Intelligent detection system for field wheat ear pest and disease damage

Abstract

The invention relates to the technical field of image processing, in particular to an intelligent detection system for field wheat ear diseases and insect pests. The system comprises an image acquisition module which is used for acquiring a field wheat ear image; the illumination analysis module is used for constructing an illumination influence coefficient based on a brightness value distribution condition in a neighborhood pixel block of each pixel point; the gray analysis module is used for determining a feature influence coefficient based on the gray value distribution condition in the neighborhood of each pixel point in the neighborhood pixel block; the image enhancement module is used for adaptively adjusting a preset basic attenuation parameter based on the feature influence coefficient and the illumination influence coefficient, and performing image enhancement on the wheat ear image in combination with a non-local mean filtering algorithm; the disease and insect pest detection module is used for detecting disease and insect pests of the wheat ears through the enhanced image; during denoising, detail reservation of the pest and disease damage area is enhanced, effective denoising is carried out, and the accuracy of subsequent field wheat ear pest and disease damage detection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an intelligent detection system for wheat ear diseases and insect pests in the field. BACKGROUND

[0002] Wheat ear diseases and insect pests are represented by scab, powdery mildew, smut, aphids and sap-sucking insects. The occurrence of these diseases and insect pests is influenced by multiple factors such as climate conditions, cultivation methods and variety resistance, which can have a significant impact on food safety and production yield of wheat. Therefore, detection of wheat ear diseases and insect pests is an important part of current smart agriculture, and is of great significance for yield prediction, disease monitoring and precision agriculture. With the development of deep learning technology, the detection method of wheat ear diseases and insect pests based on target detection algorithm shows significant advantages.

[0003] At present, when detecting wheat ear diseases and insect pests in the field by combining computer vision, considering that the wheat ear image may be affected by the field environment light and the image shooting device during acquisition, uneven illumination may occur, and the early details of the wheat ear diseases and insect pests are easily affected by the noise generated by the light, which makes it difficult to accurately obtain the local details of the wheat ear diseases and insect pests. When the conventional denoising algorithm is used to deal with the above-mentioned light influence, it is easy to cause the loss of disease and insect pest details due to over-denoising, which affects the detection accuracy of the wheat ear diseases and insect pests in the subsequent use of deep learning algorithm model. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide an intelligent detection system for wheat ear diseases and insect pests in the field, and the technical solution adopted is as follows: The present application provides an intelligent detection system for wheat ear diseases and insect pests in the field, which comprises: An image acquisition module: acquiring the image of wheat ear in the field, and obtaining the gray value and brightness value of each pixel point in the image; An illumination analysis module: determining the neighborhood pixel block of each pixel point through a preset neighborhood window; determining the illumination influence coefficient of the neighborhood pixel block of each pixel point based on the brightness value distribution in the neighborhood pixel block; A gray analysis module: determining the feature influence coefficient of the neighborhood pixel block based on the degree of confusion of the neighborhood gray value distribution and the occurrence of the same gray value pixel points in each pixel point in the neighborhood pixel block; An image enhancement module: determining a comprehensive influence coefficient of a neighborhood pixel block of each pixel point based on the feature influence coefficient and the illumination influence coefficient; determining an adaptive attenuation parameter corresponding to each search pixel point in the search window of the target pixel point based on the difference between the comprehensive influence coefficients of the target pixel point and each search pixel point in the search window of the target pixel point, combining a preset basic attenuation parameter, and performing image enhancement on the wheat ear image by using a non-local mean filtering algorithm; A disease and pest detection module: detecting diseases and pests of the wheat ear by using the enhanced image.

[0005] In one embodiment, the neighborhood pixel block is obtained by: taking a pixel block composed of all pixel points in a preset neighborhood window of each pixel point as the neighborhood pixel block of each pixel point.

[0006] In one embodiment, the illumination influence coefficient is obtained by: Interval distribution statistics are performed on the luminance values of the pixel points in the neighborhood pixel block of each pixel point, and a light feature value of the neighborhood pixel block of each pixel point is constructed based on the statistical results. The illumination influence coefficient of the neighborhood pixel block of each pixel point is determined based on the mean value of the luminance values of the pixel points in the neighborhood pixel block and the light feature value, and the illumination influence coefficient is positively correlated with the mean value of the luminance values and negatively correlated with the light feature value.

[0007] In one embodiment, the light feature value is obtained by: The number of pixel points with a luminance value greater than or equal to a preset threshold and the number of pixel points with a luminance value less than the preset threshold in the neighborhood pixel block of each pixel point are counted respectively, and are denoted as a first number and a second number respectively; and the difference between the first number and the second number is taken as the light feature value of the neighborhood pixel block of each pixel point.

[0008] In one embodiment, the feature influence coefficient is obtained by: For any pixel point c in the neighborhood pixel block of each pixel point, interval distribution statistics are performed on the gray values of the pixel points in the neighborhood of the pixel point c, and a gray feature value of the neighborhood of the pixel point c is constructed based on the statistical results; a mean value of the gray feature values of the neighborhoods of all pixel points in the neighborhood pixel block is calculated and is denoted as a first mean value; the difference between the gray feature values of the neighborhoods of the pixel points in the neighborhood pixel block and the first mean value is denoted as a first difference; and the number of pixel point pairs with the same gray value in the neighborhood of the pixel point c in the neighborhood pixel block is obtained. The feature influence coefficient of the neighborhood pixel block is positively correlated with the first difference and negatively correlated with the number of pixel point pairs with the same gray value.

[0009] In one embodiment, the gray feature value is obtained by: The number of pixel points in the neighborhood of the pixel point c and having a gray value greater than the preset threshold value and the number of pixel points in the neighborhood of the pixel point c and having a gray value less than the preset threshold value are counted respectively, and are denoted as a third number and a fourth number respectively; a difference value between the third number and the fourth number in the neighborhood of the pixel point c is calculated as a gray feature value of the neighborhood of the pixel point c.

[0010] In one embodiment, the pair of pixel points with the same gray value is a pair of two pixel points with the same gray value.

[0011] In one embodiment, the comprehensive influence coefficient is a product of the illumination influence coefficient and the feature influence coefficient of the neighborhood pixel block of each pixel point.

[0012] In one embodiment, the adaptive attenuation parameter is obtained by the following process: A negative correlation mapping function of a difference between the comprehensive influence coefficients of the neighborhood pixel blocks of the two pixel points is used as an influence difference coefficient between the neighborhood pixel blocks of the two pixel points, and a product of the influence difference coefficient between the neighborhood pixel blocks of the target pixel point and each to-be-searched pixel point in the search window of the target pixel point and a preset basic attenuation parameter is used as the adaptive attenuation parameter corresponding to each to-be-searched pixel point in the search window of the target pixel point.

[0013] In one embodiment, the expression of the influence difference coefficient is: In the expression, a represents the influence difference coefficient between the neighborhood pixel block of the pixel point a and the neighborhood pixel block of the to-be-searched pixel point b in the search window of the pixel point a; b represents the comprehensive influence coefficient of the neighborhood pixel block of the pixel point a; c represents the comprehensive influence coefficient of the neighborhood pixel block of the to-be-searched pixel point b; and e represents an exponential function with a natural constant as a base.

[0014] The present application has the following beneficial effects: ​​​​This application addresses the need for denoising in intelligent detection of pests and diseases in wheat ears during field image acquisition, considering the interference of lighting conditions. Uneven lighting and high local noise can occur due to the influence of ambient light and imaging equipment, causing detailed pest and disease features to be easily obscured. Conventional non-local mean filtering algorithms, which use fixed attenuation parameters for denoising, often result in poor denoising performance. This application analyzes the denoising requirements under pest and disease conditions and firstly... The illumination influence coefficient of each pixel's neighborhood is constructed using the light intensity value of the neighborhood, taking into account the impact of light intensity on the diseased and pest-affected areas. The feature influence coefficient of each pixel's neighborhood is constructed using the grayscale value of the neighborhood, taking into account the differences in local grayscale changes between the diseased and pest-affected areas and the normal wheat ear areas. Adaptive attenuation parameters are set based on the feature influence coefficient and illumination influence coefficient of the neighborhood pixels to ensure that the nonlocal mean filtering algorithm enhances the preservation of details in the diseased and pest-affected areas and effectively removes noise when denoising wheat ear disease and pest images, further improving the accuracy of subsequent field detection of wheat ear diseases and pests. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A block diagram of an intelligent detection system for wheat ear diseases and pests in the field, provided as an embodiment of this application; Figure 2 This is a schematic diagram illustrating the process of obtaining the illumination influence coefficient. Figure 3 This is a flowchart of an intelligent detection system for diseases and pests on wheat ears in the field. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent detection system for wheat ear diseases and pests in the field proposed according to this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The specific scheme of the intelligent detection system for field wheat ear diseases and insect pests provided by the application will be specifically described below in combination with the drawings.

[0020] Please refer to Figure 1 which shows a block diagram of an intelligent detection system for field wheat ear diseases and insect pests provided by an embodiment of the application, the system comprising: An image acquisition module 101 acquires field wheat ear images, and obtains the gray value and brightness value of each pixel point in the image.

[0021] Common diseases and insect pests of wheat ears include scab, smut and aphid damage, etc. To intelligently detect field wheat ear diseases and insect pests, a professional camera with a high-definition camera is first used to acquire images of field wheat ears with diseases and insect pests.

[0022] Further, the acquired field wheat ear images are preprocessed, the wheat ear images are taken as the input of the weighted average method, and gray scale processing is performed, and the output is a gray scale image of the wheat ear. It should be noted that for the gray scale processing of the wheat ear images, the present application only provides a gray scale processing method, and there are many existing gray scale processing methods, and other gray scale processing methods such as the maximum value method, the minimum value method and the average value method can also be used for image gray scale processing, and the present application does not make specific limitations. At the same time, the RGB image of the wheat ear image is converted into an HSV space image, and the V channel image is extracted to obtain a brightness image of the wheat ear image.

[0023] The gray value and brightness value of each pixel point in the wheat ear image can be obtained through the gray scale image and the brightness image.

[0024] An illumination analysis module 102 determines the neighborhood pixel block of each pixel point through a preset neighborhood window; and determines the illumination influence coefficient of the neighborhood pixel block of each pixel point based on the brightness value distribution in the neighborhood pixel block of each pixel point.

[0025] Considering that in the planting production process of wheat, when the wheat ear is affected by diseases and pests, the early characteristics of the diseases and pests of the wheat ear usually show the characteristics of small lesion area, low color contrast and irregular shape, which are easy to be confused with noise. The light in the field changes at different times and weather conditions, and when acquiring the image of the diseases and pests of the wheat ear region, it will be affected by uneven light, resulting in a large amount of noise interference, so the acquired image needs to be denoised. Based on the above analysis, the non-local mean filtering algorithm is selected to denoise the original RGB image. In the filtering process, a large search window and a small neighborhood window need to be defined. Considering that the wheat ear image needs to be processed in a large range to find similar wheat ear regions that are not affected by light, the size of the search window is set to 21x21 in this embodiment. To avoid the situation that the neighborhood window is too small to be sensitive to noise or too large to ignore details, the size of the neighborhood window is set to 5x5 in this embodiment. In other embodiments of the application, the implementer can set the size of the search window and the neighborhood window according to the actual situation.

[0026] However, in the denoising process, considering that the wheat ear image is affected by uneven light, the higher brightness may cause local overexposure of the corresponding part of the wheat ear image, and further cause the noise to be severely amplified. In the case of weak light and shadow, the pixel values of the corresponding region are generally low, and when there is a disease and pest in the region, the detailed features of the disease and pest are blurred, which are easy to be misjudged as noise and smoothed out.

[0027] Therefore, based on the above analysis, taking any pixel point a in the search window of the wheat ear image as an example, the neighborhood window centered on the pixel point a is obtained, and all the pixel points in the 5x5 neighborhood window are combined into a pixel block as the neighborhood pixel block of the pixel point a. Further, the brightness value of each pixel point can be obtained from the obtained brightness image, and the brightness values of all the pixel points in the neighborhood pixel block are taken as the input of the Otsu method, and the output segmentation threshold is denoted as the first segmentation threshold T. The number of pixel points with a brightness value greater than or equal to the first segmentation threshold T and the number of pixel points with a brightness value less than the first segmentation threshold T in the neighborhood pixel block are counted respectively and denoted as the first number and the second number respectively. The difference between the first number and the second number is calculated as the brightness feature value of the neighborhood pixel block.

[0028] Further, based on the above analysis, the illumination influence coefficient of the neighborhood pixel block is constructed to indicate the influence of light on the neighborhood pixel block of each pixel point, and the expression is: In the formula, the illumination influence coefficient of the neighborhood pixel block of the pixel point a; This represents the average brightness value of all pixels in the neighborhood pixel block of pixel a; This represents the brightness feature value of the neighboring pixel block of pixel a; This represents the total number of pixels in the neighborhood pixel block of pixel a; It is an exponential function with the natural constant e as the base.

[0029] When the pixel block is located in a bright lighting condition The values ​​are relatively large, and the proportion of pixels with brightness values ​​greater than or equal to the threshold T is higher. The larger the value, the better the calculated result. A larger value indicates that the pixel area is affected by stable bright lighting; when the pixel is located in a darker lighting condition... The values ​​are relatively small, and the proportion of pixels with brightness values ​​less than the threshold T is higher. The smaller the value, the better the calculated result. The smaller the value, the more likely the pixel area is affected by stable, relatively dim lighting conditions.

[0030] The grayscale analysis module 103 determines the feature influence coefficient of the neighboring pixel block based on the degree of disorder in the distribution of grayscale values ​​of each pixel in the neighborhood and the occurrence of pixels with the same grayscale value.

[0031] Considering the significant differences between diseased and healthy wheat areas when pests and diseases occur, diseased and pest-affected areas exhibit distinct characteristics compared to healthy wheat areas. For example, the pink mold layer of mildew, the black spore masses of smut, and clusters of aphids are scattered across the wheat ears.

[0032] Therefore, the distribution of gray values ​​in the 8-neighborhood of all pixels in the neighboring pixel block of each pixel is analyzed. First, taking any pixel c in the neighboring pixel block of pixel a as an example, the gray values ​​of all pixels in the 8-neighborhood of pixel c are used as the input of Otsu's method, and the output segmentation threshold is recorded as the second segmentation threshold. The number of pixels in the 8-neighborhood of pixel c with gray values ​​greater than the second segmentation threshold and the number of pixels with gray values ​​less than the second segmentation threshold are counted respectively and recorded as the third number and the fourth number. The difference between the third number and the fourth number in the 8-neighborhood of pixel c is calculated as the gray feature value in the 8-neighborhood of pixel c.

[0033] Furthermore, the distribution disorder of the grayscale feature values ​​of all pixels in the 8-neighborhood of pixel a is analyzed, and combined with the number of pairs of pixels with the same grayscale value in the 8-neighborhood of each pixel in the neighborhood of pixel a, the feature influence coefficient of the neighborhood of pixel a is constructed, and the expression is: In the formula, represents the characteristic influence coefficient of the neighborhood pixel block of the pixel point a; is a normalized function; represents the total number of pixel points in the neighborhood pixel block of the pixel point a; represents the gray scale characteristic value in the 8-neighborhood of the pixel point c in the neighborhood pixel block of the pixel point a; represents the mean value of the gray scale characteristic values of the 8-neighborhood of all the pixel points in the neighborhood pixel block of the pixel point a, and is denoted as a first mean value; represents the number of pixel point pairs with the same gray scale value in the 8-neighborhood of the pixel point c in the neighborhood pixel block of the pixel point a; is a preset minimum positive number, and in the embodiments of the present application, the value of is set to 1, which prevents the denominator from being 0. In other embodiments of the present application, the value of may be set by the implementer according to the actual situation. The pixel point pair with the same gray scale value is specifically a pixel point pair composed of two pixel points with the same gray scale value. For the number of pixel point pairs with the same gray scale value in the 8-neighborhood, for example, if there are four pixel points with the same gray scale value in the 8-neighborhood, then there are six pixel point pairs according to the permutation and combination. is a first difference.

[0034] When the pixel block is located in the disease and pest area, the mold layer, spores, aphids and the like of the disease and pest present as randomly distributed protruding points, and the number distribution of the pixel points with the gray scale value higher or lower than the segmentation threshold in the 8-neighborhood of each pixel point in the pixel block is random and irregular, and the pixel points in the 8-neighborhood rarely have the same gray scale value. When the pixel block is located in the healthy wheat area, the gray scale value in the 8-neighborhood of each pixel point in the pixel block changes smoothly, the number distribution of the pixel points with the gray scale value higher than the segmentation threshold and the number distribution of the pixel points with the gray scale value lower than the segmentation threshold are balanced, and usually differ little, and the gray scale value of the pixel points in the 8-neighborhood often has the same gray scale value. When the texture of the pixel points in the neighborhood pixel block of the pixel point a is irregular, the value of fluctuates greatly, and the value of Q is relatively small, and the value of calculated and obtained is relatively large, which indicates that the pixel block has more disease and pest details. When the gray scale in the 8-neighborhood of the pixel points in the pixel block is regular, the values of all are relatively stable, and the value of calculated and obtained is relatively small, which indicates that the pixel block mainly represents the healthy wheat spike characteristics.

[0035] The image enhancement module 104 determines the comprehensive influence coefficient of the neighboring pixel blocks of each pixel point based on the feature influence coefficient and the illumination influence coefficient; based on the difference between the comprehensive influence coefficient of the target pixel point and each search pixel point in the preset search window, and combined with the preset basic attenuation parameter, determines the adaptive attenuation parameter corresponding to each search pixel point in the target pixel point search window, and combines the non-local mean filtering algorithm to enhance the image of the wheat ear.

[0036] To address the feature fluctuations and illumination effects within the neighboring pixel blocks of pixel a after illumination, an illumination texture index is constructed. This index is used to characterize the comprehensive evaluation of the illumination effects and local features of each pixel's neighboring pixel blocks. The expression is: In the formula, This represents the combined influence coefficient of the neighboring pixel block of pixel a; This represents the illumination influence coefficient of the neighboring pixel block of pixel a; This represents the feature influence coefficient of the neighboring pixel block of pixel a.

[0037] Furthermore, when weighting the similarity between a target pixel and its neighboring pixel blocks in the search window, it is considered that when the wheat ear image is affected by uneven lighting due to external environment, equipment, etc., pixels in the diseased and pest-affected areas of the image may be assigned a high similarity to pixels in the healthy wheat ear areas due to their similar gray values, resulting in poor noise reduction. Based on the above analysis, when there are differences in lighting and features, it is necessary to increase the attenuation parameter to offset the influence of lighting. When pixel a is the target pixel, for each searchable pixel in the search window of pixel a, the influence difference coefficient between pixel a and its neighboring pixel blocks in the search window is calculated. This coefficient is used to evaluate the differences in lighting and features between the neighboring pixel blocks of the target pixel and the neighboring pixel blocks of the searchable pixel in the corresponding search window. The expression is: In the formula, This represents the coefficient of influence difference between the neighboring pixel blocks of pixel a and the neighboring pixel blocks of the pixel b to be searched within the search window; This represents the combined influence coefficient of the neighboring pixel block of pixel a; This represents the combined influence coefficient of the neighboring pixel block of pixel b; This represents an exponential function with the natural constant as its base.

[0038] When there are significant differences in brightness and features between two pixel blocks, the attenuation parameter needs to be reduced to assign a smaller weight to the pixel being searched, and the calculated value should be... The larger the value, the better. The smaller the value, the smaller the feature difference when the brightness between two pixel blocks is similar. Therefore, it is necessary to increase the attenuation parameter and assign a smaller weight to the pixel being searched. The value increases accordingly.

[0039] Based on the above analysis, adaptive attenuation parameters are constructed for each pixel to be searched, and the expression is as follows: In the formula, This represents the adaptive attenuation parameter corresponding to the weighting of the search pixel b in the search window of the target pixel a; The coefficient representing the difference in influence between the neighboring pixel blocks of pixel a and the neighboring pixel blocks of the pixel b to be searched within the search window; h is a preset base attenuation parameter, which is set to 10 in this embodiment. In other embodiments of this application, the implementer may set the value of h according to the actual situation.

[0040] The RGB image of the wheat ear is used as input to the nonlocal mean filtering algorithm. The adaptive attenuation parameters of each pixel to be searched, calculated in the above manner, are used as the corresponding attenuation parameters in the algorithm. The algorithm is then used to denoise the RGB image of the wheat ear, and the output is the denoised RGB image. The nonlocal mean filtering algorithm is a well-known technique, and its specific steps will not be described in detail.

[0041] The pest and disease detection module 105 detects pests and diseases in the wheat ears using enhanced images.

[0042] The RGB images of wheat ears, after denoising using a nonlocal mean filtering algorithm, were labeled with wheat ear diseases and pests using Lablimg annotation software. The labels were for Fusarium head blight, wheat smut, and aphids. This application input 10,000 RGB images of wheat ears, which were then divided into training, testing, and validation sets in a 7:2:1 ratio. The YOLOv10 algorithm was used to train the wheat ear disease and pest detection model. Since the detailed features of wheat ear diseases are mainly small targets, a CBAM attention mechanism was added to the core of the algorithm. This mechanism uses channel attention to select important feature channels, and then spatial attention to select important regions within these channels, further accurately highlighting the features of small-target diseases and pests. The CIoU loss function was used for localization. When wheat ears are densely distributed, traditional IoU Loss may fail to provide effective gradient directions due to similar overlapping areas, while CIoU Loss can solve this problem by using the distance between the center points. For the classification loss function, the Binary Cross-Entropy (BCE) loss function is selected. Its independent class prediction mechanism avoids direct competition between classes, ensuring independent predictions for different pests and diseases. When a wheat ear is simultaneously infected with multiple pests and diseases, BCE Loss can capture this complex symptom situation. The confidence loss function also uses the Binary Cross-Entropy (BCE) loss function. The optimizer chosen is the adaptive optimizer Adam, which features an adaptive learning rate. It dynamically adjusts the learning rate based on the statistical characteristics of the gradient for different parameters, achieving fast convergence. It is suitable for small datasets and reduces the amount of data labeling required. The prepared dataset is input into the configured YOLOv10 algorithm to train the wheat ear pest and disease detection model, with a maximum of 100 iterations.

[0043] It should be noted that this application provides only one method for selecting the wheat ear disease and pest detection model and setting the parameters in the model. Implementers may also use other neural network models for training. Implementers may set the parameters in the model according to the actual situation. This application does not impose any specific restrictions.

[0044] The trained wheat ear disease and pest detection model is used to perform real-time detection and feedback of wheat ear diseases and pests in the field. The content of module 105 is publicly known, and the specific process will not be described in detail here.

[0045] A schematic diagram illustrating the process of obtaining the illumination influence coefficient is shown below. Figure 2 As shown; a flowchart of an intelligent detection system for wheat ear diseases and pests in the field is as follows. Figure 3 As shown.

[0046] In summary, this application embodiment, during the intelligent detection of diseases and pests in wheat ears in the field, considers the need for image denoising due to lighting interference during image acquisition. Because the image acquisition is affected by field lighting conditions and the image capturing equipment, uneven lighting and significant local noise may occur, causing the detailed features of diseases and pests in the acquired image to be easily obscured by noise. To address the problem that conventional non-local mean filtering algorithms use fixed attenuation parameters for image denoising, resulting in poor denoising effects, this application analyzes the denoising requirements when diseases and pests are present, and firstly... First, the illumination influence coefficient of each pixel's neighborhood is constructed using the light intensity value of each pixel's neighborhood, taking into account the impact of light intensity on the diseased and pest-affected areas. Then, the feature influence coefficient of each pixel's neighborhood is constructed using the grayscale value of each pixel's neighborhood, considering the differences in local grayscale changes between diseased and pest-affected areas and normal wheat ear areas. Based on the feature influence coefficient and illumination influence coefficient of the neighborhood pixel blocks, adaptive attenuation parameters are set to ensure that the non-local mean filtering algorithm effectively preserves details and denoises the diseased and pest-affected areas when denoising wheat ear disease and pest images, further improving the accuracy of subsequent field detection of wheat ear diseases and pests.

[0047] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0049] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An intelligent detection system for wheat ear diseases and pests in the field, characterized in that, The system includes: Image acquisition module: Acquires images of wheat ears in the field and obtains the grayscale and brightness values ​​of each pixel in the image; Illumination Analysis Module: Determines the neighboring pixel blocks of each pixel through a preset neighborhood window; determines the illumination influence coefficient of each pixel's neighboring pixel blocks based on the brightness value distribution in the neighboring pixel blocks; Grayscale analysis module: Determines the feature influence coefficient of a neighboring pixel block based on the degree of disorder in the distribution of grayscale values ​​in the neighborhood of each pixel and the occurrence of pixels with the same grayscale value. Image enhancement module: Based on the feature influence coefficient and the illumination influence coefficient, determine the comprehensive influence coefficient of the neighboring pixel blocks of each pixel; based on the difference between the comprehensive influence coefficient of the target pixel and each search pixel in the preset search window, combined with the preset basic attenuation parameter, determine the adaptive attenuation parameter corresponding to each search pixel in the target pixel search window, and combine with the non-local mean filtering algorithm to enhance the image of wheat ears. Pest and disease detection module: Detects pests and diseases in wheat ears using enhanced images.

2. The intelligent detection system for wheat ear diseases and pests in the field according to claim 1, characterized in that, The process of obtaining the neighboring pixel block is as follows: the pixel block composed of all pixels within the preset neighbor window of each pixel is taken as the neighboring pixel block of each pixel.

3. The intelligent detection system for wheat ear diseases and pests in the field according to claim 1, characterized in that, The process for obtaining the illumination influence coefficient is as follows: The brightness values ​​of pixels in the neighboring pixel blocks of each pixel are statistically distributed over intervals, and the brightness feature values ​​of the neighboring pixel blocks of each pixel are constructed based on the statistical results. The illumination influence coefficient of each pixel's neighboring pixel block is determined based on the average brightness value of the pixels in the neighboring pixel block and the brightness feature value. The illumination influence coefficient is positively correlated with the average brightness value and negatively correlated with the brightness feature value.

4. The intelligent detection system for wheat ear diseases and pests in the field according to claim 3, characterized in that, The process for obtaining the brightness feature value is as follows: The number of pixels with brightness values ​​greater than or equal to a preset threshold and the number of pixels with brightness values ​​less than a preset threshold in the neighboring pixel blocks of each pixel are counted separately and recorded as the first number and the second number, respectively; the difference between the first number and the second number is used as the brightness feature value of the neighboring pixel blocks of each pixel.

5. The intelligent detection system for wheat ear diseases and pests in the field according to claim 1, characterized in that, The process for obtaining the feature influence coefficient is as follows: For any pixel c in the neighborhood pixel block of each pixel, perform interval distribution statistics on the gray values ​​of pixels in the neighborhood of pixel c, and construct the gray value feature value of the neighborhood of pixel c based on the statistical results. Calculate the mean of the gray-level feature values ​​of the neighborhood of all pixels in the neighborhood pixel block, and denote it as the first mean; The difference between the gray-scale feature value of each pixel in the neighborhood of the neighborhood pixel block and the first mean value is denoted as the first difference. Get the number of pairs of pixels with the same gray value in the neighborhood of pixel c within the neighborhood pixel block; The feature influence coefficient of the neighboring pixel block is positively correlated with the first difference and negatively correlated with the number of pixel pairs with the same gray value.

6. The intelligent detection system for wheat ear diseases and pests in the field according to claim 5, characterized in that, The process for obtaining the grayscale feature values ​​is as follows: The number of pixels with gray values ​​greater than a preset threshold and the number of pixels with gray values ​​less than a preset threshold in the neighborhood of pixel c are counted separately and denoted as the third number and the fourth number, respectively. The difference between the third quantity and the fourth quantity in the neighborhood of pixel c is calculated and used as the gray-level feature value of the neighborhood of pixel c.

7. The intelligent detection system for wheat ear diseases and pests in the field according to claim 5, characterized in that, The same grayscale value pixel pair is a pixel pair consisting of two pixels with the same grayscale value.

8. The intelligent detection system for wheat ear diseases and pests in the field according to claim 1, characterized in that, The comprehensive influence coefficient is the product of the illumination influence coefficient and the feature influence coefficient of the neighboring pixel blocks of each pixel.

9. The intelligent detection system for wheat ear diseases and pests in the field according to claim 1, characterized in that, The process of obtaining the adaptive attenuation parameter is as follows: The negative correlation mapping function of the difference between the comprehensive influence coefficients of the neighboring pixel blocks of two pixels is used as the influence difference coefficient between the neighboring pixel blocks of two pixels. The product of the influence difference coefficient between the target pixel and the neighboring pixel blocks of each search pixel in its search window and the preset basic attenuation parameter is used as the adaptive attenuation parameter corresponding to each search pixel in the search window of the target pixel.

10. The intelligent detection system for wheat ear diseases and pests in the field according to claim 9, characterized in that, The expression for the coefficient of difference is: In the formula, This represents the coefficient of influence difference between the neighboring pixel blocks of pixel a and the neighboring pixel blocks of the pixel b to be searched within the search window; This represents the combined influence coefficient of the neighboring pixel block of pixel a; This represents the combined influence coefficient of the neighboring pixel block of pixel b; This represents an exponential function with the natural constant as its base.

Images