Real-time discrimination system for crop drought grade
By designing a real-time judgment system for crop drought levels, and using the Mask R-CNN model to preprocess and judge crop images, the problem of difficulty in time and accurately determining drought levels in the existing technology is solved, real-time and accurate judgment of drought levels is achieved, and the normality of crop growth is ensured.
Patent Information
- Application Number
- CN202411868017.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-18
- Publication Date
- 2025-04-11
AI Technical Summary
The existing technology relies on manual inspections, making it difficult to timely and accurately determine the drought levels of each growth stage of the crop on a large scale, resulting in the possibility of missing a rescue opportunity and affecting crop growth.
Design a real-time discrimination system for crop drought levels, including image collectors and monitors. The image collector collects images of crops, and the monitor uses image storage, preprocessing, model construction and real-time discrimination modules to use the Mask R-CNN model to judge the drought level of crops in real time.
It has achieved timely and accurate identification of changes in crop drought levels on a large scale, avoided missing rescue opportunities, and ensured the normality of crop growth.
Smart Images
Figure CN119810651A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of crop drought level identification, and specifically relates to a real-time crop drought level identification system. Background Art
[0002] Crop crops often suffer from varying degrees of drought at various growth stages, such as the jointing stage, the tasseling and silking stage, and the milky and mature stages. The drought levels are usually divided into no drought, light drought, moderate drought, and severe drought. Accurately identifying the drought level at each growth stage of crops and taking corresponding rescue measures in a timely manner are of great significance for ensuring the normal growth of crops.
[0003] At present, most people rely on manual inspections to judge the drought level at various growth stages of crops. This method is extremely dependent on manual experience, consumes a lot of manpower, and is prone to omissions. It is difficult to ensure that changes in drought levels at various growth stages of crops can be judged in a timely manner over a large area, which may lead to missed rescue opportunities and serious impacts on crop growth.
[0004] This application is proposed in view of the above-mentioned technical defects.
[0005] It should be noted that the disclosure of the above background technology content is only used to assist in understanding the inventive concept and technical solution of the present invention, and it does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this application, the above background technology should not be used to evaluate the novelty and creativity of the present application. Summary of the invention
[0006] The purpose of the present application is to provide a real-time determination system of crop drought level to overcome or alleviate at least one of the known technical deficiencies.
[0007] The technical solution of this application is:
[0008] A real-time determination system for crop drought level, comprising an image collector and a monitor;
[0009] The image collector is used to collect images of crops at different growth stages suffering from different drought levels, as well as to collect real-time images of crops;
[0010] The monitor has an image storage module, an image preprocessing module, a model building module, and a real-time discrimination module;
[0011] The image storage module is used to store images of crops at different growth stages suffering from different drought levels and real-time images of crops;
[0012] The image preprocessing module is used to preprocess images of crops at different growth stages suffering from different drought levels and real-time images of crops;
[0013] The model building module is used to train the MaskR-CNN model using images of crops at different growth stages suffering from different drought levels as input, and to construct a drought level discrimination model for crops at different growth stages based on leaf curling.
[0014] The real-time discrimination module is used to use a drought level discrimination model for crops at different growth stages based on leaf curling to discriminate the drought level of crops in real-time images and obtain the drought level of crops.
[0015] Optionally, in the above-mentioned real-time identification system of crop drought level, the image collector is a camera that can rotate freely, or a drone with a camera.
[0016] Optionally, in the above-mentioned real-time determination system of crop drought level, the monitor is a high-performance computer with a display.
[0017] Optionally, in the above-mentioned real-time identification system of crop drought level, the image preprocessing module preprocesses images of crops at different growth stages suffering from different drought levels and real-time images of crops, specifically:
[0018] The images of crops at different growth stages suffering from different drought levels and the real-time images of crops were compressed into a size of 1920×1280, and the curled leaves of the crops were annotated using the image annotation tool LabelMe software. After each image was annotated, a JSON format file was generated, which contained annotation information such as the image's location coordinates, category label, and image size. The open source computer vision library OpenCV was used to annotate the annotated images and draw the coordinate image of each curled leaf.
[0019] Optionally, in the above-mentioned real-time discrimination system for crop drought levels, in the model building module, 80% of the images of crops suffering from different drought levels at different growth stages are divided into a training set and 20% are divided into a test set to train the Mask R-CNN model.
[0020] Optionally, in the above-mentioned real-time discrimination system for crop drought level, in the model construction module, the Mask R-CNN model uses a convolution kernel to automatically extract image features, and the convolution kernel slides on the image to generate a feature map.
[0021] Optionally, in the above-mentioned real-time discrimination system of crop drought level, in the model building module, in the Mask R-CNN model, RoI Align uses a bilinear interpolation method to achieve pixel-to-pixel alignment, instead of RoIPooling to perform pooling operations on feature maps.
[0022] Optionally, in the above-mentioned real-time discrimination system for crop drought level, in the model building module, the mean average precision MAP of the model detection, the precision Precision of the model, the recall rate Recall of the model, and the mean average precision F1 are used. score , perform model evaluation and parameter tuning.
[0023] This application has at least the following beneficial technical effects:
[0024] A real-time discrimination system for crop drought levels is provided. By collecting images of crops suffering from different drought levels at different growth stages, preprocessing them, and using them as input to train a Mask R-CNN model, a discrimination model for crop drought levels at different growth stages based on leaf curling is obtained. Then, crop images can be collected in real time, preprocessed, and the discrimination model for crop drought levels at different growth stages based on leaf curling is used to discriminate drought levels, thereby obtaining the drought levels of crops. The system can timely and accurately discriminate changes in crop drought levels over a large range, thereby preventing the opportunity for rescue from being missed and avoiding situations that seriously affect crop growth. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 Schematic diagram of a real-time determination system of crop drought level provided in an embodiment of the present application;
[0026] Figure 2 Schematic diagram of the Mask R-CNN model structure provided in the embodiment of the present application;
[0027] Figure 3 This is a schematic diagram of an embodiment of the present application, which uses images of crops suffering from different drought levels at different growth stages as input, trains the Mask R-CNN model, and obtains a drought level discrimination model for crops at different growth stages based on leaf curling.
[0028] In order to better illustrate this embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product. In addition, the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. DETAILED DESCRIPTION
[0029] In order to make the technical solution and advantages of the present application clearer, the technical solution of the present application will be further described in detail in detail and in detail in conjunction with the accompanying drawings. It can be understood that the specific embodiments described here are only partial embodiments of the present application, which are only used to explain the present application, not to limit the present application. It should be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, and other related parts can refer to the general design. In the absence of conflict, the embodiments in the present application and the technical features in the embodiments can be combined with each other to obtain new embodiments.
[0030] In addition, unless otherwise defined, the technical terms or scientific terms used in the description of this application shall be the common meanings understood by the general technicians in the field to which this application belongs. The words "upper", "lower", "left", "right", "center", "vertical", "horizontal", "inside", "outside" and other words indicating orientation used in the description of this application are only used to indicate the relative direction or positional relationship, and do not imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. When the absolute position of the described object changes, its relative positional relationship may also change accordingly, so it cannot be understood as a limitation on this application. The "first", "second", "third" and similar terms used in the description of this application are only used for descriptive purposes to distinguish different components, and cannot be understood as indicating or implying relative importance. The similar words "one", "one" or "the" used in the description of this application should not be understood as an absolute limitation on quantity, but should be understood as the existence of at least one. The similar words "including" or "comprising" used in the description of this application mean that the elements or objects appearing in front of the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.
[0031] In addition, it should be noted that, unless otherwise clearly specified and limited, the words "installed", "connected", "connected" and similar terms used in the description of this application should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, an indirect connection through an intermediate medium, or the internal connection of two components. Technical personnel in the field can understand their specific meanings in this application according to the specific circumstances.
[0032] The impact of different drought levels on crops is usually directly reflected in the curling degree of crop leaves. Based on this, the embodiment of the present application provides a real-time determination system for crop drought levels, such as Figure 1 shown.
[0033] The real-time identification system of crop drought level includes an image collector and a monitor.
[0034] The image collector and the monitor are wirelessly connected, and specifically can be connected via a signal antenna to enable signal transmission.
[0035] Image collectors and monitors can be powered by solar panels.
[0036] The image collector can be a freely rotating camera or a drone with a camera, which can collect images of crops at different growth stages suffering from different drought levels, as well as real-time images of crops, and can collect crop images every two hours. The growth stages of crops can include jointing stage, tasseling-silking stage, and milk-maturity stage.
[0037] The monitor can be a high-performance computer with a display, which has a control module, an image storage module, an image preprocessing module, a model building module, and a real-time identification module.
[0038] The control module can control the image collector. For example, when the image collector is a freely rotating camera, the control module can control the time, frequency, and angle of the camera's rotation. When the image collector is a drone with a camera, the control module can control the time, frequency, and flight trajectory of the drone.
[0039] The image storage module is used to store images of crops at different growth stages suffering from different drought levels and real-time images of crops.
[0040] The image preprocessing module is used to preprocess images of crops at different growth stages suffering from different drought levels and real-time images of crops.
[0041] The images of crops at different growth stages suffering from different drought levels and the real-time images of crops were compressed into a size of 1920×1280, and the curled leaves of the crops were annotated using the image annotation tool LabelMe software. After each image was annotated, a JSON format file was generated, which contained annotation information such as the image's location coordinates, category label, and image size. The open source computer vision library OpenCV was used to annotate the annotated images and draw the coordinate image of each curled leaf.
[0042] The model building module is used to train the MaskR-CNN model using images of crops at different growth stages suffering from different drought levels as input, and to construct a drought level discrimination model for crops at different growth stages based on leaf curling, such as Figure 3 shown.
[0043] The Mask R-CNN model was trained by dividing 80% of the images of crops at different growth stages suffering from different drought levels into training sets and 20% into test sets.
[0044] The Mask R-CNN model structure is as follows: Figure 2 shown.
[0045] The Mask R-CNN model uses convolution kernels to automatically extract image features. The convolution kernels slide on the image to generate feature maps to reduce the spatial dimension of the input data.
[0046] In the Mask R-CNN model, RoI Align uses bilinear interpolation to achieve pixel-to-pixel alignment, instead of RoIPooling to perform pooling operations on feature maps. During instance segmentation, the feature maps can be better mapped to the original image.
[0047] In the Mask R-CNN model, the input includes the number of curled leaves, curl confidence and segmentation mask (border length and width) of the image. By calculating the curl confidence of the curled leaves, the maximum, minimum, mean, variance and standard deviation of the border coordinates and the length and width of the rectangular border, the drought level is graded according to the curl information of the leaves to obtain the drought level of the crop.
[0048] In the Mask R-CNN model, the mean average precision MAP, the model's precision Precision, the model's recall rate Recall, and the mean average precision F1 are used for model detection score , perform model evaluation and parameter tuning.
[0049]
[0050]
[0051]
[0052]
[0053] Among them, TP is a positive example with correct classification; FP is a positive example with incorrect classification; FN and TN are respectively a negative example with incorrect classification and a negative example with correct classification; N is the number of image samples;
[0054] Precision is the accuracy of the model; Recall is the recall rate of the model; F1 score It is the harmonic mean of the model accuracy and recall rate; MAP is the mean average precision of the model detection.
[0055] The real-time discrimination module is used to use a drought level discrimination model for crops at different growth stages based on leaf curling to discriminate the drought level of crops in real-time images and obtain the drought level of crops.
[0056] The real-time discrimination system for crop drought level disclosed in the above embodiment collects images of crops suffering from different drought levels at different growth stages, performs preprocessing, and uses the images as input to train the Mask R-CNN model to obtain a discrimination model for crop drought levels at different growth stages based on leaf curling. Then, crop images can be collected in real time, preprocessed, and the discrimination model for crop drought levels at different growth stages based on leaf curling can be used to discriminate drought levels, thereby obtaining the drought level of the crops. This system can timely and accurately discriminate changes in crop drought levels over a large range, thereby preventing missed rescue opportunities and avoiding situations that seriously affect crop growth.
[0057] In addition, technicians in the field should also be able to realize that the various modules of the real-time discrimination system for crop drought level disclosed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, this application generally describes them according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Technicians in the field can choose to adopt different methods to implement the described functions for each specific application and its actual constraints, but such implementation should not be considered to be beyond the scope of this application.
[0058] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. Those skilled in the art should understand that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the scope of protection of the present application.
Claims
1. A real-time determination system for crop drought level, characterized in that: Including image collector and monitor; The image collector is used to collect images of crops at different growth stages suffering from different drought levels, as well as to collect real-time images of crops; The monitor has an image storage module, an image preprocessing module, a model building module, and a real-time discrimination module; The image storage module is used to store images of crops at different growth stages suffering from different drought levels and real-time images of crops; The image preprocessing module is used to preprocess images of crops at different growth stages suffering from different drought levels and real-time images of crops; The model building module is used to train the Mask R-CNN model using images of crops at different growth stages experiencing different drought levels as input, and to construct a drought level discrimination model for crops at different growth stages based on leaf curling. The real-time discrimination module is used to use a drought level discrimination model for crops at different growth stages based on leaf curling to discriminate the drought level of crops in real-time images and obtain the drought level of crops.
2. The real-time determination system of crop drought level according to claim 1, characterized in that: The image collector is a freely rotating camera, or a drone equipped with a camera.
3. The real-time determination system of crop drought level according to claim 1, characterized in that: A monitor is a high-performance computer with a display.
4. The real-time determination system of crop drought level according to claim 1, characterized in that: The image preprocessing module preprocesses images of crops at different growth stages suffering from different drought levels and real-time images of crops, specifically: The images of crops at different growth stages suffering from different drought levels and the real-time images of crops were compressed into a size of 1920×1280, and the curled leaves of the crops were annotated using the image annotation tool LabelMe software. After each image was annotated, a JSON format file was generated, which contained annotation information such as the image's location coordinates, category label, and image size. The open source computer vision library OpenCV was used to annotate the annotated images and draw the coordinate image of each curled leaf.
5. The real-time determination system of crop drought level according to claim 1, characterized in that: In the model building module, 80% of the images of crops at different growth stages suffering from different drought levels are divided into training sets and 20% are divided into test sets to train the Mask R-CNN model.
6. The real-time determination system of crop drought level according to claim 1, characterized in that: In the model building module, the Mask R-CNN model uses convolution kernels to automatically extract image features, and the convolution kernels slide on the image to generate feature maps.
7. The real-time determination system of crop drought level according to claim 1, characterized in that: In the model building module, in the Mask R-CNN model, RoIAlign uses bilinear interpolation to achieve pixel-to-pixel alignment, replacing RoIPooling to perform pooling operations on feature maps.
8. The real-time determination system of crop drought level according to claim 1, characterized in that: In the model building module, the mean average precision MAP, model precision Precision, model recall Recall, and mean average precision F1 of the model detection are used score , perform model evaluation and parameter tuning.