Seedling missing detection method and device of rice transplanter and rice transplanter

Abstract

The invention discloses a rice transplanter seedling missing detection method and device and a rice transplanter, and relates to the technical field of agricultural machinery. The seedling missing detection method for the rice transplanter comprises the steps that a ground seedling image of the rice transplanter is acquired in real time, and the ground seedling image is acquired based on the current image acquisition frequency, so that no repeated acquisition area exists in the ground seedling image; the current image acquisition frequency is calculated based on preset rice transplanting parameters and the current running speed of the rice transplanter; identifying the ground seedling image by adopting a preset seedling identification model to obtain a seedling identification result; and based on the seedling identification result, obtaining a seedling missing detection result. The frequency of collecting the ground seedling image is determined through the driving speed, so that the ground seedling image collected every time does not have a repeated collection area, the ground seedling image identification every time does not have the identification of the repeated area, the repeated detection does not occur, and the seedling missing detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural machinery, and in particular to a method for detecting seedling shortage of a rice transplanter, a device for detecting seedling shortage of a rice transplanter, a rice transplanter and an electronic device. Background Art

[0002] With the rapid development of modern agricultural technology, intelligence and automation have become important means to improve agricultural production efficiency. As a key equipment for rice planting, the operation quality of the rice transplanter directly affects the yield and quality of rice. However, in the actual operation process, due to various factors (such as soil conditions, seedling quality, operating errors, etc.), the rice transplanter may lack seedlings, which will not only reduce rice yields, but also increase the labor intensity of users. Therefore, it is necessary to detect the lack of seedlings during the operation of the rice transplanter in real time.

[0003] The existing detection method is to use visual image processing to identify in real time whether there are missing seedlings in the current working image. However, the working image may have repeated parts, which will lead to the problem of repeated detection, resulting in low efficiency of missing seedling detection. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method for detecting seedling shortage of a rice transplanter, a device for detecting seedling shortage of a rice transplanter, a rice transplanter and an electronic device, so as to solve the problem of repeated detection in the prior art.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for detecting seedling shortage of a rice transplanter, comprising: Acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset transplanting parameters and the current driving speed of the rice transplanter; Using a preset rice seedling recognition model to recognize the rice seedling image on the ground, and obtaining a rice seedling recognition result; Based on the rice seedling identification result, a rice seedling shortage detection result is obtained.

[0006] In the embodiment of the present application, the preset transplanting parameters include the spacing between seedlings and the number of rows of seedlings in a single image; The calculation process of the current image acquisition frequency includes: Obtaining the current travel speed of the rice transplanter; The current image acquisition frequency is calculated based on the ratio of the seedling spacing to the current travel speed of the rice transplanter and the number of plant rows in the single image.

[0007] In the embodiment of the present application, the preset rice seedling recognition model is used to recognize the rice seedling image on the ground to obtain the rice seedling recognition result, including: Determining whether the ground seedling image is an abnormal image; When it is determined that the ground seedling image is not an abnormal image, a preset seedling recognition model is used to recognize the ground seedling image to obtain a seedling recognition result.

[0008] In an embodiment of the present application, determining whether the ground seedling image is an abnormal image includes: Based on an edge detection algorithm, a water body area is determined in the ground seedling image; Based on the ground seedling image, determining whether the image acquisition area is a reflective area; It is determined that the water body area is not empty and the image acquisition area is a reflective area, and the ground seedling image is obtained as an abnormal image.

[0009] In the embodiment of the present application, the seedling shortage detection result is obtained based on the seedling identification result, including: Based on the theoretical number of rice seedlings and the rice seedling identification result, the number of missed rice seedlings is obtained; Based on the number of missed seedlings and the theoretical number of seedlings, a missed seedling rate is calculated; Based on the missing seedling rate, a seedling shortage detection result is obtained.

[0010] In the embodiment of the present application, the seedling shortage detection result is obtained based on the seedling identification result, including: Acquiring the position information of the rice transplanter in real time; Based on the rice seedling identification result, obtaining a rice seedling shortage identification result; Based on the seedling absence identification result and the position information, a seedling absence detection result is obtained.

[0011] In the embodiment of the present application, it also includes: Obtain the seedling shortage detection results at multiple times; A seedling shortage report is generated based on the seedling shortage detection results at the multiple moments.

[0012] A second aspect of the present application provides a seedling shortage detection device for a rice transplanter, comprising: An acquisition module is used to acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset transplanting parameters and the current driving speed of the rice transplanter; A recognition module, used to recognize the ground seedling image using a preset seedling recognition model to obtain a seedling recognition result; A determination module is used to obtain a seedling shortage detection result based on the seedling identification result.

[0013] A third aspect of the present application provides a rice transplanter, which uses the above-mentioned rice transplanter seedling shortage detection method to perform seedling shortage detection.

[0014] A fourth aspect of the present application provides an electronic device, the electronic device comprising: at least one processor; a memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned rice transplanter seedling shortage detection method by executing the instructions stored in the memory.

[0015] Through the above technical scheme, the ground seedling image of the rice transplanter is acquired in real time, and the ground seedling image is acquired based on the current image acquisition frequency, so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on the preset transplanting parameters and the current driving speed of the rice transplanter; the ground seedling image is recognized by using the preset seedling recognition model to obtain the seedling recognition result; based on the seedling recognition result, the missing seedling detection result is obtained. The frequency of collecting the ground seedling image is determined by the driving speed. If the driving speed is slow, the interval is longer for collection, and if the driving speed is fast, the interval is shorter for collection, so that the rice transplanter just passes through the area that may be repeatedly collected during the collection interval, so that each collected ground seedling image will not have a repeated acquisition area, so that each ground seedling image has no repeated area, and then each ground seedling image recognition will not have a repeated area recognition, and there will be no repeated detection, thereby improving the efficiency of missing seedling detection. By acquiring the ground seedling image in real time and performing recognition and detection, the probability of missed detection can be reduced and the reliability of missing seedling detection can be improved.

[0016] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A schematic diagram of a process flow of a method for detecting seedling shortage of a rice transplanter according to an embodiment of the present application is schematically shown; Figure 2 A diagram schematically shows a result of seedling identification according to an embodiment of the present application; Figure 3The structure diagram of a device for detecting seedling shortage of a rice transplanter according to an embodiment of the present application is schematically shown; Figure 4 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown.

[0018] Description of Reference Numerals 410 - acquisition module; 420 - identification module; 430 - determination module; A01 - processor; A02 - network interface; A03 - internal memory; A04 - display screen; A05 - input device; A06 - non-volatile storage medium; B01 - operating system; B02 - computer program. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0021] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0022] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0023] Figure 1 The following schematically shows a flow chart of a method for detecting seedling shortage in a rice transplanter according to an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a method for detecting seedling shortage in a rice transplanter, which may include the following steps: Step 210: acquiring a ground seedling image of the rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset rice transplanting parameters and the current driving speed of the rice transplanter; In this embodiment, the ground seedling image of the above-mentioned transplanter can be obtained by real-time shooting of the working image during the operation of the transplanter, and can be specifically obtained by collecting the machine vision detection system on the transplanter, and the machine vision detection system includes a camera installed on the transplanter, a camera, etc. For example: the ground seedling image can be obtained by collecting the image data of the field seedlings in real time through a camera installed on the transplanter seedling box. The above-mentioned current image acquisition frequency can be set according to actual needs. The spacing of the transplanter transplanting is fixed. The faster the transplanter travels, the faster the needle rotates to keep the same spacing. The spacing here refers to the distance between the front and rear seedlings. In order to make the current collected ground seedling image not repeated with the previously collected ground seedling image, the frequency of collecting the ground seedling image can be determined according to the driving speed. If the driving speed is slow, the interval is longer for collection, and if the driving speed is fast, the interval is shorter for collection. Let the transplanter just pass through the area that may be repeatedly collected during the collection interval, so that each collected ground seedling image will not have a repeated collection area, so that each ground seedling image has no repeated area.

[0024] In some embodiments, the preset transplanting parameters include the spacing between seedlings and the number of rows in a single image; accordingly, the calculation process of the current image acquisition frequency includes: First, the current travel speed of the rice transplanter is obtained; In this embodiment, the current driving speed may be obtained by real-time measurement by a sensor, or may be obtained by a control system of the rice transplanter, which is not limited in this embodiment.

[0025] Then, based on the ratio of the spacing between the seedlings and the current travel speed of the transplanter, and the number of rows in the single image, the current image acquisition frequency is calculated using a calculation formula.

[0026] In this embodiment, the above calculation process can be expressed as: f = (L / V) * n, Among them, V is the current travel speed of the rice transplanter, L is the spacing between seedlings, and n is the number of rows in a single image. The spacing between seedlings is set and will not change. The number of rows in a single image refers to how many rows of seedlings there are in a single image, which can be obtained in advance through experiments. L / V represents the time required to transplant a seedling at present. The current image acquisition frequency is related to the current travel speed of the rice transplanter. The slower the travel speed, the greater the current image acquisition frequency, that is, the longer the interval for acquisition. The faster the travel speed, the smaller the current image acquisition frequency, that is, the shorter the interval for acquisition. By substituting the current image acquisition frequency into the above calculation formula, the current image acquisition frequency can be calculated, so that acquisition is performed according to the current image acquisition frequency, so that the ground seedling image of the rice transplanter can be obtained in real time without repeated acquisition areas.

[0027] The image acquisition frequency can be quickly calculated by combining the current travel speed of the transplanter, the spacing between seedlings, and the number of rows in a single image.

[0028] In some embodiments, after the image data of the field seedlings is collected in real time, the image can also be preprocessed, including denoising, contrast enhancement, etc., to improve the accuracy of subsequent processing to obtain a ground seedling image. For example, after starting the rice transplanter, the machine vision detection system can be turned on to ensure that the camera and other devices are working properly, and then connected to the data processing center. The image data of the field seedlings is collected in real time by the camera and preprocessed. The preprocessing includes operations such as denoising and contrast enhancement to improve image quality. The above denoising can be performed using a Gaussian filter, which can be expressed as: , in,( ) are pixel coordinates, is the standard deviation and determines the smoothness of the filter.

[0029] The contrast enhancement can be achieved by adjusting the grayscale histogram of the image using the principle of histogram equalization to make its distribution more uniform, thereby enhancing the contrast of the image. The denoising and contrast enhancement can be achieved using existing technologies, which will not be described in detail here.

[0030] In some embodiments, according to the operation characteristics of the rice transplanter and the field layout, the ground seedling image can also be divided into regions to determine the position range of each row of seedlings.

[0031] Step 220: using a preset rice seedling recognition model to recognize the ground rice seedling image to obtain a rice seedling recognition result; In this embodiment, the preset seedling recognition model can be a model constructed based on machine learning, including a target detection model constructed based on a convolutional neural network target detection algorithm, a target detection model constructed based on a deep learning target detection algorithm, etc. The preset seedling recognition model can be pre-trained. For example, the preset seedling recognition model is constructed using the YOLOv8 algorithm. First, a large number of data sets need to be collected in advance. The data sets include images collected during the transplanting process, and each seedling in the image is labeled. Then, the data set is used for model training to obtain a seedling recognition model. During the training process, an Attention mechanism can be added. The Attention mechanism can help the model pay more attention to potential target areas in the image, thereby improving the accuracy of detection. The preset seedling recognition model can identify the seedlings in the ground seedling image and mark them in the image to obtain the seedling recognition result. The construction of the preset seedling recognition model can be obtained by using the existing target detection model construction process, which will not be repeated here. By inputting the ground seedling image into the preset seedling recognition model, the seedlings in the ground seedling image can be identified to obtain the seedling recognition result. Please refer to Figure 2 , Figure 2 The figure schematically shows the result of seedling identification according to the embodiment of the present application.

[0032] In some embodiments, before identifying the rice seedlings, the influence of factors such as field water volume, angle and reflection on the image quality can be considered, that is, the preset rice seedling identification model is used to identify the ground rice seedling image to obtain the rice seedling identification result, including the following steps: First, determine whether the ground seedling image is an abnormal image; In this embodiment, the above judgment of whether it is an abnormal image can be made by judging the environment in the ground seedling image. If the environment in the ground seedling image is in a deep water level and there is a problem of sunlight reflection, the seedlings have no visual features and the detection result may be untrue. In this case, the current frame image can be saved as an abnormal situation without detection, and manual judgment will be made later.

[0033] In some embodiments, the step of determining whether the ground seedling image is an abnormal image comprises the following steps: The first step is to determine the water area in the ground seedling image based on an edge detection algorithm; In this embodiment, the edge detection algorithm can identify points or areas with drastic changes in brightness in the image. The edge detection algorithm in image processing can be used to separate the farmland area and the water area in the ground seedling image. It can be determined whether it is a water area based on image features such as area, shape, color, etc. in the area, so as to determine the water area in the ground seedling image. The above edge detection algorithm belongs to the prior art and will not be described in detail here.

[0034] The second step is to determine whether the image acquisition area is a reflective area based on the ground seedling image; In this embodiment, the reflective area usually appears as an area with abnormally high brightness or a color that is significantly different from the surrounding area. Based on the brightness and color analysis in the ground seedling image, it can be determined whether the image acquisition area is a reflective area.

[0035] The third step is to determine that the water body area is not empty and the image acquisition area is a reflective area, and obtain that the ground seedling image is an abnormal image.

[0036] In this embodiment, if the water area is not empty and the image acquisition area is a reflective area, it means that the ground seedling image has a problem of sunlight reflection; otherwise, it means that there is no problem of sunlight reflection. If the ground seedling image has a problem of sunlight reflection, the current frame of the ground seedling image is saved as an abnormal situation, and no detection is performed, and it is judged manually later. Otherwise, the next step of detection can be performed.

[0037] By determining the water area in the ground seedling image and judging whether the image acquisition area is a reflective area, the abnormal environment can be identified, so that it can be quickly and accurately determined whether the ground seedling image has the problem of sunlight reflection, which helps to accurately judge whether the ground seedling image is an abnormal image.

[0038] Then, when it is determined that the ground seedling image is not an abnormal image, a preset seedling recognition model is used to recognize the ground seedling image to obtain a seedling recognition result.

[0039] In this embodiment, if it is determined that the image of the seedlings on the ground is abnormal, no detection is performed and subsequent judgment is made manually; otherwise, image recognition can be performed.

[0040] By judging whether the ground seedling image is an abnormal image, if it is determined that the ground seedling image is not an abnormal image, a preset seedling recognition model is used to recognize the ground seedling image to obtain the seedling recognition result. The rice planting environment in the field can be pre-identified, and the abnormal environment can be judged in advance. The ground seedling images to be identified can be normal images, thereby improving the reliability of image recognition.

[0041] Step 230: Based on the rice seedling identification result, a rice seedling shortage detection result is obtained.

[0042] In this embodiment, the above-mentioned seedling recognition result may refer to the seedlings in the ground seedling image, and the position where the seedlings should be in the ground seedling image has been determined. According to the seedling recognition result, the missing seedling situation can be determined, thereby obtaining the missing seedling detection result.

[0043] In some embodiments, in order to timely understand the degree of seedling shortage, the step of obtaining the seedling shortage detection result based on the seedling identification result includes the following steps: Firstly, based on the theoretical number of rice seedlings and the rice seedling identification result, the number of missed rice seedlings is obtained; In this embodiment, the theoretical number of rice seedlings refers to the number of rice seedlings that should be in the ground rice seedling image under ideal conditions. After the acquisition position is determined, the theoretical number of rice seedlings can be obtained in advance through experiments and theoretical calculations. For example, there are 5 rows in an image, and the theoretical number of rice seedlings in each row is 8, then the theoretical number of rice seedlings is 5x8, that is, the theoretical number of rice seedlings is 40. The actual number of rice seedlings can be counted according to the rice seedling recognition results, and the number of missed rice seedlings can be obtained by subtracting the actual number of rice seedlings from the theoretical number of rice seedlings.

[0044] Then, based on the number of missed seedlings and the theoretical number of seedlings, the missed seedling rate is calculated; In this embodiment, the above calculation can be obtained by using the following formula: Missing seedling rate = number of missed seedlings / total number of seedlings to be planted, and the total number of seedlings to be planted is the theoretical number of seedlings.

[0045] Finally, based on the missing seedling rate, the missing seedling detection result is obtained.

[0046] In this embodiment, after the missing seedling rate is obtained, the missing seedling detection result includes the missing seedling rate.

[0047] The number of missed seedlings is obtained based on the theoretical number of seedlings and the seedling identification results. The missed seedling rate is calculated based on the number of missed seedlings and the theoretical number of seedlings. The seedling shortage detection results are obtained based on the missed seedling rate. Therefore, the degree of seedling shortage can be understood based on the seedling shortage detection results, which helps to quickly understand the seedling shortage situation in the field and take corresponding measures to remedy it.

[0048] In some embodiments, obtaining a seedling shortage detection result based on the seedling identification result includes: First, obtaining the position information of the rice transplanter; In this embodiment, the above-mentioned position information can be obtained by using the Real-Time Kinematic (RTK) technology, and the position information includes longitude, latitude, altitude and other information. RTK is a real-time dynamic differential positioning technology that receives satellite signals and differential information from ground reference stations, reads the position information data output by the RTK device, and achieves centimeter-level positioning accuracy. The RTK technology can be used to obtain the precise position information (longitude, latitude, altitude, etc.) of the rice transplanter.

[0049] Then, based on the rice seedling identification result, a rice seedling shortage identification result is obtained; In this embodiment, the seedling shortage identification result is the seedling shortage result determined according to the seedling identification result.

[0050] Finally, based on the seedling absence identification result and the position information, a seedling absence detection result is obtained.

[0051] In this embodiment, the seedling absence identification result and the position information can be matched to obtain the seedling absence detection result.

[0052] By obtaining the position information of the rice transplanter, the seedling shortage identification result is obtained based on the seedling identification result, and the seedling shortage detection result is obtained based on the seedling shortage identification result and the position information. By using the position information as an additional attribute of the seedling shortage detection result, the seedling shortage situation of each section can be located, so as to quickly determine the seedling shortage location and help to quickly take corresponding measures to remedy it. The introduction of RTK positioning technology can achieve accurate positioning of the seedling shortage situation.

[0053] In the above implementation process, the ground seedling image of the rice transplanter is acquired in real time, and the ground seedling image is acquired based on the current image acquisition frequency, so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on the preset transplanting parameters and the current driving speed of the rice transplanter; the ground seedling image is recognized by the preset seedling recognition model to obtain the seedling recognition result; based on the seedling recognition result, the missing seedling detection result is obtained. The frequency of collecting the ground seedling image is determined by the driving speed. If the driving speed is slow, the interval is longer for collection, and if the driving speed is fast, the interval is shorter for collection, so that the rice transplanter just passes through the area that may be repeatedly collected during the collection interval, so that each collected ground seedling image will not have a repeated collection area, so that each ground seedling image has no repeated area, and then each ground seedling image recognition will not have a repeated area recognition, and there will be no repeated detection, thereby improving the efficiency of missing seedling detection. By acquiring the ground seedling image in real time and performing recognition and detection, the probability of missed detection can be reduced and the reliability of missing seedling detection can be improved.

[0054] In some embodiments, it also includes: First, obtain the seedling shortage detection results at multiple times; In this embodiment, the seedling shortage detection result at each moment can be obtained according to the above steps 210 to 230, which will not be repeated here.

[0055] Then, based on the seedling shortage detection results at the multiple moments, a seedling shortage report is generated.

[0056] In this embodiment, the seedling shortage detection results at multiple times are combined to generate a seedling shortage report. The seedling shortage detection results, location information, video playback and other data can also be integrated into a seedling shortage report for an entire field. Through data processing and visualization technology, the seedling shortage detection results, location information and other data are integrated into the report. For example, a seedling shortage heat map can be generated in the seedling shortage report, and the degree of seedling shortage can be indicated by the depth of color, so that users can intuitively understand the seedling shortage situation in the field. The generation and output of the seedling shortage report is achieved through the automated processing flow of the data processing center to ensure the accuracy and timeliness of the seedling shortage report. The seedling shortage report can be output to the user for reference and decision-making. The introduction of RTK positioning technology can achieve accurate positioning of the seedling shortage situation, and can also provide users with a more detailed and accurate seedling shortage report.

[0057] In some embodiments, based on the seedling shortage detection results at multiple times, it can be determined whether there are rows or columns that are missing seedlings for a long time. If so, an early warning prompt is given to remind the user.

[0058] Figure 1 FIG. 1 is a flow chart of a method for detecting seedling shortage in a rice transplanter in an embodiment. Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0059] The present embodiment provides a rice transplanter, which uses the above-mentioned rice transplanter seedling shortage detection method to perform seedling shortage detection.

[0060] In this embodiment, the rice transplanter may be provided with a camera, a machine vision detection system, a data processing center, etc. The camera may be used to collect image data of the seedlings in the field in real time and send the data to the data processing center for processing.

[0061] In the above implementation process, the frequency of collecting ground seedling images is determined by the driving speed. If the driving speed is slow, the intervals for collecting are longer, and if the driving speed is fast, the intervals for collecting are shorter. The rice transplanter just passes through the area where repeated collection may occur during the collection interval, so that each collected ground seedling image will not have repeated collection areas, and each ground seedling image will have no repeated areas, and then each ground seedling image recognition will not have repeated areas, and there will be no repeated detection, thereby improving the efficiency of missing seedling detection. By acquiring the ground seedling image in real time and performing identification and detection, the probability of missed detection can be reduced and the reliability of missing seedling detection can be improved. Real-time detection and identification of missing seedlings during the operation of the rice transplanter is realized. This solution not only improves the operation quality and agricultural production efficiency of the rice transplanter, but also provides farmers with an intuitive reference basis.

[0062] Please see Figure 3 , Figure 3 The schematic diagram of the structure of a rice transplanter seedling shortage detection device according to an embodiment of the present application is schematically shown. This embodiment provides a rice transplanter seedling shortage detection device, including an acquisition module 410, an identification module 420 and a determination module 430, wherein: An acquisition module 410 is used to acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset rice transplanting parameters and a current driving speed of the rice transplanter; The recognition module 420 is used to recognize the ground seedling image using a preset seedling recognition model to obtain a seedling recognition result; The determination module 430 is used to determine the seedling shortage detection result based on the theoretical seedling quantity and the seedling identification result.

[0063] The rice transplanter seedling shortage detection device includes a processor and a memory. The acquisition module 410, the identification module 420 and the determination module 430 are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

[0064] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the planting position is aligned with the planting position before the turn by adjusting the kernel parameters.

[0065] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0066] An embodiment of the present invention provides a processor, which is used to run a program, wherein the rice transplanter seedling shortage detection method is executed when the program is run.

[0067] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a method for detecting seedling shortage in a rice transplanter is implemented. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.

[0068] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0069] In one embodiment, the rice transplanter seedling shortage detection method device provided in the present application can be implemented in the form of a computer program. The computer program can be Figure 4 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules constituting the rice transplanter seedling shortage detection method device, for example, Figure 3 The acquisition module 410, the identification module 420 and the determination module 430 are shown. The computer program composed of various program modules enables the processor to execute the steps of the rice transplanter seedling shortage detection method of each embodiment of the present application described in this specification.

[0070] Figure 4 The computer device shown can be Figure 3The acquisition module 410 in the illustrated rice transplanter seedling shortage detection method device executes step 210. The computer device may execute step 220 through the identification module 420. The computer device may execute step 230 through the determination module 430.

[0071] An embodiment of the present application provides an electronic device, which includes: at least one processor; a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned rice transplanter seedling shortage detection method by executing the instructions stored in the memory, and the processor implements the following steps when executing the instructions: Acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset transplanting parameters and the current driving speed of the rice transplanter; Using a preset rice seedling recognition model to recognize the rice seedling image on the ground, and obtaining a rice seedling recognition result; Based on the rice seedling identification result, a rice seedling shortage detection result is obtained.

[0072] In one embodiment, the preset transplanting parameters include the spacing between seedlings and the number of rows of seedlings in a single image; The calculation process of the current image acquisition frequency includes: Obtaining the current travel speed of the rice transplanter; The current image acquisition frequency is calculated based on the ratio of the seedling spacing to the current travel speed of the rice transplanter and the number of plant rows in the single image.

[0073] In one embodiment, the using of a preset rice seedling recognition model to recognize the ground rice seedling image to obtain a rice seedling recognition result includes: Determining whether the ground seedling image is an abnormal image; When it is determined that the ground seedling image is not an abnormal image, a preset seedling recognition model is used to recognize the ground seedling image to obtain a seedling recognition result.

[0074] In one embodiment, determining whether the ground seedling image is an abnormal image includes: Based on an edge detection algorithm, a water body area is determined in the ground seedling image; Based on the ground seedling image, determining whether the image acquisition area is a reflective area; It is determined that the water body area is not empty and the image acquisition area is a reflective area, and the ground seedling image is obtained as an abnormal image.

[0075] In one embodiment, obtaining the seedling shortage detection result based on the seedling identification result includes: Based on the theoretical number of rice seedlings and the rice seedling identification result, the number of missed rice seedlings is obtained; Based on the number of missed seedlings and the theoretical number of seedlings, a missed seedling rate is calculated; Based on the missing seedling rate, a seedling shortage detection result is obtained.

[0076] In one embodiment, obtaining the seedling shortage detection result based on the seedling identification result includes: Acquiring the position information of the rice transplanter in real time; Based on the rice seedling identification result, obtaining a rice seedling shortage identification result; Based on the seedling absence identification result and the position information, a seedling absence detection result is obtained.

[0077] In one embodiment, it further includes: Obtain the seedling shortage detection results at multiple times; A seedling shortage report is generated based on the seedling shortage detection results at the multiple moments.

[0078] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0083] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0084] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0085] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0086] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for detecting seedling shortage of a rice transplanter, characterized in that: include: Acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset transplanting parameters and the current driving speed of the rice transplanter; Using a preset rice seedling recognition model to recognize the rice seedling image on the ground, and obtaining a rice seedling recognition result; Based on the rice seedling identification result, a rice seedling shortage detection result is obtained.

2. The method according to claim 1, characterized in that The preset transplanting parameters include the spacing between seedlings and the number of rows in a single image; The calculation process of the current image acquisition frequency includes: Obtaining the current travel speed of the rice transplanter; The current image acquisition frequency is calculated based on the ratio of the seedling spacing to the current travel speed of the rice transplanter and the number of plant rows in the single image.

3. The method according to claim 1, characterized in that The preset rice seedling recognition model is used to recognize the rice seedling image on the ground to obtain the rice seedling recognition result, including: Determining whether the ground seedling image is an abnormal image; When it is determined that the ground seedling image is not an abnormal image, a preset seedling recognition model is used to recognize the ground seedling image to obtain a seedling recognition result.

4. The method according to claim 3, characterized in that The determining whether the ground seedling image is an abnormal image comprises: Based on an edge detection algorithm, a water body area is determined in the ground seedling image; Based on the ground seedling image, determining whether the image acquisition area is a reflective area; It is determined that the water body area is not empty and the image acquisition area is a reflective area, and the ground seedling image is obtained as an abnormal image.

5. The method according to claim 1, characterized in that The step of obtaining a seedling shortage detection result based on the seedling identification result includes: Based on the theoretical number of rice seedlings and the rice seedling identification result, the number of missed rice seedlings is obtained; Based on the number of missed seedlings and the theoretical number of seedlings, a missed seedling rate is calculated; Based on the missing seedling rate, a seedling shortage detection result is obtained.

6. The method according to claim 1, characterized in that The step of obtaining a seedling shortage detection result based on the seedling identification result includes: Acquiring the position information of the rice transplanter in real time; Based on the rice seedling identification result, obtaining a rice seedling shortage identification result; Based on the seedling absence identification result and the position information, a seedling absence detection result is obtained.

7. The method according to claim 1, characterized in that Also includes: Obtain the seedling shortage detection results at multiple times; A seedling shortage report is generated based on the seedling shortage detection results at the multiple moments.

8. A device for detecting seedling shortage of a rice transplanter, characterized in that: include: An acquisition module is used to acquire a ground seedling image of a rice transplanter in real time, wherein the ground seedling image is acquired based on a current image acquisition frequency so that there is no repeated acquisition area in the ground seedling image, and the current image acquisition frequency is calculated based on preset transplanting parameters and the current driving speed of the rice transplanter; A recognition module, used to recognize the ground seedling image using a preset seedling recognition model to obtain a seedling recognition result; A determination module is used to obtain a seedling shortage detection result based on the seedling identification result.

9. A rice transplanter, characterized in that: The method for detecting seedling shortage of a rice transplanter according to any one of claims 1 to 7 is used to detect seedling shortage.

10. An electronic device, characterized in that: The electronic device includes: at least one processor; a memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the rice transplanter seedling shortage detection method according to any one of claims 1 to 7 by executing the instructions stored in the memory.

Images