Crop morphology detection method, device, equipment and storage medium

Abstract

The application discloses a crop morphology detection method, device, equipment and storage medium. The technical scheme provided by the embodiment of the application comprises the following steps: acquiring first image data and second image data of a to-be-detected area, wherein the second image data comprises ground height information of the to-be-detected area; determining a lodging area in the to-be-detected area according to ground color information in the first image data and the ground height information in the second image data; and determining a lodging degree of the lodging area according to the ground height information of the lodging area. Through the above technical means, the problem that the crop morphology detection method based on pixel points in the prior art has low detection precision and cannot determine the lodging degree due to noise influence is solved, the crop lodging detection precision is improved, and the accuracy of the loss determination result is improved.

Description

Technical Field

[0001] This application relates to the field of agricultural technology, and in particular to a method, apparatus, equipment and storage medium for crop morphology detection. Background Technology

[0002] Crop morphology detection is a widely used technique in agricultural production, used to determine crop growth status or predict yield. Crops lodging, a type of abnormal growth condition, can lead to significant yield reductions or even total crop failure, causing substantial economic losses. After lodging occurs, the extent of the lodging can be assessed by agricultural insurance companies to facilitate claims and mitigate economic losses.

[0003] Current crop morphology detection methods are pixel-based. By extracting image features of the crop region, the crop morphology of corresponding pixels can be detected based on these features, and the presence or absence of lodging can be determined accordingly. However, this method is susceptible to noise, resulting in low accuracy in lodging detection and an inability to determine the degree of lodging, thus affecting the accuracy of damage assessment. Summary of the Invention

[0004] This application provides a crop morphology detection method, apparatus, equipment, and storage medium, which solves the problem that the existing pixel-based crop morphology detection methods have low detection accuracy due to noise and cannot determine the degree of lodging, thereby improving the accuracy of crop lodging detection and the accuracy of damage assessment results.

[0005] Firstly, this application provides a method for detecting crop morphology, including:

[0006] Acquire first image data and second image data of the area to be detected, wherein the second image data includes ground height information of the area to be detected;

[0007] Based on the ground color information in the first image data and the ground height information in the second image data, the collapsed area in the area to be detected is determined;

[0008] The degree of lodging in the lodged area is determined based on the ground height information of the lodged area.

[0009] Secondly, this application provides a crop morphology detection device, comprising:

[0010] The image data acquisition module is configured to acquire first image data and second image data of the area to be detected, wherein the second image data includes ground height information of the area to be detected.

[0011] The collapsed area determination module is configured to determine the collapsed area in the area to be detected based on the ground color information in the first image data and the ground height information in the second image data;

[0012] The lodging degree determination module is configured to determine the lodging degree of the lodging area based on the ground height information of the lodging area.

[0013] Thirdly, this application provides a crop morphology detection device, comprising:

[0014] One or more processors; a storage device storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the crop morphology detection method as described in the first aspect.

[0015] Fourthly, this application provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the crop morphology detection method as described in the first aspect.

[0016] This application acquires first and second image data of the area to be inspected, the second image data including ground height information of the area to be inspected; based on ground color information in the first image data and ground height information in the second image data, it determines the lodging areas within the area to be inspected; and based on the ground height information of the lodging areas, it determines the degree of lodging in the lodging areas. By combining the ground height and ground color information of the area to be inspected, the lodging areas are determined, improving the accuracy of lodging area detection. Determining the degree of crop lodging using the ground height information of the lodging areas improves the accuracy of damage assessment results. Attached Figure Description

[0017] Figure 1 This is a flowchart of a crop morphology detection method provided in an embodiment of this application;

[0018] Figure 2 This is a flowchart of determining the lodged area provided in an embodiment of this application;

[0019] Figure 3 This is a flowchart illustrating the process of determining an edge set, as provided in an embodiment of this application.

[0020] Figure 4 This is a flowchart of image data binarization processing provided in an embodiment of this application;

[0021] Figure 5 This is a flowchart of the edge set denoising correction provided in the embodiments of this application;

[0022] Figure 6This is a flowchart of the modified edge set provided in the embodiments of this application;

[0023] Figure 7 This is a schematic diagram of the area to be detected provided in an embodiment of this application;

[0024] Figure 8 This is a flowchart illustrating the determination of the degree of lodging in the lodging area, provided in an embodiment of this application.

[0025] Figure 9 This is a flowchart illustrating the determination of sub-regions corresponding to various degrees of lodging, provided in an embodiment of this application.

[0026] Figure 10 This is a schematic diagram of the sub-regions corresponding to the degree of lodging provided in the embodiments of this application;

[0027] Figure 11 This is a flowchart illustrating the gradient range for optimizing the degree of lodging, provided in an embodiment of this application.

[0028] Figure 12 This is a schematic diagram of the structure of a crop morphology detection device provided in an embodiment of this application;

[0029] Figure 13 This is a schematic diagram of the structure of a crop morphology detection device provided in an embodiment of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0031] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0032] The crop morphology detection method provided in this embodiment can be executed by a crop morphology detection device, which can be implemented through software and / or hardware. This device can consist of two or more physical entities, or it can be a single physical entity. For example, the crop morphology detection device can be a server or other device with strong computing power, or it can be an intelligent device that collects image data, such as an unmanned aerial vehicle (UAV). For instance, when the server is the executing entity of the crop morphology detection method, the server receives remote sensing image data of the crop area sent by the UAV and determines the lodging areas in the crop area based on the remote sensing image data. When the UAV is the executing entity of the crop morphology detection method, after acquiring remote sensing image data of the crop area, the UAV determines the lodging areas in the crop area based on the remote sensing image data.

[0033] The crop morphology detection device is equipped with at least one type of operating system, including but not limited to Android, Linux, and Windows. The crop morphology detection device can install at least one application based on the operating system. This application can be a built-in application of the operating system or an application downloaded from a third-party device or server. In this embodiment, the crop morphology detection device has at least one application capable of executing the crop morphology detection method; therefore, the crop morphology detection device itself can also be the application.

[0034] For ease of understanding, this embodiment uses a server as the main entity executing the crop morphology detection method as an example for description.

[0035] In one embodiment, after receiving remote sensing image data of a crop area sent by an unmanned device, the server processes the remote sensing image data to obtain orthophoto data of the crop area, and extracts image features from the orthophoto data to obtain image features of the crop area. Based on the image features, the server detects the crop morphology of corresponding pixels and determines whether the crop has lodged. Based on the lodged pixels, the server identifies the lodged areas within the crop area, and determines the area of ​​the lodged areas and their proportion within the total area of ​​the crop area. The server then uses the area and proportion of the lodged areas for agricultural insurance loss assessment to obtain the assessment result. However, the method of detecting crop morphology based on image features is easily affected by image noise, leading to false detections of crop morphology and reducing the accuracy of lodged area detection. Furthermore, the degree of lodging within a lodged area may vary, and different degrees of lodging have different impacts on crop yield. Therefore, the loss assessment result determined based on the lodged area cannot accurately reflect the degree of economic loss to the crop area.

[0036] To address the aforementioned issues, this embodiment provides a crop morphology detection method to improve the accuracy of crop lodging detection and determine the degree of lodging.

[0037] Figure 1 A flowchart of a crop morphology detection method provided in an embodiment of this application is given. (Reference) Figure 1 The crop morphology detection method specifically includes:

[0038] S110. Obtain first image data and second image data of the area to be detected. The second image data includes ground height information of the area to be detected.

[0039] In this embodiment, the area to be detected refers to the crop area, such as farmland, used to detect crop lodging. The first image data refers to orthophoto data, the second image data refers to a digital terrain model, and the ground height information refers to the crop height within the area to be detected as included in the digital terrain model.

[0040] In one embodiment, the crop to be detected for lodging is selected, and the planting area of ​​this crop is determined as the detection area. An expanded flight path is planned for the mapping task in this area. The mapping task is assigned to an unmanned aerial vehicle (UAV), which then flies along the flight path and collects remote sensing images of the detection area. After completing the mapping task, the UAV processes all the remote sensing images collected during the task to obtain model data such as DOM, DEM, DSM, and LAS. The UAV sends the DOM, DEM, DSM, and LAS model data to a server. The server performs crop morphology detection based on the DOM, DEM, DSM, and LAS model data to determine the lodged area and degree of lodging within the detection area. Agricultural insurance loss assessment is then performed based on the lodged area and degree of lodging. In this embodiment, DOM is the first image data used, and DSM is the second image data used. In this embodiment, the UAV can be a remote sensing mapping drone with RTK functionality, which can be implemented based on cloud base stations, mobile base stations, or third-party satellite technology. The drone is not limited to multi-rotor, fixed-wing, vertical take-off and landing, and compound-wing drones. The drone is equipped with an image acquisition device to collect images of the area to be detected. The image acquisition device is not limited to visible light cameras, lidar, infrared cameras, and hyperspectral cameras.

[0041] In one embodiment, a detection area larger than the crop planting area is determined on a satellite map. Based on the geographical location and area of ​​the detection area, a mapping task and flight path are planned. When the geographical area of ​​the detection area is larger than the maximum aerial surveying area of ​​the remote sensing mapping drone, the flight path is divided into multiple sub-paths according to the maximum operational efficiency algorithm. Multiple remote sensing mapping drones fly along their respective sub-paths to collect remote sensing image data, which is then uploaded to the server. The server processes the remote sensing image data uploaded by the multiple remote sensing mapping drones to obtain model data of the detection area. When the ground area of ​​the detection area is less than or equal to the maximum aerial surveying area of ​​the remote sensing mapping drone, one remote sensing mapping drone collects remote sensing image data of the detection area along the flight path, processes the remote sensing image data to obtain model data of the detection area, and uploads the model data to the server.

[0042] S120. Based on the ground color information in the first image data and the ground height information in the second image data, determine the collapsed area in the area to be detected.

[0043] In this context, ground color information refers to the pixel values ​​of each pixel in the first image data, which can represent the crop color in the area to be detected. Ground height information refers to the height values ​​of each pixel in the second image data, which can represent the crop height in the area to be detected. Since the area to be detected is planned based on the crop planting area, and the crops in the area to be detected are of the same category, the crops in the area to be detected have a certain degree of uniformity in color and height information. Therefore, this embodiment combines the crop color information and crop height information to detect crop lodging, thereby improving the accuracy of lodging detection.

[0044] In one embodiment, Figure 2 This is a flowchart illustrating the process of determining the collapsed area, as provided in an embodiment of this application. Figure 2 As shown, the steps for determining the lodged area specifically include S1201-S1202:

[0045] S1201. Determine the edge set of the collapsed area based on the ground color information in the first image data and the ground height information in the second image data.

[0046] For example, an edge set refers to a set of pixels whose grayscale values ​​change drastically from those of surrounding pixels. Since there is a color difference between lodged and unlodged crops, edge detection on the first image data can determine the edge sets of lodged and unlodged crops. However, due to noise in edge detection, directly performing edge detection on the first image data of the area to be detected may detect other edges within that area. Therefore, this embodiment proposes that the approximate lodged area range can be determined based on ground color information in the first image data and ground height information in the second image data, and edge detection can be performed on this range to filter out other edge noise in the area to be detected. In this embodiment, Figure 3 This is a flowchart illustrating the process of determining an edge set, as provided in an embodiment of this application. Figure 3 As shown, the steps for determining the edge set specifically include S12011-S12012:

[0047] S12011. Perform color binarization on the first image data and height binarization on the second image data, and determine the overlapping area of ​​the two binarized image data.

[0048] For example, the colors and heights of the lodged and unlodged crops differ. Crops in the first image data can be roughly distinguished based on the color of the lodged crops; similarly, crops in the second image data can be roughly distinguished based on the height of the lodged crops. Binarization processing can divide an image into black and white regions. Therefore, the first image data can be binarized based on the color of the lodged crops, roughly dividing the first image data into lodged and unlodged areas. Similarly, the second image data can be binarized based on the height of the lodged crops, roughly dividing the second image data into lodged and unlodged areas.

[0049] In this embodiment, Figure 4 This is a flowchart illustrating the binarization process for image data provided in an embodiment of this application. For example... Figure 4 As shown, the specific steps for binarizing image data include S120111-S120113:

[0050] S120111. Obtain the color histogram of the first image data, and determine the main color threshold of the first image data based on the color histogram.

[0051] For example, a color histogram of the first image data is plotted, and the proportion of each crop color in the first image data is obtained based on the color histogram. The color with the highest proportion is determined as the main color threshold of the first image data. Since the proportion of lodging-resistant crops in the first image data is the largest, and the color of lodging-resistant crops has the largest proportion in the first image data, the main color threshold can be determined as the color of lodging-resistant crops in the first image data through the color histogram.

[0052] S120112. Obtain the height histogram of the second image data, and determine the main height threshold of the second image data based on the height histogram.

[0053] For example, a height histogram of the second image data is plotted, and the proportion of each crop height in the second image data is obtained based on the height histogram. The height with the highest proportion is determined as the main height threshold of the second image data. Since the proportion of lodging-free crops in the second image data is the largest, and the height of lodging-free crops accounts for the largest proportion in the second image data, the main height threshold can be determined as the height of lodging-free crops in the second image data through the height histogram.

[0054] S120113. Binarize the first image data according to the main color threshold, and binarize the second image data according to the main height threshold.

[0055] For example, after binarizing the first image data using a primary color threshold, the grayscale values ​​of pixels in the first image data with pixel values ​​greater than or equal to the primary color threshold are set to 255, and the grayscale values ​​of pixels in the first image data with pixel values ​​less than the primary color threshold are set to 0. Similarly, after binarizing the second image data using a primary height threshold, the grayscale values ​​of pixels in the second image data with height values ​​greater than or equal to the primary height threshold are set to 255, and the grayscale values ​​of pixels in the second image data with height values ​​less than the primary height threshold are set to 0.

[0056] Furthermore, the pixel regions with a grayscale value of 0 in the first image data can be considered as lodged areas roughly determined based on crop color, and the pixel regions with a grayscale value of 0 in the second image data can be considered as lodged areas roughly determined based on crop height. By comparing the lodged areas in the first and second image data, the overlapping area is determined as the lodged area range. The crops within this overlapping area simultaneously meet the requirements of both the height and color of the lodged crops.

[0057] S12012. Perform edge detection on the overlapping areas in the first image data, determine the feature value of each pixel in the overlapping areas, and determine the edge points in the edge set based on the feature values.

[0058] For example, since the crops in the overlapping region simultaneously satisfy the height and color of the lodged crops estimated based on histograms, edge detection can be performed on the overlapping region in the first image data to determine the edge set of the lodged region within the overlapping region. This edge set includes multiple pixels with feature values ​​greater than a preset threshold.

[0059] S1202, The edge set is corrected according to the pixel gradient value of the first image data and the height threshold of the second image data, and the collapsed area in the first image data and / or the second image data is determined according to the corrected edge set.

[0060] For example, since the overlapping area is roughly the collapsed area, its edge detection will still contain noise. In this case, noise reduction correction can be performed on the edge set to remove pixels in the edge set that do not belong to the edge of the collapsed area, or to add pixels in the edge set that belong to the edge of the collapsed area. In this embodiment, Figure 5 This is a flowchart illustrating the denoising correction of edge sets provided in an embodiment of this application. For example... Figure 5 As shown, the steps for denoising and correcting the edge set specifically include S12021-S12023:

[0061] S12021. Perform grayscale processing on the first image data and determine the pixel gradient value of each pixel based on the grayscale image.

[0062] For example, grayscale processing is performed on the first image data to obtain the grayscale image. Based on the pixel difference between each pixel and its surrounding pixels in the grayscale image, the pixel gradient value of each pixel is determined. The pixel gradient value can be used to characterize the pixel change trend between the corresponding pixel and its surrounding pixels. Since there is a large pixel difference between the pixel values ​​of the collapsed area and the non-collapsed area, the pixel gradient values ​​of the edge points of the collapsed area are relatively large. Therefore, it can be determined whether a pixel is an edge point of the collapsed area based on its pixel gradient value.

[0063] S12022. Determine the height threshold for each pixel based on the height histogram of the second image data.

[0064] For example, the height histogram of the second image data divides the second image data into multiple image regions corresponding to different height ranges based on the height of each pixel. Pixels within the same image region correspond to the same height range. The maximum height within the height range corresponding to a pixel is used as the height threshold for that pixel. Since there is a height difference between the height values ​​of collapsed and non-collapsed areas, the pixel's height threshold can be used to determine whether it is an edge point of a collapsed area.

[0065] S12023. Adjust the edge points in the edge set according to the pixel gradient value and height threshold of each pixel.

[0066] For example, the pixel gradient value and height threshold of a pixel are combined to determine whether the pixel is an edge point of a collapsed region. In this embodiment, Figure 6 This is a flowchart of the corrected edge set provided in an embodiment of this application. For example... Figure 6 As shown, the steps for correcting the edge set based on pixel gradient values ​​and height thresholds specifically include S120231-S120232:

[0067] S120231. The pixel gradient value and height threshold of the pixel are weighted to obtain the weighted value of the pixel.

[0068] For example, the pixel gradient value and height threshold are configured with corresponding weight coefficients, which are set according to actual needs. The weighted value of the pixel is obtained by multiplying the pixel gradient value by the corresponding weight coefficient and then adding the height threshold multiplied by the corresponding weight coefficient.

[0069] S120232. Add the weighted value of the pixel to the feature value, and adjust the edge points in the edge set according to the added pixel values.

[0070] For example, when performing edge detection on overlapping regions in the first image data, the feature value of each pixel is calculated. The feature value of the pixel is added to its corresponding weighted value to obtain the score value of that pixel. The higher the score value of a pixel, the greater the probability that the pixel is an edge point. Based on the score values ​​of each pixel in the overlapping region, the edge points of the collapsed area are determined. Edge points in the edge set are then added or removed based on these edge points to eliminate noise points in the edge set and / or add new edge points, thereby improving the accuracy of collapsed area detection.

[0071] Furthermore, based on the denoised edge set, the corresponding collapsed area is extracted from the first image data and / or the second image data, and the geographical area of ​​the collapsed area is calculated based on the polygon differential method.

[0072] S130. Determine the degree of lodging in the lodged area based on the ground height information of the lodged area.

[0073] Figure 7 This is a schematic diagram of the area to be detected provided in an embodiment of this application. For example... Figure 7 As shown, the degree of lodging varies among crops within the lodging area, and the morphology of crops differs depending on the degree of lodging. Taking rice as an example, the degree of lodging is divided into three levels. In the first level, the rice stem tilt angle is less than 45 degrees; in the second level, the rice stem tilt angle is greater than 45 degrees; and in the third level, the rice stems and ears are completely flat against the ground. The higher the level, the more severe the lodging and the lower the rice height. Therefore, the degree of lodging can be determined based on the crop height within the lodging area.

[0074] In one embodiment, Figure 8 This is a flowchart illustrating the determination of the degree of lodging in the lodged area, provided in an embodiment of this application. For example... Figure 8 As shown, the steps for determining the degree of lodging in the lodged area specifically include S1301-S1302:

[0075] S1301. Determine the height gradient value of the collapsed area based on the ground height information of the collapsed area in the second image data.

[0076] For example, based on the height difference between each pixel and its surrounding pixels in the second image data, a height gradient value for each pixel is determined. This height gradient value can be used to characterize the height change trend between the corresponding pixel and its surrounding pixels. (Reference) Figure 7 Based on the degree of crop lodging, the lodged area can be divided into sub-regions corresponding to various degrees of lodging. Significant height differences exist between crops in different sub-regions, resulting in large height gradients at the edge points of these sub-regions. Therefore, the edge set of a sub-region can be determined based on the height gradient values ​​of its pixels.

[0077] S1302. Determine the degree of lodging in the lodging area based on the height gradient value of the lodging area.

[0078] In this embodiment, Figure 9 This is a flowchart illustrating the determination of sub-regions corresponding to various degrees of lodging, as provided in an embodiment of this application. For example... Figure 9 As shown, the steps for determining the sub-regions corresponding to various degrees of lodging specifically include SS13021-S13022:

[0079] S13021. Compare the height gradient value of each pixel in the collapsed area with the preset gradient range corresponding to various degrees of collapse, and determine the pixel whose height gradient value meets the gradient range as the edge point of the corresponding degree of collapse.

[0080] S13022. Determine the corresponding sub-regions in the collapsed area based on the edge points corresponding to various degrees of lodging.

[0081] For example, when configuring a surveying task, the lodging degree and the corresponding gradient range are configured according to the selected crop category. The server obtains the lodging degree and the corresponding gradient range of the crop based on the surveying task. The gradient range corresponding to the lodging degree refers to the gradient range covered by the minimum and maximum height gradient values ​​corresponding to that lodging degree. When the height gradient value of a pixel in the lodging region falls within the gradient range corresponding to a certain lodging degree, that pixel is determined as an edge point of that lodging degree. The connected region enclosed by all edge points corresponding to a certain lodging degree is determined as the sub-region corresponding to that lodging degree. Figure 10 This is a schematic diagram of the sub-regions corresponding to the degree of lodging provided in the embodiments of this application. For example... Figure 10 As shown, for Figure 7 After performing crop morphology detection on the first and second image data of the area to be detected as provided in this embodiment, the lodged area and sub-regions corresponding to various degrees of lodging within the lodged area are obtained. Different colors are used to mark the sub-regions corresponding to various degrees of lodging in the first image data of the area to be detected. Figure 10 The central area has an area of ​​105.36m². 2 and 35.94m 2 The sub-region has an area of ​​8.51m². 2 The sub-region has an area of ​​73.59m². 2 The sub-regions are sub-regions with different degrees of landslide. In this embodiment, the area of ​​the sub-regions in the first image data can be calculated based on polygon differentiation to obtain the geographical area of ​​each sub-region.

[0082] In one embodiment, Figure 11 This is a flowchart illustrating the gradient range for optimizing the degree of lodging, as provided in an embodiment of this application. For example... Figure 11 As shown, the steps for optimizing the gradient range of the lodging degree specifically include S1401-S1402:

[0083] S1401. Based on the height gradient value of each edge point in each sub-region, calculate the height gradient histogram.

[0084] S1402. Adjust the gradient range corresponding to the degree of lodging based on the area ratio of the sub-region in the lodging area and the ratio of each gradient range in the height gradient histogram.

[0085] For example, based on the height gradient values ​​of all edge points in all sub-regions, a height gradient histogram of the collapsed area is calculated, and the proportion of each gradient range in the histogram is determined. The geographical area of ​​the collapsed area and each sub-region is calculated using polygon differentiation, and the area proportion of each sub-region within the collapsed area is also calculated. Since the height gradient histogram is calculated based on the height gradient values ​​of edge points, the proportion of its height gradient range can be considered as the standard proportion of each sub-region within the collapsed area. The pre-set gradient range corresponding to the degree of collapse is derived from historical data; therefore, based on the estimated sub-region proportions and the standard proportions, the gradient range corresponding to the degree of collapse is fine-tuned to improve its accuracy.

[0086] In one embodiment, a project report can be generated based on the area and degree of lodging of each sub-region within the lodged area. The project report includes, for example, the following: Figure 10 The diagram showing the lodged area, along with other data, enhances the visualization of the project report. The report can be imported into a third-party platform, such as an agricultural insurance claims assessment platform, to determine the economic loss from lodging and improve the accuracy of the assessment. Alternatively, it can be imported into agricultural machinery, such as a harvester, to adjust the harvester's bucket height in the lodged area, achieving precise harvesting of the lodged crops.

[0087] In summary, the crop morphology detection method provided in this application acquires first and second image data of the area to be detected, the second image data including ground height information of the area to be detected; based on ground color information in the first image data and ground height information in the second image data, lodging areas within the area to be detected are determined; and based on the ground height information of the lodging areas, the degree of lodging is determined. By combining the ground height and ground color information of the area to be detected, the accuracy of lodging area detection is improved. Determining the degree of crop lodging using the ground height information of the lodging areas improves the accuracy of damage assessment results.

[0088] Based on the above embodiments, Figure 12This is a schematic diagram of a crop morphology detection device provided in an embodiment of this application. (Reference) Figure 12 The crop morphology detection device provided in this embodiment specifically includes: an image data acquisition module 21, a lodging area determination module 22, and a lodging degree determination module 23.

[0089] The image data acquisition module is configured to acquire first image data and second image data of the area to be detected, wherein the second image data includes ground height information of the area to be detected.

[0090] The landslide area determination module is configured to determine the landslide area in the area to be detected based on the ground color information in the first image data and the ground height information in the second image data.

[0091] The lodging degree determination module is configured to determine the lodging degree of the lodging area based on the ground height information of the lodging area.

[0092] Based on the above embodiments, the collapsed area determination module includes: an edge set determination submodule, configured to determine the edge set of the collapsed area based on the ground color information in the first image data and the ground height information in the second image data; and a collapsed area determination submodule, configured to correct the edge set based on the pixel gradient value of the first image data and the height threshold of the second image data, and determine the collapsed area in the first image data and / or the second image data based on the corrected edge set.

[0093] Based on the above embodiments, the edge set determination submodule includes: an overlapping region determination unit, configured to perform color binarization processing on the first image data and height binarization processing on the second image data, and determine the overlapping region of the two binarized image data; and an edge set determination unit, configured to perform edge detection on the overlapping region in the first image data, determine the feature value of each pixel in the overlapping region, and determine the edge points in the edge set based on the feature values.

[0094] Based on the above embodiments, the overlapping region determination unit includes: a color histogram acquisition subunit configured to acquire a color histogram of the first image data and determine a major color threshold of the first image data based on the color histogram; a height histogram acquisition subunit configured to acquire a height histogram of the second image data and determine a major height threshold of the second image data based on the height histogram; and a binarization processing subunit configured to perform binarization processing on the first image data based on the major color threshold and on the second image data based on the major height threshold.

[0095] Based on the above embodiments, the submodule for determining the collapsed area includes: a pixel gradient value determination unit, configured to perform grayscale processing on the first image data and determine the pixel gradient value of each pixel based on the grayscale image; a height threshold determination unit, configured to determine the height threshold of each pixel based on the height histogram of the second image data; and an edge set correction unit, configured to adjust the edge points in the edge set based on the pixel gradient value and the height threshold of each pixel.

[0096] Based on the above embodiments, the edge set correction unit includes: a weighted value calculation subunit, configured to perform weighted processing on the pixel gradient value and height threshold of the pixel to obtain the weighted value of the pixel; and an edge point adjustment subunit, configured to add the weighted value of the pixel to the feature value, and adjust the edge points in the edge set according to the added pixel.

[0097] Based on the above embodiments, the lodging degree determination module includes: a height gradient value determination submodule, configured to determine the height gradient value of the lodging area based on the ground height information of the lodging area in the second image data; and a lodging degree determination submodule, configured to determine the lodging degree of the lodging area based on the height gradient value of the lodging area.

[0098] Based on the above embodiments, the lodging degree determination submodule includes: an edge point determination unit, configured to compare the height gradient value of each pixel in the lodging region with a preset gradient range corresponding to various lodging degrees, and determine the pixel whose height gradient value satisfies the gradient range as the edge point of the corresponding lodging degree; and a sub-region determination unit, configured to determine the corresponding sub-region in the lodging region based on the edge points corresponding to various lodging degrees.

[0099] Based on the above embodiments, the crop morphology detection device further includes: a gradient histogram determination module, configured to calculate a height gradient histogram based on the height gradient value of each edge point of each sub-region; and a gradient range optimization module, configured to adjust the gradient range corresponding to the degree of lodging based on the area ratio of the sub-region in the lodging area and the ratio of each gradient range in the height gradient histogram.

[0100] The crop morphology detection device provided in this application, as described above, acquires first image data and second image data of the area to be detected, the second image data including ground height information of the area to be detected; determines the lodging area within the area to be detected based on ground color information in the first image data and ground height information in the second image data; and determines the degree of lodging in the lodging area based on the ground height information of the lodging area. By combining the ground height information and ground color information of the area to be detected, the lodging area is determined, improving the detection accuracy of the lodging area. Determining the degree of lodging of the crop based on the ground height information of the lodging area improves the accuracy of the damage assessment results.

[0101] The crop morphology detection device provided in this application embodiment can be used to execute the crop morphology detection method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0102] Figure 13 This is a schematic diagram of the structure of a crop morphology detection device provided in an embodiment of this application, with reference to... Figure 13 The crop morphology detection device includes a processor 31, a memory 32, a communication device 33, an input device 34, and an output device 35. The number of processors 31 and the number of memories 32 in the crop morphology detection device can be one or more. The processor 31, memory 32, communication device 33, input device 34, and output device 35 of the crop morphology detection device can be connected via a bus or other means.

[0103] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the crop morphology detection method in any embodiment of this application (e.g., image data acquisition module 21, lodging area determination module 22, and lodging degree determination module 23 in the crop morphology detection device). The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory 32 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0104] The communication device 33 is used for data transmission.

[0105] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 32, thereby realizing the crop morphology detection method described above.

[0106] Input device 34 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 35 may include display devices such as a display screen.

[0107] The crop morphology detection equipment provided above can be used to perform the crop morphology detection method provided in the above embodiments, and has corresponding functions and beneficial effects.

[0108] This application embodiment also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a crop morphology detection method. The crop morphology detection method includes: acquiring first image data and second image data of a region to be detected, the second image data including ground height information of the region to be detected; determining lodging areas in the region to be detected based on ground color information in the first image data and ground height information in the second image data; and determining the degree of lodging in the lodging areas based on the ground height information of the lodging areas.

[0109] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROM, floppy disk, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which the program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0110] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the crop morphology detection method described above, but can also perform related operations in the crop morphology detection method provided in any embodiment of this application.

[0111] The crop morphology detection device, storage medium, and crop morphology detection equipment provided in the above embodiments can execute the crop morphology detection method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the crop morphology detection method provided in any embodiment of this application.

[0112] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application. The scope of this application is determined by the scope of the claims.

Claims

1. A method for detecting crop morphology, characterized in that, include: Acquire first image data and second image data of the area to be detected, wherein the second image data includes ground height information of the area to be detected; Based on the ground color information in the first image data and the ground height information in the second image data, the collapsed area in the area to be detected is determined; The degree of lodging in the lodged area is determined based on the ground height information of the lodged area; This includes: determining the height gradient value of the collapsed area based on the ground height information of the collapsed area in the second image data; comparing the height gradient value of each pixel in the collapsed area with a preset gradient range corresponding to various degrees of collapse, and determining the pixels whose height gradient values ​​satisfy the gradient range as edge points of the corresponding degree of collapse; and determining the corresponding sub-regions in the collapsed area based on the edge points corresponding to various degrees of collapse. Based on the height gradient value of each edge point of each sub-region, a height gradient histogram is calculated; based on the area ratio of the sub-region in the collapsed area and the ratio of each gradient range in the height gradient histogram, the gradient range corresponding to the degree of collapse is adjusted.

2. The crop morphology detection method according to claim 1, characterized in that, The step of determining the collapsed area in the area to be detected based on the ground color information in the first image data and the ground height information in the second image data includes: Based on the ground color information in the first image data and the ground height information in the second image data, the edge set of the collapsed area is determined; The edge set is corrected based on the pixel gradient value of the first image data and the height threshold of the second image data, and the collapsed area in the first image data and / or the second image data is determined based on the corrected edge set.

3. The crop morphology detection method according to claim 2, characterized in that, Determining the edge set of the collapsed area based on the ground color information in the first image data and the ground height information in the second image data includes: The first image data is subjected to color binarization and the second image data is subjected to height binarization, and the overlapping area of ​​the two binarized image data is determined. Edge detection is performed on the overlapping regions in the first image data to determine the feature value of each pixel in the overlapping regions, and the edge points in the edge set are determined based on the feature values.

4. The crop morphology detection method according to claim 3, characterized in that, The step of performing color binarization on the first image data and height binarization on the second image data includes: Obtain the color histogram of the first image data, and determine the main color threshold of the first image data based on the color histogram. The main color threshold is the crop color with the highest proportion in the color histogram. Obtain the height histogram of the second image data, and determine the main height threshold of the second image data based on the height histogram. The main height threshold is the crop height with the highest proportion in the height histogram. The first image data is binarized based on the primary color threshold, and the second image data is binarized based on the primary height threshold.

5. The crop morphology detection method according to any one of claims 2-4, characterized in that, The step of correcting the edge set based on the pixel gradient values ​​of the first image data and the height threshold of the second image data includes: The first image data is processed to grayscale, and the pixel gradient value of each pixel is determined based on the grayscale image. Based on the height histogram of the second image data, determine the height threshold for each pixel. The edge points in the edge set are adjusted based on the pixel gradient value and height threshold of each pixel.

6. The crop morphology detection method according to claim 5, characterized in that, The step of adjusting the edge points in the edge set based on the pixel gradient value and height threshold of each pixel includes: The pixel gradient value and height threshold of the pixel are weighted to obtain the weighted value of the pixel. The weighted value of the pixel is added to the feature value, and the edge points in the edge set are adjusted based on the added pixel value.

7. A crop morphology detection device, characterized in that, include: The image data acquisition module is configured to acquire first image data and second image data of the area to be detected, wherein the second image data includes ground height information of the area to be detected. The collapsed area determination module is configured to determine the collapsed area in the area to be detected based on the ground color information in the first image data and the ground height information in the second image data; The lodging degree determination module is configured to determine the lodging degree of the lodging area based on the ground height information of the lodging area; specifically, the lodging degree determination module is configured to: determine the height gradient value of each pixel in the lodging area based on the ground height information of the lodging area in the second image data; compare the height gradient value of each pixel in the lodging area with a preset gradient range corresponding to various lodging degrees, determine the pixels whose height gradient values ​​satisfy the gradient range as edge points of the corresponding lodging degree, and determine the corresponding sub-regions in the lodging area based on the edge points corresponding to various lodging degrees; The gradient histogram determination module is configured to calculate a height gradient histogram based on the height gradient value of each edge point of each sub-region. The gradient range optimization module is configured to adjust the gradient range corresponding to the degree of lodging based on the area ratio of the sub-region in the lodging region and the ratio of each gradient range in the height gradient histogram, wherein the ratio of the height gradient range is the standard ratio of each sub-region in the lodging region.

8. A crop morphology detection device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the crop morphology detection method as described in any one of claims 1-6.

9. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the crop morphology detection method as described in any one of claims 1-6.

Images