is used to perform model training on the processed training set images, and the model training is performed on a DELL Precision 7560 mobile workstation, wherein the operating system is Windows 11, the CPU is 11th Gen Intel(R) Core(TM) i7-11850H, and the graphics card is NVIDIA RTX A2000; Pytorch2.5.1 based on CUDA12.4 is built, and the programming language is Python3.9; the training parameter Epoch size is 400, the batch size (Batch size) is set to 8, the initial image size is 640×640, and the AdamW optimizer is used and the initial learning rate is set to 0.01.

[0033] In some embodiments, the automatic recognition method of the present disclosure further includes: using the optimal model weights to detect the validation set images to obtain a validation set confusion matrix. In some embodiments, after training, the validation set images are detected using the obtained optimal model weights to obtain the following: Figure 3 The validation set confusion matrix is ​​shown.

[0034] In some embodiments, the method of the present disclosure may further include step S106, using the trained model to detect the image of the pink and white azalea, and outputting the target label, confidence, and position coordinates of the detection box detected on each image. In some embodiments, the optimal weight file best.pt obtained by the trained model is used to detect 1813 images obtained from October 1, 2023 to September 30, 2024, and outputs the target label, confidence, and XY coordinates of the detection box detected on each image (such as Figure 4 shown).

[0035] In some embodiments, the automatic identification method of the present disclosure further includes: generating the phenological period of the pink-white azalea in each image based on the detected target label. In some specific embodiments, the phenological period of each image is generated based on the detected target, and the growth and development changes of the object for the whole year from October 2023 to October 2024 are plotted, see Figure 5 , and then correspond to the corresponding phenological period according to Table 2 below.

[0036] Table 2

[0037]

[0038] Compared with traditional manual observation, the automatic identification method disclosed in the present invention greatly reduces the consumption of manpower and material resources, and can still realize automatic observation of the phenological period of pink and white azalea under severe weather conditions. The observation standard is relatively unified in long-term observations, and the model calculation is relatively rapid. It can well complete the automatic observation of the phenology of pink and white azalea, and further analyze its relationship with environmental meteorological factors.

[0039] The embodiment of the present disclosure also provides an automatic identification device 400 for the phenological period of Rhododendron rubra. Figure 6The automatic identification device 400 of the phenological period of pink and white azalea according to some embodiments is shown. The automatic identification device 400 of the phenological period of pink and white azalea includes an image acquisition module 401, a screening and annotation module 402, an image classification module 403, an image processing module 404, a model training module 405 and a detection module 406. In some embodiments, the image acquisition module 401 is configured to use a phenological camera to take images of pink and white azalea at a fixed time and point every day. In some embodiments, the screening and annotation module 402 is configured to filter out representative images under different weather and different lighting conditions from the image, annotate the representative images, and annotate the yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of pink and white azalea in each image. In some embodiments, the image classification module 403 is configured to divide the annotated images into training set images and verification set images. In some embodiments, the image processing module 404 is configured to perform data enhancement processing on the training set images to obtain processed training set images. In some embodiments, the model training module 405 is configured to perform model training on the YOLO model using the processed training set images to obtain a trained model. In some embodiments, the detection module 406 is configured to detect images of the pink and white azalea using a trained model, and output the detected target label, confidence level, and position coordinates of the detection box on each image.

[0040] It should be understood that the contents described about the method for automatically identifying the phenological period of pink-white azalea are also applicable to the automatic device 400 for automatically identifying the phenological period of pink-white azalea herein, and for the sake of simplicity, a detailed description is not given here.

[0041] In some embodiments, marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image includes: marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image as 0, 1, 2, 3, 4, 5, 6, 7 respectively. In some embodiments, performing data enhancement processing on the training set images to obtain processed training set images includes: randomly processing the training set images using five methods, repeating four times, and obtaining a total of five times the number of processed training set images as the training set images. In some embodiments, the five methods include flipping, rotating, affine transformation, color jittering and grayscale conversion. In some embodiments, the YOLO model is trained using the processed training set images to obtain the trained model, including: using YOLO11n to train the processed training set images, the model training is performed on a DELL Precision 7560 mobile workstation, wherein the operating system is Windows 11, the CPU is 11th GenIntel(R)Core(TM)i7-11850H, and the graphics card is NVIDIA RTX A2000; Pytorch2.5.1 based on CUDA12.4 is built, and the programming language is Python3.9; the training parameter Epoch size is 400, the batch size is set to 8, the initial image size is 640×640, and the AdamW optimizer is used and the initial learning rate is set to 0.01. In some embodiments, the detection module is also configured to: use the optimal model weight to detect the validation set image to obtain the validation set confusion matrix. In some embodiments, the automatic recognition device for the phenological period of pink and white azalea also includes: a generation module, configured to generate the phenological period of pink and white azalea in each image based on the detected target label.

[0042] In addition, the present disclosure also provides a terminal, including: at least one memory and at least one processor; wherein the memory is used to store program codes, and the processor is used to call the program codes stored in the memory to execute the above-mentioned method for automatically identifying the phenological period of pink and white azalea.

[0043] In addition, the present disclosure also provides a computer storage medium, which stores a program code, and the program code is used to execute the above-mentioned method for automatically identifying the phenological period of pink and white azalea.

[0044] The above describes the method and device for automatically identifying the phenological period of the pink-white azalea according to the present disclosure based on the embodiments and application examples. In addition, the present disclosure also provides a terminal and a storage medium, which are described below.

[0045] Reference below Figure 7, which shows a schematic diagram of the structure of an electronic device (such as a terminal device or a server) 500 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0046] like Figure 7 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0047] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0048] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0049] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-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 computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0050] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0051] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0052] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method of the present disclosure.

[0053] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0054] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0055] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0056] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0057] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 foregoing.

[0058] According to one or more embodiments of the present disclosure, a method for automatically identifying the phenological period of pink and white azalea is provided, and the method comprises: using a phenological camera to take images of pink and white azalea at a fixed time and point every day; selecting representative images under different weather and lighting conditions from the images, annotating the representative images, and annotating the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of pink and white azalea in each image; dividing the annotated images into training set images and validation set images; performing data enhancement processing on the training set images to obtain processed training set images; using the processed training set images to perform model training on a YOLO model to obtain a trained model; using the trained model to detect images of pink and white azalea, and outputting the target label, confidence and position coordinates of the detection box detected on each image.

[0059] According to one or more embodiments of the present disclosure, marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image includes: marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image as 0, 1, 2, 3, 4, 5, 6, 7 respectively.

[0060] According to one or more embodiments of the present disclosure, data enhancement processing is performed on the training set images to obtain processed training set images, including: using five methods to randomly process the training set images, repeating four times, and obtaining a total of five times the number of the processed training set images as the training set images.

[0061] According to one or more embodiments of the present disclosure, the five methods include flipping, rotating, affine transformation, color jittering, and grayscale conversion.

[0062] According to one or more embodiments of the present disclosure, the YOLO model is trained using the processed training set images to obtain the trained model, including: using YOLO11n to train the processed training set images, and the model training is performed on a DELL Precision 7560 mobile workstation, wherein the operating system is Windows 11, the CPU is 11thGen Intel(R)Core(TM)i7-11850H, and the graphics card is NVIDIA RTX A2000; Pytorch2.5.1 based on CUDA12.4 is built, and the programming language is Python3.9; the training parameter Epoch size is 400, the batch size is set to 8, the initial image size is 640×640, the AdamW optimizer is used, and the initial learning rate is set to 0.01.

[0063] According to one or more embodiments of the present disclosure, the method for automatically identifying the phenological period of pinky azalea further includes: using the optimal model weights to detect the validation set images to obtain a validation set confusion matrix.

[0064] According to one or more embodiments of the present disclosure, the method for automatically identifying the phenological period of pinky-white azalea further includes: generating the phenological period of pinky-white azalea in each image based on the detected target label.

[0065] According to one or more embodiments of the present disclosure, there is provided an automatic device for identifying the phenological period of pink and white azalea, the device comprising: an image acquisition module, configured to use a phenological camera to take images of pink and white azalea at a fixed time and point every day; a screening and annotation module, configured to screen out representative images under different weather and different lighting conditions from the images, annotate the representative images, and annotate the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of pink and white azalea in each image; an image classification module, configured to divide the annotated images into training set images and verification set images; an image processing module, configured to perform data enhancement processing on the training set images to obtain processed training set images; a model training module, configured to perform model training on a YOLO model using the processed training set images to obtain a trained model; a detection module, configured to use the trained model to detect the images of pink and white azalea, and output the target label, confidence and position coordinates of the detection box detected on each image.

[0066] According to one or more embodiments of the present disclosure, a terminal is provided, comprising: at least one memory and at least one processor; wherein the at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute any one of the methods described above.

[0067] According to one or more embodiments of the present disclosure, a storage medium is provided, wherein the storage medium is used to store program code, and the program code is used to execute the above method.

[0068] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0069] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0070] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for automatically identifying the phenological period of Rhododendron truncatum, characterized in that: The method for automatically identifying the phenological period of pink-white azalea comprises: Use a phenological camera to capture images of the pink-white azalea at fixed times every day; Select representative images under different weather and light conditions from the images, annotate the representative images, and annotate the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink-white azalea in each image; Divide the labeled images into training set images and validation set images; Performing data enhancement processing on the training set images to obtain processed training set images; Performing model training on the YOLO model using the processed training set images to obtain a trained model; The trained model is used to detect images of pink and white azaleas, and the detected target label, confidence level and position coordinates of the detection box on each image are output.

2. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 1, characterized in that: Marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image includes marking the withered yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image as 0, 1, 2, 3, 4, 5, 6, 7 respectively.

3. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 1, characterized in that: Performing data enhancement processing on the training set images to obtain processed training set images includes: using five methods to randomly process the training set images, repeating four times, and obtaining five times the number of the processed training set images as the number of the training set images.

4. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 3, characterized in that: The five methods include flipping, rotating, affine transformation, color jittering and grayscale conversion.

5. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 1, characterized in that: The YOLO model is trained using the processed training set images, and the trained model includes: YOLO11n was used to perform model training on the processed training set images. The model training was performed on a DELL Precision7560 mobile workstation, where the operating system was Windows 11, the CPU was an 11th Gen Intel(R)Core(TM)i7-11850H, and the graphics card was NVIDIA RTX A2000. Pytorch2.5.1 based on CUDA12.4 was built, and the programming language used was Python3.

9. The training parameter Epoch size was 400, the batch size was set to 8, the initial image size was 640×640, the AdamW optimizer was used, and the initial learning rate was set to 0.

01.

6. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 1, characterized in that: Also includes: The validation set images are detected using the optimal model weights to obtain a validation set confusion matrix.

7. The method for automatically identifying the phenological period of Rhododendron truncatum according to claim 1, characterized in that: Also includes: The phenological period of the pink-white azalea in each image is generated based on the detected target labels.

8. An automatic identification device for the phenological period of pink-white azalea, characterized in that: The device for automatically identifying the phenological period of pink and white azalea comprises: An image acquisition module is configured to use a phenological camera to capture images of the pink-white azalea at a fixed time and point every day; a screening and labeling module, configured to screen representative images under different weather and different lighting conditions from the images, label the representative images, and label the withered and yellow leaves, buds, flower buds, fruits, leaf buds, new leaves, flowers and flower buds of the pink and white azalea in each image; An image classification module, configured to divide the labeled images into training set images and validation set images; An image processing module is configured to perform data enhancement processing on the training set images to obtain processed training set images; A model training module is configured to perform model training on a YOLO model using the processed training set images to obtain a trained model; The detection module is configured to use the trained model to detect images of pink and white azaleas and output the target label, confidence and position coordinates of the detection box detected on each image.

9. A terminal, comprising: at least one memory and at least one processor; The at least one memory is used to store program codes, and the at least one processor is used to call the program codes stored in the at least one memory to execute the method for automatically identifying the phenological period of pink-white azalea according to any one of claims 1 to 7.

10. A storage medium, the storage medium being used to store program codes, the program codes being used to execute the method for automatically identifying the phenological period of Rhododendron rubra according to any one of claims 1 to 7.

Images