Method and device for detecting abnormality of seedling box of rice transplanter and rice transplanter

Abstract

The invention discloses a rice transplanter seedling box anomaly detection method and device and a rice transplanter, and relates to the technical field of agricultural machinery. The rice transplanter seedling box anomaly detection method comprises the following steps: acquiring a seedling image in real time; calculating a proportion of a seedling area in the seedling image to obtain a current seedling ratio; obtaining a mud blocking result based on the current seedling ratio; and obtaining a first seedling box abnormal result based on the mud blocking result. Through the proportion of the seedling area in the seedling image, the mud blocking condition in the seedling emergence box can be detected, then the first seedling box abnormal result is obtained according to the mud blocking result, abnormal detection through machine vision is achieved, detection is more accurate, the real-time performance is higher, and operation is easy and convenient. The first seedling box abnormity result is obtained by considering the seedling box mud blocking condition, and the accuracy and reliability of seedling box abnormity detection are improved.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural machinery, and specifically to a method for detecting abnormalities in a seedling box of a rice transplanter, a device for detecting abnormalities in a seedling box of a rice transplanter, a rice transplanter, a machine-readable storage medium, and an electronic device. Background Art

[0002] During the operation of the rice transplanter, the seedling box is a component used to store the seedlings. Its main function is to carry and transport the seedlings so that the seedlings can be sent to the transplanting position in an orderly manner. Abnormal detection of the seedling box of the rice transplanter is an important part of ensuring the quality and efficiency of transplanting.

[0003] The existing abnormal detection of the seedling box of the rice transplanter ignores the detection of the mud blockage of the seedling box, making the abnormal detection of the seedling box not accurate and reliable enough. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method for detecting abnormalities in a seedling box of a rice transplanter, a device for detecting abnormalities in a seedling box of a rice transplanter, a rice transplanter, a machine-readable storage medium and an electronic device, so as to solve the problem that the prior art ignores the detection of mud blockage in the seedling box, making the detection of abnormalities in the seedling box not accurate and reliable enough.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a method for detecting abnormality of a seedling box of a rice transplanter, comprising: Acquire seedling images in real time; Calculating the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; Based on the current rice seedling ratio, a mud blocking result is obtained; Based on the mud blocking results, an abnormal result of the first seedling box is obtained.

[0006] In the embodiment of the present application, the mud blocking result is obtained based on the current rice seedling ratio, including: Calculate the difference between the rice seedling ratio at the previous moment and the current rice seedling ratio to obtain a ratio change value; Comparing the ratio change value with a preset ratio change threshold to obtain a comparison result; Based on the comparison result, the mud plugging result is obtained.

[0007] In the embodiment of the present application, it also includes: Determining the proportion of the rice seedling area in each row in the rice seedling image to obtain the rice seedling ratio in each row; Based on the ratio of the seedlings in each row, judging whether the amount of the seedlings in the current seedling box is sufficient, and obtaining a seedling amount detection result; Based on the mud blocking result and the rice seedling quantity detection result, the abnormal result of the second seedling box is obtained.

[0008] In the embodiment of the present application, determining the proportion of the seedling area of ​​each row in the seedling image to obtain the ratio of the seedlings of each row includes: Converting the color space of the rice seedling image to obtain a rice seedling conversion image; The seedling area of ​​each row is determined in the seedling conversion image, and the proportion of the seedling area of ​​each row is calculated to obtain the seedling ratio of each row.

[0009] In the embodiment of the present application, it also includes: Performing image segmentation on the rice seedling image to obtain a rice seedling pixel area; Determine the sparsity of the rice seedlings based on the number of pixels in the rice seedling pixel area and the number of pixels in the rice seedling image; Based on the mud blocking results and the seedling sparseness, the abnormal result of the third seedling box is obtained.

[0010] In an embodiment of the present application, the step of performing image segmentation on the rice seedling image to obtain a rice seedling pixel area includes: Inputting the rice seedling image into a preset rice seedling segmentation model to obtain a rice seedling segmentation mask; Based on the rice seedling segmentation mask, the rice seedling pixel area is obtained.

[0011] A second aspect of the present application provides a device for detecting abnormality in a seedling box of a rice transplanter, comprising: An acquisition module, used for acquiring rice seedling images in real time; A calculation module, used for calculating the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; A judgment module, used for obtaining a mud blocking result based on the current rice seedling ratio; The detection module is used to obtain the abnormal result of the first seedling box based on the mud blocking result.

[0012] A third aspect of the present application provides a rice transplanter, which uses the above-mentioned rice transplanter seedling box abnormality detection method to detect the seedling box of the rice transplanter.

[0013] 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 method for detecting abnormalities in the seedling box of a rice transplanter by executing the instructions stored in the memory.

[0014] A fifth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the above-mentioned method for detecting abnormalities in a seedling box of a rice transplanter.

[0015] Through the above technical scheme, the seedling image is acquired in real time; the proportion of the seedling area in the seedling image is calculated to obtain the current seedling ratio; based on the current seedling ratio, the mud blocking result is obtained; based on the mud blocking result, the abnormal result of the first seedling box is obtained. The mud blocking situation in the seedling box can be detected by the proportion of the seedling area in the seedling image, and then the abnormal result of the first seedling box is obtained according to the mud blocking result, so as to realize the abnormal detection by machine vision, making the detection more accurate, more real-time and easy to operate. The above-mentioned abnormal result of the first seedling box is obtained by considering the mud blocking situation of the seedling box, which improves the accuracy and reliability of abnormal detection of the seedling box. Through this scheme, the abnormal situation in the seedling box can be detected in real time, which helps to reduce problems such as missed planting, seedling pressing and damage to planting claws, and improves the quality and efficiency of transplanting.

[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 of detecting an abnormality of a seedling box of a rice transplanter according to an embodiment of the present application is schematically shown; Figure 2 The structure diagram of a device for detecting abnormality of a seedling box of a rice transplanter according to an embodiment of the present application is schematically shown; Figure 3 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 - calculation module; 430 - judgment module; 440 - detection 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 is a schematic diagram showing a flow chart of a method for detecting abnormality in a seedling box of 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 abnormality in a seedling box of a rice transplanter, and the method may include the following steps: Step 210: Acquire the rice seedling image in real time; In this embodiment, the above-mentioned seedling image refers to the seedling image in the seedling box, which can be obtained by real-time acquisition of image information inside the seedling box, specifically, by using a camera installed on the rice transplanter to capture the video stream or image sequence inside the seedling box in real time. For example, a camera can be fixedly installed just above the seedling box of the rice transplanter to ensure that the camera field of view covers the entire seedling box, and then the rice transplanter is started, and the machine vision detection system is turned on to ensure that the camera equipment works normally, and is connected to the data processing center to obtain the seedling image in real time.

[0024] In some embodiments, after the seedling image is acquired in real time, the seedling image may be preprocessed, including denoising, contrast enhancement, etc., to improve the accuracy of subsequent processing. That is, acquiring the seedling image in real time includes: First, the initial seedling image is acquired in real time; In this embodiment, the initial rice seedling image may refer to a rice seedling image collected in real time.

[0025] Then, the initial rice seedling image is preprocessed to obtain a rice seedling image.

[0026] In this embodiment, the preprocessing includes denoising, contrast enhancement, etc. The denoising may be performed by using a Gaussian filter, which can be expressed as: , in,( ) are pixel coordinates, is the standard deviation and determines the smoothness of the filter.

[0027] 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.

[0028] For example, after starting the rice transplanter, you can turn on the machine vision inspection system, ensure that the camera and other equipment are working properly, and then connect to the data processing center. The camera collects image data of rice seedlings in the field in real time and performs preprocessing. Preprocessing includes operations such as denoising and contrast enhancement to improve image quality.

[0029] Step 220: Calculate the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; In this embodiment, during the operation of the rice transplanter, the inside of the seedling box may be blocked by mud due to the accumulation of soil. By real-time monitoring of the image information inside the seedling box and analyzing the image using an image processing algorithm, it can be determined whether there is a mud blockage. Specifically, the proportion of the green area (representing the seedlings) in the seedling box can be calculated, that is, the proportion of the seedling area in the seedling image can be calculated to obtain the current seedling ratio. And monitor the changes in the ratio. If the green ratio remains unchanged for a long time or suddenly drops sharply, it may indicate that the seedling box is blocked by mud. The above calculation of the proportion of the seedling area in the seedling image can be to first identify the green area in the seedling image, and then calculate the proportion of the green area in the seedling image based on the area of ​​the green area to obtain the current seedling ratio. The above method for identifying the green area includes a method based on color thresholds, a method based on machine learning, etc., which is not limited in this embodiment.

[0030] Step 230: obtaining a mud blocking result based on the current rice seedling ratio; In this embodiment, it is possible to determine whether the seedlings in the seedling box have changed based on the current seedling ratio, thereby determining whether the seedling box is blocked by mud.

[0031] In some embodiments, obtaining the mud blocking result based on the current rice seedling ratio comprises the following steps: First, the difference between the rice seedling ratio at the previous moment and the current rice seedling ratio is calculated to obtain a ratio change value; In this embodiment, the above-mentioned seedling ratio at the previous moment can be obtained by calculating the proportion of the seedling area in the seedling image acquired at the previous moment. During the operation of the rice transplanter, the seedling box image is continuously collected, and the proportion of the green area in each frame of the image is calculated to monitor the change of the green ratio. If it remains unchanged for a long time or suddenly drops sharply, a mud blockage warning can be issued. During the movement, the ratio difference ΔRthreshold of the green seedling area in the seedling box is continuously monitored. If the ratio difference is inconsistent for a long time, it may indicate the presence of mud blockage or other abnormal conditions. The calculation of the above-mentioned ratio change value can be expressed as: ΔRthreshold=|Rgreen,t-Rgreen,t-1|, where ΔRthreshold represents the green ratio difference, Rgreen,t represents the green ratio at the current moment, that is, the current seedling ratio, and Rgreen,t-1 represents the green ratio at the previous moment, that is, the seedling ratio at the previous moment.

[0032] Then, the ratio change value is compared with a preset ratio change threshold value to obtain a comparison result; In this embodiment, the preset ratio change threshold may be set in advance based on experience, and the comparison result includes the ratio change value being greater than the preset ratio change threshold and the ratio change value being not greater than the preset ratio change threshold.

[0033] Finally, based on the comparison result, the mud plugging result is obtained.

[0034] In this embodiment, if the comparison result is that the ratio change value is greater than the preset ratio change threshold, it means that mud blockage has occurred, otherwise, it means that mud blockage has not occurred.

[0035] For example, the above determination of mud blocking results can be expressed as: ΔRthreshold=∣Rgreen,t-Rgreen,t-1∣> , Among them, ΔRthreshold represents the green ratio difference, Rgreen,t represents the green ratio at the current moment, that is, the current seedling ratio, and Rgreen,t-1 represents the green ratio at the previous moment, that is, the seedling ratio at the previous moment. Indicates the set change threshold, which can be set based on experience. , it means that mud blockage has occurred, otherwise, it means that mud blockage has not occurred.

[0036] By calculating the difference between the seedling ratio at the previous moment and the current seedling ratio, it is possible to determine whether the seedling ratio remains unchanged for a long time or drops sharply suddenly. It is also possible to quickly and accurately determine whether the seedling box is blocked with mud and obtain the mud blocking result.

[0037] Step 240: Based on the mud blocking result, the abnormal result of the first seedling box is obtained.

[0038] In this embodiment, if the mud blocking result is that mud blocking occurs, it can be determined that the abnormal result of the first seedling box is abnormal, otherwise, it can be determined that the abnormal result of the first seedling box is normal.

[0039] In the above implementation process, the seedling image is acquired in real time; the proportion of the seedling area in the seedling image is calculated to obtain the current seedling ratio; based on the current seedling ratio, the mud blocking result is obtained; based on the mud blocking result, the abnormal result of the first seedling box is obtained. The mud blocking situation in the seedling box can be detected by the proportion of the seedling area in the seedling image, and then the abnormal result of the first seedling box is obtained according to the mud blocking result, so as to realize the abnormal detection by machine vision, making the detection more accurate, more real-time and easy to operate. The above-mentioned abnormal result of the first seedling box is obtained by considering the mud blocking situation of the seedling box, which improves the accuracy and reliability of abnormal detection of the seedling box. Through this scheme, the abnormal situation in the seedling box can be detected in real time, which helps to reduce problems such as missed planting, seedling pressing and damage to planting claws, and improves the quality and efficiency of transplanting.

[0040] In some embodiments, the following steps are also included: First, determining the proportion of the rice seedling area in each row in the rice seedling image to obtain the rice seedling ratio in each row; In this embodiment, the image is processed and analyzed using an image processing algorithm to obtain the ratio of each row of rice seedlings. Since the camera installation position is relatively fixed, the area range of the seedling box and the range of each row can be easily found in the image, and the rice seedlings in each row can be identified by image recognition technology, and then the ratio of rice seedlings can be calculated.

[0041] In some embodiments, determining the proportion of the seedling area of ​​each row in the seedling image to obtain the ratio of each row of seedlings includes the following steps: The first step is to convert the color space of the rice seedling image to obtain a rice seedling conversion image; In this embodiment, the above conversion is to convert the rice seedling image from the BGR (or RGB) color space to the HSV (or HSL) color space, because the HSV (or HSL) space is more intuitive and convenient for color segmentation. For example, in the HSV space, green is usually within a certain range of hue (H) and saturation (S), and the conversion formula for color space conversion is as follows: , H represents hue, S represents saturation, and V represents brightness. R, G, and B represent the red, green, and blue layers in the image respectively.

[0042] The second step is to determine the rice seedling area of ​​each row in the rice seedling conversion image, and calculate the rice seedling area ratio of each row to obtain the rice seedling ratio of each row; In this embodiment, the green range of the rice seedlings can be found in each row to determine the rice seedling area. For example, in the HSV space, the green range of the rice seedlings is calculated and the rice seedling area is found by threshold segmentation. The ratio of the green area in each row to the total area of ​​the image can be calculated to obtain the rice seedling ratio of each row. The green ratio calculation formula is: Rgreen = , Among them, Rgreen represents the green ratio, that is, the ratio of seedlings in each row, Agreen represents the area of ​​green seedlings in each row in the image, and Atotal represents the total area of ​​the image.

[0043] By converting the color space of the seedling image, color segmentation is more intuitive and convenient. The seedling area of ​​each row can be quickly determined in the seedling conversion image, so that the proportion of the seedling area of ​​each row can be quickly and conveniently calculated to obtain the seedling ratio of each row.

[0044] Then, based on the ratio of the seedlings in each row, it is determined whether the amount of the seedlings in the current seedling box is sufficient to obtain a seedling amount detection result.

[0045] In this embodiment, after calculating the ratio of each row of rice seedlings, the ratio of each row of rice seedlings can be compared with a set threshold value to determine whether the rice seedling quantity is sufficient. The above threshold value can be set as needed. When the ratio of each row of rice seedlings is greater than the preset threshold value, it means that the rice seedling quantity in the current seedling box is sufficient, and the rice seedling quantity detection result is sufficient. Otherwise, it means that the rice seedling quantity is insufficient, and the rice seedling quantity detection result is insufficient.

[0046] Finally, based on the mud blocking results and the rice seedling quantity detection results, the abnormal results of the second seedling box are obtained.

[0047] In this embodiment, the abnormal result of the second seedling box may include the mud blockage result and the seedling quantity detection result, thereby realizing fault detection from the aspects of mud blockage situation and seedling quantity detection.

[0048] By determining the proportion of the seedling area of ​​each row in the seedling image, the seedling ratio of each row is obtained. Based on the seedling ratio of each row, it is possible to quickly and accurately determine whether the amount of seedlings in the current seedling box is sufficient, thereby realizing the monitoring of the amount of seedlings inside the seedling box. Based on the mud blockage results and the seedling quantity detection results, the abnormal results of the second seedling box are obtained, further improving the accuracy and reliability of seedling box fault detection.

[0049] In some embodiments, the following steps are also included: Firstly, the rice seedling image is segmented to obtain a rice seedling pixel area; In this embodiment, the above-mentioned image segmentation can be implemented by adopting a threshold segmentation-based method, an edge detection-based method, a deep learning-based image segmentation algorithm, etc.

[0050] In some embodiments, performing image segmentation on the rice seedling image to obtain a rice seedling pixel area comprises the following steps: The first step is to input the seedling image into a preset seedling segmentation model to obtain a seedling segmentation mask; The second step is to obtain the rice seedling pixel area based on the rice seedling segmentation mask.

[0051] In this embodiment, the preset seedling segmentation model can be a pre-trained image segmentation model for detecting the seedling area in the seedling image. The preset seedling segmentation model can be constructed based on a deep learning image segmentation algorithm. For example, the seedling image can be segmented using a deep convolutional neural network, and the green edge range can be accurately found as the seedling area, thereby judging the sparsity of the seedlings. In the specific implementation, the algorithm can be integrated into an artificial intelligence (AI) algorithm chip, which is not limited to the design method, manufacturer, and model of the AI ​​algorithm chip. Furthermore, the AI ​​algorithm chip can also be integrated into the camera mainboard, making the product structure simpler, installation more convenient, cost lower, and data transmission faster.

[0052] The following takes the YOLOv8 image segmentation algorithm as an example to illustrate the construction process of the preset seedling segmentation model. The YOLOv8 image segmentation algorithm combines the advantages of the YOLOv8 target detection algorithm and the principle of semantic segmentation, and regards each pixel in the image as a target for segmentation. First, collect the image data of the seedlings on the seedling box to ensure that the data is diverse and representative. Annotate the image data, including the location, category and other information of the seedlings. Then use the YOLOv8 image segmentation algorithm to train the annotated image data to obtain the YOLOv8 segmentation model, that is, the seedling segmentation model. During the training process, data enhancement techniques (such as image scaling, cropping, flipping, rotation, etc.) can be used to improve the generalization ability of the model. In the actual detection process, the seedling image is input into the trained YOLOv8 segmentation model, the model segments the image, outputs the segmentation mask of the seedling, processes the segmentation mask, and extracts the seedling pixel area.

[0053] The seedling image is segmented by using a preset seedling segmentation model. The seedling segmentation model is constructed based on a deep learning image segmentation algorithm, which makes the image segmentation more accurate and can obtain a more accurate seedling pixel area.

[0054] Then, based on the number of pixels in the rice seedling pixel area and the number of pixels in the rice seedling image, the rice seedling sparsity is determined.

[0055] In this embodiment, the proportion of the seedling pixel area to the entire seedling box image can be calculated as a measure of sparsity, and the sparsity calculation formula can be simplified as follows: Sparsity = (number of seedling pixels / total number of pixels) × 100%.

[0056] Finally, based on the mud blocking results and the seedling sparsity, the abnormal results of the third seedling box are obtained.

[0057] In this embodiment, the abnormal result of the third seedling box includes the mud blockage result and the seedling sparseness, thereby realizing fault detection from the aspects of mud blockage and seedling sparseness.

[0058] It should be noted that the above determination of the seedling sparsity can also be obtained by further analyzing the distribution of the seedlings using an image processing algorithm based on the determination of the seedling quantity, for example, the seedling sparsity on the seedling box can be calculated in real time based on the YOLOv8 image segmentation algorithm. The above seedling sparsity can also be measured by calculating the average distance between seedlings or the number of seedlings per unit area.

[0059] By performing image segmentation on the seedling image, the seedling pixel area is obtained. Based on the number of pixels in the seedling pixel area and the number of pixels in the seedling image, the seedling sparsity can be quickly determined. Based on the mud blocking result and the seedling sparsity, the abnormal result of the third seedling box is obtained, which further improves the accuracy and reliability of seedling box abnormality detection.

[0060] It should be noted that, in specific implementation, the abnormal results of the seedling box may include one or more of the mud blockage results, seedling quantity detection results and seedling sparseness.

[0061] Figure 1 FIG. 1 is a flow chart of a method for detecting abnormality of a rice transplanter seedling box 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.

[0062] The present embodiment provides a rice transplanter, and the seedling box of the rice transplanter is detected by using the above-mentioned method for detecting abnormality of the seedling box of the rice transplanter.

[0063] 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.

[0064] In the above implementation process, the seedling image is acquired in real time; the proportion of the seedling area in the seedling image is calculated to obtain the current seedling ratio; based on the current seedling ratio, the mud blocking result is obtained; based on the mud blocking result, the abnormal result of the first seedling box is obtained. The mud blocking situation in the seedling box can be detected by the proportion of the seedling area in the seedling image, and then the abnormal result of the first seedling box is obtained according to the mud blocking result, so as to realize the abnormal detection by machine vision, making the detection more accurate, more real-time and easy to operate. The above-mentioned abnormal result of the first seedling box is obtained by considering the mud blocking situation of the seedling box, which improves the accuracy and reliability of abnormal detection of the seedling box. Through this scheme, the abnormal situation in the seedling box can be detected in real time, which helps to reduce problems such as missed planting, seedling pressing and damage to planting claws, and improves the quality and efficiency of transplanting.

[0065] Please see Figure 2 , Figure 2 The schematic diagram of the structure of a device for detecting abnormality of a seedling box of a rice transplanter according to an embodiment of the present application is shown schematically. This embodiment provides a device for detecting abnormality of a seedling box of a rice transplanter, comprising an acquisition module 410, a calculation module 420, a judgment module 430 and a detection module 440, wherein: An acquisition module 410 is used to acquire the rice seedling image in real time; A calculation module 420 is used to calculate the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; A judgment module 430 is used to obtain a mud blocking result based on the current rice seedling ratio; The detection module 440 is used to obtain the abnormal result of the first seedling box based on the mud blocking result.

[0066] The rice transplanter seedling box abnormality detection device includes a processor and a memory. The above-mentioned acquisition module 410, calculation module 420, judgment module 430 and detection module 440 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0067] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the abnormality detection of the seedling box of the rice transplanter can be performed by adjusting the kernel parameters.

[0068] 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.

[0069] An embodiment of the present invention provides a machine-readable storage medium on which a program is stored. When the program is executed by a processor, the method for detecting abnormalities in a seedling box of a rice transplanter is implemented.

[0070] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for detecting abnormalities in a seedling box of a rice transplanter is executed when the program is running.

[0071] 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 3 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 abnormalities in a seedling box of 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 housing, or an external keyboard, touchpad or mouse, etc.

[0072] Those skilled in the art will understand that Figure 3 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.

[0073] In one embodiment, the method and device for detecting abnormality of a seedling box of a rice transplanter provided in the present application can be implemented in the form of a computer program. Figure 3 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules that constitute the device for detecting abnormality of the seedling box of the rice transplanter, for example, Figure 2 The acquisition module 410, the calculation module 420, the judgment module 430 and the detection module 440 are shown. The computer program composed of various program modules enables the processor to execute the steps of the rice transplanter seedling box abnormality detection method of each embodiment of the present application described in this specification.

[0074] Figure 3 The computer device shown can be Figure 2The acquisition module 410 in the device for detecting abnormality of a seedling box of a rice transplanter shown in the figure executes step 210. The computer device may execute step 220 through the calculation module 420. The computer device may execute step 230 through the judgment module 430. The computer device may execute step 240 through the detection module 440.

[0075] 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 method for detecting abnormalities in a seedling box of a rice transplanter by executing the instructions stored in the memory. When the processor executes the instructions, the following steps are implemented: Acquire seedling images in real time; Calculating the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; Based on the current rice seedling ratio, a mud blocking result is obtained; Based on the mud blocking results, an abnormal result of the first seedling box is obtained.

[0076] In one embodiment, obtaining the mud blocking result based on the current rice seedling ratio includes: Calculate the difference between the rice seedling ratio at the previous moment and the current rice seedling ratio to obtain a ratio change value; Comparing the ratio change value with a preset ratio change threshold to obtain a comparison result; Based on the comparison result, the mud plugging result is obtained.

[0077] In one embodiment, it further includes: Determining the proportion of the rice seedling area in each row in the rice seedling image to obtain the rice seedling ratio in each row; Based on the ratio of the seedlings in each row, judging whether the amount of the seedlings in the current seedling box is sufficient, and obtaining a seedling amount detection result; Based on the mud blocking result and the rice seedling quantity detection result, the abnormal result of the second seedling box is obtained.

[0078] In one embodiment, determining the proportion of the seedling area of ​​each row in the seedling image to obtain the ratio of the seedlings of each row includes: Converting the color space of the rice seedling image to obtain a rice seedling conversion image; The seedling area of ​​each row is determined in the seedling conversion image, and the proportion of the seedling area of ​​each row is calculated to obtain the seedling ratio of each row.

[0079] In one embodiment, it further includes: Performing image segmentation on the rice seedling image to obtain a rice seedling pixel area; Determine the sparsity of the rice seedlings based on the number of pixels in the rice seedling pixel area and the number of pixels in the rice seedling image; Based on the mud blocking results and the seedling sparseness, the abnormal result of the third seedling box is obtained.

[0080] In one embodiment, performing image segmentation on the rice seedling image to obtain a rice seedling pixel area includes: Inputting the rice seedling image into a preset rice seedling segmentation model to obtain a rice seedling segmentation mask; Based on the rice seedling segmentation mask, the rice seedling pixel area is obtained.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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 abnormality in a seedling box of a rice transplanter, characterized in that: include: Acquire seedling images in real time; Calculating the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; Based on the current rice seedling ratio, a mud blocking result is obtained; Based on the mud blocking results, an abnormal result of the first seedling box is obtained.

2. The method according to claim 1, characterized in that The method of obtaining the mud blocking result based on the current rice seedling ratio includes: Calculate the difference between the rice seedling ratio at the previous moment and the current rice seedling ratio to obtain a ratio change value; Comparing the ratio change value with a preset ratio change threshold to obtain a comparison result; Based on the comparison result, the mud plugging result is obtained.

3. The method according to claim 1, characterized in that Also includes: Determining the proportion of the rice seedling area in each row in the rice seedling image to obtain the rice seedling ratio in each row; Based on the ratio of the seedlings in each row, judging whether the amount of the seedlings in the current seedling box is sufficient, and obtaining a seedling amount detection result; Based on the mud blocking results and the rice seedling quantity detection results, the abnormal result of the second seedling box is obtained.

4. The method according to claim 3, characterized in that Determining the proportion of the seedling area of ​​each row in the seedling image to obtain the ratio of the seedlings of each row includes: Converting the color space of the rice seedling image to obtain a rice seedling conversion image; The seedling area of ​​each row is determined in the seedling conversion image, and the proportion of the seedling area of ​​each row is calculated to obtain the seedling ratio of each row.

5. The method according to claim 1, characterized in that Also includes: Performing image segmentation on the rice seedling image to obtain a rice seedling pixel area; Determine the sparsity of the rice seedlings based on the number of pixels in the rice seedling pixel area and the number of pixels in the rice seedling image; Based on the mud blocking results and the seedling sparseness, the abnormal result of the third seedling box is obtained.

6. The method according to claim 5, characterized in that The step of performing image segmentation on the rice seedling image to obtain a rice seedling pixel area comprises: Inputting the rice seedling image into a preset rice seedling segmentation model to obtain a rice seedling segmentation mask; Based on the rice seedling segmentation mask, the rice seedling pixel area is obtained.

7. A device for detecting abnormality of a seedling box of a rice transplanter, characterized in that: include: An acquisition module, used for acquiring rice seedling images in real time; A calculation module, used for calculating the proportion of the rice seedling area in the rice seedling image to obtain a current rice seedling ratio; A judgment module, used for obtaining a mud blocking result based on the current rice seedling ratio; The detection module is used to obtain the abnormal result of the first seedling box based on the mud blocking result.

8. A rice transplanter, characterized in that: The seedling box of the rice transplanter is detected by using the abnormality detection method of the seedling box of the rice transplanter as described in any one of claims 1 to 7.

9. 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 method for detecting abnormalities in a seedling box of a rice transplanter according to any one of claims 1 to 6 by executing the instructions stored in the memory.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for detecting abnormality in a seedling box of a rice transplanter according to any one of claims 1 to 6.

Images