Kelp culture area monitoring method, device, equipment and medium

Abstract

The invention relates to a kelp culture area monitoring method, device and equipment and a medium, and relates to the technical field of kelp culture area monitoring. The kelp cultivation area monitoring method comprises the following steps: acquiring a plurality of remote sensing images corresponding to a plurality of first time intervals in a kelp harvesting period in a kelp cultivation area; according to each remote sensing image, determining a first actually measured kelp culture area of each first time interval; determining a second actually measured kelp culture area of at least one second time interval in the kelp harvesting period; and according to each first actually measured kelp culture area and at least one second actually measured kelp culture area, determining predicted kelp culture areas of the first time interval and the second time interval. According to the kelp culture area monitoring method, the actually measured kelp culture area in the kelp harvesting period is taken as the basis, the precision, robustness and interpretability of the predicted kelp culture area are ensured, and comprehensive and accurate technical support is provided for informatization management and scientific decision-making of the kelp culture industry.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of kelp cultivation area monitoring, and in particular to a kelp cultivation area monitoring method, device, equipment and medium. BACKGROUND

[0002] The time law of the kelp cultivation area change of the kelp cultivation area in the kelp harvesting period can provide comprehensive and accurate technical support for the informatization management and scientific decision-making of the kelp cultivation industry, and has important application value. Satellite remote sensing technology has the advantages of short observation period, repeated monitoring and wide range of spatial information acquisition of ground objects, and has become a key technical means for dynamic monitoring of the ground. At present, when satellite remote sensing technology is applied to the study of the kelp cultivation area, only the kelp cultivation area is automatically extracted, and there is no effective method to obtain the time law of the kelp cultivation area change of the kelp cultivation area in the kelp harvesting period. SUMMARY

[0003] In order to overcome the problems in the related art, the present application provides a kelp cultivation area monitoring method, device, equipment and medium.

[0004] According to a first aspect of an embodiment of the present application, a kelp cultivation area monitoring method is provided, which comprises: obtaining a plurality of remote sensing images corresponding to a plurality of first time intervals of a kelp cultivation area in a kelp harvesting period; determining a first measured kelp cultivation area of each of the first time intervals according to each of the remote sensing images; determining a second measured kelp cultivation area of at least one second time interval in the kelp harvesting period; determining a predicted kelp cultivation area of the first time interval and the second time interval according to each of the first measured kelp cultivation area and at least one of the second measured kelp cultivation area.

[0005] In some exemplary embodiments of the present application, the determination of the first measured kelp cultivation area of each of the first time intervals according to each of the remote sensing images comprises: dividing each of the remote sensing images into a plurality of image units; determining the ground object corresponding to each of the image units; summing up the area of the region corresponding to the image unit in which the corresponding ground object is kelp in the kelp cultivation area in each of the remote sensing images to obtain each of the first measured kelp cultivation area.

[0006] In some exemplary embodiments of the present application, the determination of the second measured kelp cultivation area of at least one second time interval in the kelp harvesting period comprises: a plurality of the remote sensing images are sorted according to the corresponding first time intervals in sequence; the second measured kelp cultivation area in the second time interval between each two adjacent remote sensing images is determined.

[0007] In some exemplary embodiments of the present application, the second measured kelp cultivation area in the second time interval between each two adjacent remote sensing images is determined, comprising: binary data corresponding to the remote sensing image sorted earlier among each two adjacent remote sensing images is determined, wherein in the binary data, the image unit corresponding to the ground feature of kelp corresponds to a first numerical value, and the image unit corresponding to the ground feature other than kelp corresponds to a second numerical value; the following steps are repeated until the second measured kelp cultivation area in all the second time intervals between each two adjacent remote sensing images corresponding to the first time interval is calculated: the image unit corresponding to the first numerical value in the binary data of the current time interval is taken as a target image unit, the current time interval being the first time interval or the second time interval; the number of target image units in each image unit adjacent to each target image unit is calculated; in the case where the number is less than a preset number, the binary data is updated, so that the target image unit corresponding to the second numerical value is the target image unit whose number in each adjacent image unit is less than the preset number; the second measured kelp cultivation area in the next time interval is determined according to the updated binary data, and the updated binary data is taken as the binary data of the next time interval, the next time interval being the second time interval after the current time interval.

[0008] In some exemplary embodiments of the present application, the preset number is a variable, and the preset number is negatively correlated with the kelp harvesting speed of the kelp cultivation area.

[0009] In some exemplary embodiments of the present application, the predicted kelp cultivation area in the first time interval and the second time interval is determined according to each first measured kelp cultivation area and at least one second measured kelp cultivation area, comprising: a kelp cultivation area nonlinear fitting formula is constructed according to each first measured kelp cultivation area and at least one second measured kelp cultivation area; According to the nonlinear fitting formula of the kelp cultivation area, the predicted kelp cultivation areas of the first time intervals and the second time intervals are determined.

[0010] In some exemplary embodiments of the present application, the method for monitoring the kelp cultivation area further comprises: According to the predicted kelp cultivation areas, kelp spatial distribution data of the kelp cultivation area in the first time intervals and the second time intervals are obtained.

[0011] According to a second aspect of the embodiments of the present application, a device for monitoring a kelp cultivation area is provided, which comprises: The acquisition module is configured to acquire a plurality of remote sensing images corresponding to a plurality of first time intervals in a kelp harvesting period of a kelp cultivation area; The first determination module is configured to determine a first measured kelp cultivation area of each of the first time intervals according to each of the remote sensing images; The second determination module is configured to determine a second measured kelp cultivation area of at least one second time interval in the kelp harvesting period; The third determination module is configured to determine predicted kelp cultivation areas of the first time intervals and the second time intervals according to the first measured kelp cultivation areas and the second measured kelp cultivation area.

[0012] According to a third aspect of the embodiments of the present application, a computer device is provided, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to the first aspect when executing the computer program.

[0013] According to a fourth aspect of the embodiments of the present application, a non-transitory computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method according to the first aspect.

[0014] The technical solutions provided by the embodiments of the present application can have the following beneficial effects: the method for monitoring the kelp cultivation area of the present application is based on the measured kelp cultivation area in the kelp harvesting period with high precision and comprehensive coverage, which ensures the precision, robustness and interpretability of the predicted kelp cultivation area, and the predicted kelp cultivation area reflects the time regularity of the change of the kelp cultivation area in the kelp harvesting period, which can provide comprehensive and accurate technical support for the information management and scientific decision-making of the kelp cultivation industry.

[0015] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0017] Figure 1 is a flow chart of a monitoring method of a kelp cultivation area according to a first exemplary embodiment of the present application; Figure 2 is a flow chart of a monitoring method of a kelp cultivation area according to a second exemplary embodiment of the present application; Figure 3 is a scatter plot of a measured kelp cultivation area over time according to an exemplary embodiment of the present application; Figure 4 is a flow chart of a monitoring method of a kelp cultivation area according to a third exemplary embodiment of the present application; Figure 5 is a flow chart of a monitoring method of a kelp cultivation area according to a fourth exemplary embodiment of the present application; Figure 6 is a plot of a measured kelp cultivation area over time according to an exemplary embodiment of the present application; Figure 7 is a flow chart of a monitoring method of a kelp cultivation area according to a fifth exemplary embodiment of the present application; Figure 8 is a plot of a predicted kelp cultivation area over time according to an exemplary embodiment of the present application; Figure 9 is a flow chart of a monitoring method of a kelp cultivation area according to a sixth exemplary embodiment of the present application; Figure 10 is a block diagram of a monitoring device of a kelp cultivation area according to an exemplary embodiment of the present application; Figure 11 is a block diagram of a computer device according to an exemplary embodiment of the present application.

[0018] In the drawings: 10 - acquisition module; 20 - first determination module; 30 - second determination module; 40 - third determination module; 1100 - computer device; 1101 - calculation unit; 1102 - read-only memory (ROM); 1103 - random access memory (RAM); 1104 - bus; 1105 - input / output (I / O); 1106 - input unit; 1107 - output unit; 1108 - storage unit; 1109 - communication unit. DETAILED DESCRIPTION

[0019] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description below refers to the accompanying drawings, which show, by way of example, specific embodiments with which the application can be practiced. The following detailed description is not intended to limit the application. Rather, the following detailed description includes specific details for the purpose of providing a thorough understanding of the inventive concepts. However, it will be apparent to those skilled in the art that the application can be practiced without these specific details. In some instances, well-known structures and processes have not been described in detail in order to avoid obscuring the application.

[0020] The time law of the kelp cultivation area change of the kelp cultivation area in the kelp harvesting period can provide comprehensive and accurate technical support for the informatization management and scientific decision of the kelp cultivation industry, and has important application value. Satellite remote sensing technology has the advantages of short observation period, repeated monitoring and wide range of spatial information acquisition of ground objects, and has become a key technical means for dynamic monitoring of the ground. At present, when satellite remote sensing technology is applied to the study of the kelp cultivation area, only the kelp cultivation area is automatically extracted, and there is no effective method to obtain the time law of the kelp cultivation area change of the kelp cultivation area in the kelp harvesting period.

[0021] In order to solve the above technical problems, the present application provides a kelp cultivation area monitoring method. A plurality of first time intervals corresponding to a plurality of remote sensing images of the kelp cultivation area in the kelp harvesting period are obtained. According to each remote sensing image, the first measured kelp cultivation area of each first time interval is determined. The second measured kelp cultivation area of at least one second time interval in the kelp harvesting period is determined. According to the first measured kelp cultivation area and the second measured kelp cultivation area, the predicted kelp cultivation area of the first time interval and the second time interval is determined. Based on the measured kelp cultivation area with high precision and comprehensive coverage in the kelp harvesting period, the accuracy, robustness and interpretability of the obtained predicted kelp cultivation area are ensured, and the predicted kelp cultivation area reflects the time law of the kelp cultivation area change of the kelp cultivation area in the kelp harvesting period, which can provide comprehensive and accurate technical support for the informatization management and scientific decision of the kelp cultivation industry.

[0022] The exemplary embodiments of the present application provide a kelp cultivation area monitoring method. As shown in Figure 1 The kelp cultivation area monitoring method shown in the exemplary embodiments of the present application includes: S100, a plurality of first time intervals corresponding to a plurality of remote sensing images of the kelp cultivation area in the kelp harvesting period are obtained.

[0023] The kelp cultivation area is a region for large-scale cultivation of kelp in a specific coastal area through scientific planning and management. In some examples, the kelp cultivation area is a floating raft kelp cultivation area. In the floating raft kelp cultivation area, floating rafts are set up at sea, and seed ropes with kelp seedlings are hung on the floating rafts, so that the kelp grows in natural seawater.

[0024] The kelp harvesting period is a specific time period in a year during which mature kelp is concentratedly harvested. In some examples, the kelp harvesting period is from April to July in a year.

[0025] The plurality of first time intervals correspond to the plurality of remote sensing images one-to-one. The first time interval is a unit time within the kelp harvesting period.

[0026] In some examples, the first time interval is a natural day within the kelp harvesting period. The plurality of remote sensing images of the kelp cultivation area in the natural days within the kelp harvesting period are acquired. The plurality of natural days correspond to the plurality of remote sensing images one-to-one. In some examples, the 13 remote sensing images of the kelp cultivation area on April 5 (i.e., the starting date of the kelp harvesting period), April 17, April 27, May 2, May 7, May 14, May 17, June 6, June 8, June 11, June 24, June 26, and July 21 (i.e., the ending date of the kelp harvesting period) are acquired. In some examples, the plurality of remote sensing images are acquired at the same time of the corresponding natural day. In other examples, the plurality of remote sensing images are acquired at different times of the corresponding natural day.

[0027] In some examples, the remote sensing image is a satellite remote sensing image, which is an image obtained by photographing and scanning the earth or other celestial bodies from space using a remote sensing sensor carried on an artificial satellite. The remote sensing image can be acquired using existing platforms, and the present application does not limit the platform, satellite series, and data set series. The acquired remote sensing image can be a remote sensing image that has been preprocessed, such as radiometric calibration, atmospheric correction, geometric correction, image cropping, and cloud shadow processing, to improve data processing efficiency.

[0028] S200, determining, according to each remote sensing image, a first measured kelp cultivation area of each first time interval.

[0029] In an exemplary embodiment of the present application, as shown in FIG. 2, the step S200 of determining, according to each remote sensing image, a first measured kelp cultivation area of each first time interval includes: Figure 2 S210, dividing each remote sensing image into a plurality of image units.

[0030] Each remote sensing image is divided into a plurality of image units, and each image unit has the same size. In some examples, each pixel of the remote sensing image is taken as an image unit. The pixel of the remote sensing image is the smallest unit constituting the remote sensing image, which corresponds to an actual area on the earth's surface, and the spectral information of the pixel records the reflectivity or radiance of the actual area in a specific waveband (such as the red waveband, the green waveband, the blue waveband, the near-infrared waveband, and the short-wave infrared waveband).

[0031] ​S220, determine the ground object corresponding to each image unit.

[0032] In some examples, each remote sensing image is input into the trained support vector machine (SVM), and the radial basis kernel function in the trained support vector machine is used to determine the ground object corresponding to each image unit in the corresponding remote sensing image. The support vector machine is a powerful machine learning algorithm for classification and regression. The radial basis kernel function is a function used in the support vector machine to handle complex nonlinear classification problems, which measures the similarity between data points to perform classification work.

[0033] In some examples, the ground objects in the kelp cultivation area include kelp, seawater, silt and land. The ground object corresponding to one image unit can be one of kelp, seawater, silt and land.

[0034] In some examples, before determining the ground object corresponding to each image unit using the radial basis kernel function of the trained support vector machine, the support vector machine is trained to obtain the trained support vector machine. The image units corresponding to the ground objects obviously kelp, the image units corresponding to the ground objects obviously seawater, the image units corresponding to the ground objects obviously silt and the image units corresponding to the ground objects obviously land can be selected from the obtained remote sensing images, and the spectral information of the selected image units is recorded. The support vector machine is trained using the ground objects corresponding to the selected image units and the spectral information corresponding to the selected image units, so that the trained support vector machine can determine the ground object corresponding to one image unit according to the spectral information of the image unit.

[0035] S230, in each remote sensing image, sum the area of the region corresponding to the image unit corresponding to the ground object kelp in the kelp cultivation area to obtain each first measured kelp cultivation area.

[0036] The area of the region corresponding to each image unit corresponding to the ground object kelp in the kelp cultivation area in one remote sensing image is summed to obtain the first measured kelp cultivation area corresponding to the first time interval of the remote sensing image. For example, the area of the region corresponding to each image unit corresponding to the ground object kelp in the kelp cultivation area in the remote sensing image corresponding to April 5 is summed to obtain the first measured kelp cultivation area on April 5.

[0037] In some examples, one image unit can correspond to one pixel, and the area of the region corresponding to one image unit in the kelp cultivation area can be the area of the actual region on the earth's surface represented by one pixel, that is, the resolution of the remote sensing sensor. For example, one pixel represents an actual region of 30m x 30m on the earth's surface, and the area of the region corresponding to one image unit in the kelp cultivation area is 900㎡.

[0038] In some examples, Figure 3 is a scatter plot of the first measured kelp cultivation area changing over time. Figure 3 In some examples, the first measured kelp cultivation area in each of the 13 first time intervals includes April 5, April 17, April 27, May 2, May 7, May 14, May 17, June 6, June 8, June 11, June 24, June 26, and July 21.

[0039] In the exemplary embodiments of the present application, after step S220 and before step S230, the determination of the first measured kelp cultivation area in each first time interval according to each remote sensing image in step S200 further includes: performing noise reduction processing and adhesion separation processing on the ground object determination results of the image units of each remote sensing image.

[0040] In some examples, the image units corresponding to the ground objects that are connected into patches in a remote sensing image and are kelp are referred to as a patch, and a patch includes at least two image units corresponding to the ground objects that are kelp. The noise reduction processing is to calculate the area of each patch in the remote sensing image, and remove the patches with an area less than a preset area from the remote sensing image as noise. The preset area can be 1000 square meters. Due to the small spacing between the kelp cultivation rafts, the seawater between some rafts in the remote sensing image will be mistakenly identified as kelp, resulting in adhesion between patches. The adhesion separation processing is to separate the adhesion patches in the remote sensing image by visual interpretation.

[0041] S300, determining a second measured kelp cultivation area in at least one second time interval in the kelp harvesting period.

[0042] The kelp harvesting period includes a plurality of time intervals, and each time interval corresponds to the same unit time. The time interval corresponding to the remote sensing image is the first time interval, and the other time intervals are the second time intervals. The kelp harvesting period includes at least one second time interval.

[0043] In some examples, the kelp harvesting period is from April 5 to July 21, a total of 108 natural days, and one natural day is taken as a time interval. The remote sensing images of the kelp cultivation area on April 5, April 17, April 27, May 2, May 7, May 14, May 17, June 6, June 8, June 11, June 24, June 26, and July 21 are obtained, and the 13 natural days are the first time interval, and the remaining 95 natural days are the second time interval.

[0044] The first measured kelp cultivation area in each first time interval is determined according to the remote sensing image corresponding to the first time interval.

[0045] In some examples, the second measured kelp cultivation area of at least one second time interval is determined according to each remote sensing image.

[0046] In some examples, the second measured kelp cultivation area of each second time interval can be determined according to each remote sensing image using a spatio-temporal interpolation algorithm. The spatio-temporal interpolation algorithm is an interpolation algorithm for processing data containing both spatial dimensions and time dimensions, and the spatio-temporal interpolation algorithm calculates the data value at any unsampled location and any unsampled time point according to known discrete data collected at a specific location and a specific time. Using the spatio-temporal interpolation algorithm to determine each second measured kelp cultivation area can solve the problem of low time continuity of the first measured kelp cultivation area.

[0047] In the exemplary embodiments of the present application, as shown in Figure 4 the step of determining the second measured kelp cultivation area of at least one second time interval in the kelp harvesting period in step S300 includes: S310, sorting a plurality of remote sensing images in the order of corresponding first time intervals.

[0048] In some examples, remote sensing images of the kelp cultivation area in the 13 first time intervals of April 5, April 17, April 27, May 2, May 7, May 14, May 17, June 6, June 8, June 11, June 24, June 26 and July 21 are obtained. The 13 remote sensing images are sorted in the order of the first time intervals from front to back.

[0049] S320, determining the second measured kelp cultivation area of the second time interval located between the first time intervals corresponding to each adjacent two remote sensing images.

[0050] In some examples, the second measured kelp cultivation area of each second time interval in the 11 second time intervals between April 5 and April 17 is determined, the second measured kelp cultivation area of each second time interval in the 9 second time intervals between April 17 and April 27 is determined, the second measured kelp cultivation area of each second time interval in the 4 second time intervals between April 27 and May 2 is determined, and so on.

[0051] In the exemplary embodiments of the present application, as shown in Figure 5 the step of determining the second measured kelp cultivation area of the second time interval located between the first time intervals corresponding to each adjacent two remote sensing images in step S320 includes: S321, determining the binarization data corresponding to the remote sensing image sorted earlier in each adjacent two remote sensing images.

[0052] In the binarization data, the image unit corresponding to the ground object of kelp corresponds to the first value, and the image unit corresponding to the ground object not of kelp corresponds to the second value.

[0053] In some examples, the first value is 0, and the second value is 1. In other examples, the first value is 1, and the second value is 0.

[0054] S322, taking the image unit corresponding to the first value in the binarization data of the current time interval as a target image unit.

[0055] The current time interval is the first time interval or the second time interval.

[0056] In some examples, the first value is 0, and the image unit corresponding to 0 in the binarization data of the current time interval is taken as the target image unit. In other examples, the first value is 1, and the image unit corresponding to 1 in the binarization data of the current time interval is taken as the target image unit.

[0057] In some examples, when calculating the second measured kelp cultivation area of the second time interval between the first time interval corresponding to the adjacent two remote sensing images, the current time interval of the first round of calculation is the first time interval corresponding to the remote sensing image with a higher ranking in the adjacent two remote sensing images, and the binarization data of the current time interval is the binarization data corresponding to the remote sensing image with a higher ranking in the adjacent two remote sensing images. The current time interval of the second round of calculation is the second time interval adjacent to the first time interval corresponding to the remote sensing image with a higher ranking in the adjacent two remote sensing images, the current time interval of the third round of calculation is the next second time interval adjacent to the second time interval of the second round of calculation, and so on. For example, the adjacent two remote sensing images are the remote sensing images on April 27 and May 2. The current time interval of the first round of calculation is April 27, the current time interval of the second round of calculation is April 28, the current time interval of the third round of calculation is April 29, and the current time interval of the fourth round of calculation is April 30.

[0058] S323, calculating the number of target image units in each image unit adjacent to each target image unit.

[0059] In some examples, for each target image unit, eight image units of the target image unit, including the upper, lower, left, right, and diagonal four corners, are taken as the neighborhood structure matrix of the target image unit. The number of target image units in the eight image units of the neighborhood structure matrix is calculated.

[0060] S324, in the case where the number is less than the preset number, updating the binarization data, so that the target image unit corresponding to the target image unit with a number less than the preset number in each adjacent image unit corresponds to the second value.

[0061] In some examples, in a case where the number of target image units in each of the adjacent image units of the target image unit is greater than or equal to the preset number, the binarization data of the current time interval can be taken as the updated binarization data.

[0062] In the exemplary embodiments of the present application, the preset number is a variable, and the preset number is negatively correlated with the harvesting speed of the kelp cultivation area. The preset number may, for example, be 3, 4, 5, etc.

[0063] During the kelp harvesting period, the harvesting speed of the kelp cultivation area is not uniform, but is adjusted according to the maturation of kelp, the landing time and path of typhoon, etc. In some examples, the harvesting speed of the kelp cultivation area is determined through on-site investigation of the kelp cultivation area and questionnaire survey of kelp breeders, etc.

[0064] The preset number is negatively correlated with the harvesting speed of the kelp cultivation area. When the harvesting speed corresponding to the current time interval is fast, the preset number is small, and then the number of target image units reduced in the updated binarization data is more, which corresponds to the fast harvesting speed of kelp. When the harvesting speed corresponding to the current time interval is slow, the preset number is large, and then the number of target image units reduced in the updated binarization data is less, which corresponds to the slow harvesting speed of kelp. Setting the preset number negatively correlated with the harvesting speed of kelp can improve the degree of conformity of the updated binarization data to the actual situation of the next time interval.

[0065] S325, determining the second measured kelp cultivation area of the next time interval according to the updated binarization data, and taking the updated binarization data as the binarization data of the next time interval.

[0066] The next time interval is a second time interval located after the current time interval. Through step S325, the measured kelp cultivation area and the binarization data of the second time interval after the current time interval can be obtained.

[0067] In step S325, determining the second measured kelp cultivation area of the next time interval according to the updated binarization data can include: summing the area of the region corresponding to the image unit corresponding to the first value in the updated binarization data in the kelp cultivation area to obtain the second measured kelp cultivation area of the next time interval.

[0068] S326, determining whether the second measured kelp cultivation area of all the second time intervals between the first time interval corresponding to each pair of adjacent remote sensing images has been calculated. If not, return to step S322. If yes, end.

[0069] In a case where it is judged that the second measured kelp cultivation areas of all the second time intervals between the first time intervals corresponding to each of the adjacent two remote sensing images are not calculated, a next time interval is taken as a new current time interval, and the method returns to step S322 to start a new round of calculation using the binary data of the new current time interval until the second measured kelp cultivation areas of all the second time intervals between the first time intervals corresponding to each of the adjacent two remote sensing images are calculated.

[0070] In some examples, Figure 6 is a curve graph of the measured kelp cultivation area changing over time. Figure 6 In the embodiment, each of the first measured kelp cultivation areas of the 13 first time intervals including April 5, April 17, April 27, May 2, May 7, May 14, May 17, June 6, June 8, June 11, June 24, June 26 and July 21 also includes the second measured kelp cultivation areas of each of the second time intervals between April 5 and July 21.

[0071] Each of the time intervals in the kelp harvesting period has its corresponding first measured kelp cultivation area or second measured kelp cultivation area, and the kelp harvesting speed is simulated when the second measured kelp cultivation area is calculated, so that the measured kelp cultivation area has high accuracy and fully covers the kelp harvesting period, ensuring the accuracy, robustness and interpretability of the predicted kelp cultivation area obtained from the measured kelp cultivation area.

[0072] S400, determining the predicted kelp cultivation area of the first time interval and the second time interval according to each of the first measured kelp cultivation areas and at least one of the second measured kelp cultivation areas.

[0073] In the exemplary embodiments of the present application, as shown in Figure 7 In step S400, the predicted kelp cultivation area of the first time interval and the second time interval is determined according to each of the first measured kelp cultivation areas and at least one of the second measured kelp cultivation areas, including: S410, constructing a kelp cultivation area nonlinear fitting formula according to each of the first measured kelp cultivation areas and at least one of the second measured kelp cultivation areas.

[0074] In some examples, the Levenberg-Marquardt (LM) algorithm can be used to construct a kelp cultivation area nonlinear fitting formula according to each of the first measured kelp cultivation areas and each of the second measured kelp cultivation areas. The kelp cultivation area nonlinear fitting formula is as follows:

[0075] wherein, is the predicted kelp cultivation area; is an amplitude, for example, 29.5; is a growth rate, for example, 0.08; is a unit time quantity from the start time of the kelp harvesting period, for example, one natural day; is a curve center, for example, 63; is a minimum value, for example, 0.1.

[0076] S420, according to the nonlinear fitting formula of the kelp cultivation area, determine the predicted kelp cultivation area of the first time interval and the second time interval.

[0077] According to the nonlinear fitting formula of the kelp cultivation area, by changing the parameter , the predicted kelp cultivation area of each first time interval and each second time interval in the kelp harvesting period can be calculated, that is, the predicted kelp cultivation area of the kelp cultivation area in all time intervals in the kelp harvesting period.

[0078] In some examples, Figure 8 is a curve graph of the predicted kelp cultivation area changing with time. Figure 8 In the formula, the predicted kelp cultivation area of each first time interval and each second time interval between April 5 and July 21 is included.

[0079] The actual kelp cultivation area provides high-precision, comprehensive coverage of the kelp harvesting period, which can make the predicted kelp cultivation area obtained according to the constructed nonlinear fitting formula of the kelp cultivation area accurately reflect the trend of the kelp cultivation area of the kelp cultivation area changing with time in the kelp harvesting period, and can provide comprehensive and accurate technical support for the information management and scientific decision-making of the kelp cultivation industry.

[0080] In this embodiment, the high-precision, comprehensive coverage of the kelp harvesting period is based on the actual kelp cultivation area, which ensures the accuracy, robustness and interpretability of the obtained predicted kelp cultivation area, and the predicted kelp cultivation area reflects the time law of the change of the kelp cultivation area of the kelp cultivation area in the kelp harvesting period, which can provide comprehensive and accurate technical support for the information management and scientific decision-making of the kelp cultivation industry.

[0081] In the information management of the kelp cultivation industry, in addition to the time law of the change of the kelp cultivation area of the kelp cultivation area in the kelp harvesting period as technical support, the spatial law of the change of the kelp cultivation area of the kelp cultivation area in the kelp harvesting period is also needed as technical support. In the exemplary embodiments of the present application, the monitoring method of the kelp cultivation area further comprises: obtaining the kelp spatial distribution data of the kelp cultivation area in the first time interval and the second time interval according to each predicted kelp cultivation area.

[0082] In some examples, the random forest algorithm is used to gradually increase or remove the image units corresponding to the ground features of kelp in the kelp cultivation area, so as to realize the uniform expansion or contraction of the kelp cultivation area in space, and obtain the kelp spatial distribution data of the kelp cultivation area in each first time interval and each second time interval in the kelp harvesting period, that is, the kelp spatial distribution data of the kelp cultivation area in all time intervals in the kelp harvesting period. The kelp cultivation area in the kelp spatial distribution data of each time interval is the same as the predicted kelp cultivation area of the time interval. The random forest algorithm is a machine learning algorithm that can achieve high accuracy and robustness by building a large number of decision trees with differences and integrating the opinions of each decision tree. The process of using the random forest algorithm to realize the expansion of the kelp cultivation area in space is to simulate the natural growth of kelp by randomly adding new kelp growth points near the original patch formed by the image units corresponding to the ground features of kelp. The process of using the random forest algorithm to realize the contraction of the kelp cultivation area in space is to simulate the natural degradation or harvesting of kelp by randomly removing a certain number of image units in the original patch formed by the image units corresponding to the ground features of kelp.

[0083] In this embodiment, the kelp spatial distribution data of each time interval of the kelp cultivation area in the kelp harvesting period can accurately reflect the trend of the kelp cultivation area of the kelp cultivation area in the kelp harvesting period, and can provide comprehensive and accurate technical support for the informatization management and scientific decision-making of the kelp cultivation industry.

[0084] The exemplary embodiments of the present application provide a method for monitoring the area of kelp cultivation. As shown in the figure, Figure 9 The method for monitoring the area of kelp cultivation according to the exemplary embodiments of the present application comprises: S1, obtaining a plurality of remote sensing images corresponding to a plurality of first time intervals in the kelp harvesting period of the kelp cultivation area.

[0085] S2, dividing each remote sensing image into a plurality of image units.

[0086] S3, determining the ground feature corresponding to each image unit.

[0087] S4, in each remote sensing image, summing the area of the region corresponding to the image unit corresponding to the ground feature of kelp in the kelp cultivation area to obtain each first measured kelp cultivation area.

[0088] S5, sorting the plurality of remote sensing images in order according to the corresponding first time interval.

[0089] S6, determining the binarization data corresponding to the remote sensing image in front of each adjacent two remote sensing images.

[0090] S7. Take the image unit corresponding to the first value in the binarized data of the current time interval as the target image unit.

[0091] S8. Calculate the number of target image units in each image unit adjacent to each target image unit.

[0092] S9. If the number is less than the preset number, update the binarized data so that the number of target image units in each adjacent image unit is less than the preset number of target image units corresponding to the second value.

[0093] S10. Determine the second measured kelp farming area for the next time interval based on the updated binarized data, and use the updated binarized data as the binarized data for the next time interval.

[0094] S11. Determine whether the second measured kelp aquaculture area for all second time intervals between the first time intervals corresponding to each pair of adjacent remote sensing images has been calculated. If not, return to step S7. If yes, proceed to step S12.

[0095] S12. Based on each first measured kelp farming area and at least one second measured kelp farming area, construct a nonlinear fitting formula for kelp farming area.

[0096] S13. Based on the nonlinear fitting formula for kelp farming area, determine the predicted kelp farming area for the first and second time intervals.

[0097] S14. Based on the predicted kelp farming area, obtain the spatial distribution data of kelp in the kelp farming area for the first and second time intervals.

[0098] In this embodiment, the measured kelp farming area provides high-precision, comprehensive basic data covering the kelp harvesting period for constructing a nonlinear fitting formula for kelp farming area. This allows the predicted kelp farming area derived from the constructed nonlinear fitting formula to accurately reflect the trend of kelp farming area changes over time during the kelp harvesting period. The resulting spatial distribution data of kelp in various time intervals during the kelp harvesting period can accurately reflect the trend of kelp farming area changes spatially during the kelp harvesting period. The predicted kelp farming area and spatial distribution data can provide comprehensive and accurate technical support for the information management and scientific decision-making of the kelp farming industry.

[0099] An exemplary embodiment of the present invention provides a monitoring device for kelp cultivation area. For example... Figure 10 As shown, the kelp farming area monitoring device provided in this exemplary embodiment includes an acquisition module 10, a first determination module 20, a second determination module 30, and a third determination module 40.

[0100] The acquisition module 10 is configured to acquire a plurality of remote sensing images corresponding to a plurality of first time intervals in a kelp cultivation area during a kelp harvesting period.

[0101] The first determination module 20 is configured to determine a first measured kelp cultivation area of each first time interval according to each remote sensing image.

[0102] The second determination module 30 is configured to determine a second measured kelp cultivation area of at least one second time interval in the kelp harvesting period.

[0103] The third determination module 40 is configured to determine a predicted kelp cultivation area of the first time interval and the second time interval according to the first measured kelp cultivation area and the second measured kelp cultivation area.

[0104] In an exemplary embodiment of the present application, the first determination module 20 is further configured to: divide each remote sensing image into a plurality of image units; determine a ground object corresponding to each image unit; sum up the area of the image units corresponding to the kelp in the kelp cultivation area in each remote sensing image to obtain the first measured kelp cultivation area of each first time interval.

[0105] In an exemplary embodiment of the present application, the second determination module 30 is further configured to: sort the plurality of remote sensing images according to the order of the corresponding first time intervals; determine the second measured kelp cultivation area of the second time interval between the first time intervals corresponding to each adjacent two remote sensing images.

[0106] In an exemplary embodiment of the present application, the second determination module 30 is further configured to: determine the binarization data corresponding to the remote sensing image sorted earlier in each adjacent two remote sensing images, wherein in the binarization data, the image units corresponding to the kelp correspond to a first numerical value, and the image units not corresponding to the kelp correspond to a second numerical value; repeat the following steps until the second measured kelp cultivation areas of all second time intervals between the first time intervals corresponding to each adjacent two remote sensing images are calculated: take the image units corresponding to the first numerical value in the binarization data of the current time interval as target image units, wherein the current time interval is the first time interval or the second time interval; count the number of target image units in each image unit adjacent to each target image unit; In the case that the number is less than the preset number, the binarization data is updated so that the number of target image units in each adjacent image unit is less than the target image unit corresponding to the second value; According to the updated binarization data, the second measured kelp cultivation area of the next time interval is determined, and the updated binarization data is taken as the binarization data of the next time interval, and the next time interval is the second time interval located after the current time interval.

[0107] In the exemplary embodiment of the present application, the preset number is a variable, and the preset number is negatively correlated with the kelp harvesting speed of the kelp cultivation area.

[0108] In the exemplary embodiment of the present application, the third determination module 40 is further configured to: According to each first measured kelp cultivation area and at least one second measured kelp cultivation area, a kelp cultivation area nonlinear fitting formula is constructed; According to the kelp cultivation area nonlinear fitting formula, the predicted kelp cultivation area of the first time interval and the second time interval is determined.

[0109] In the exemplary embodiment of the present application, the kelp cultivation area monitoring device further comprises a fourth determination module. The fourth determination module is configured to obtain the kelp spatial distribution data of the kelp cultivation area in the first time interval and the second time interval according to each predicted kelp cultivation area.

[0110] Each module in the kelp cultivation area monitoring device described above can be realized by software, hardware and a combination thereof in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0111] The exemplary embodiment of the present application provides a computer device comprising a processor and a memory, and the memory stores a computer program. When the processor executes the computer program, the steps of any of the kelp cultivation area monitoring methods described above are realized.

[0112] The exemplary embodiment of the present application provides a non-transitory computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any of the kelp cultivation area monitoring methods described above are realized. The non-transitory computer readable storage medium can be a ROM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0113] The exemplary embodiment of the present application provides a computer program product comprising a computer program. When the computer program is executed by a processor, the steps of any of the kelp cultivation area monitoring methods described above are realized.

[0114] Reference Figure 11 A block diagram of a structure of a computer device that can be the computer device 1100 of the present application will now be described. The computer device 1100 includes a computing unit 1101 that can perform various appropriate actions and processes according to a computer program stored in a read only memory (ROM) 1102 or a computer program loaded into a random access memory (RAM) 1103 from a storage unit 1108. Various programs and data required for the operation of the computer device 1100 can also be stored in the RAM 1103. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other through a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0115] Various components in the computer device 1100 are connected to the I / O interface 1105, including an input unit 1106, an output unit 1107, the storage unit 1108, and a communication unit 1109. The input unit 1106 can be any type of device that can input information to the computer device 1100, and can receive inputted numerical or character information, and generate key signal inputs related to user settings and / or function controls of the computer device 1100, and can include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 1107 can be any type of device that can present information, and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1108 can include, but is not limited to, a magnetic disk, an optical disk. The communication unit 1109 allows the computer device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0116] The computing unit 1101 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1101 performs various methods and processes described above, such as the monitoring method of kelp cultivation area. For example, in some embodiments, the monitoring method of kelp cultivation area can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed onto the computer device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded onto the RAM 1103 and executed by the computing unit 1101, one or more steps of the monitoring method of kelp cultivation area described above can be performed. Alternatively, in other embodiments, the computing unit 1101 can be configured to perform the monitoring method of kelp cultivation area by any other appropriate means, such as by means of firmware.

[0117] The computer device 1100 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for performing the monitoring method of kelp cultivation area described above.

[0118] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the present application cover any and all variations of the application that come within the scope of the present application. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0119] It is to be understood that the application is not limited to the precise construction described and shown above and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is limited only by the claims that follow.

Claims

1. A method for monitoring the area of ​​kelp cultivation, characterized in that, The monitoring methods for the kelp farming area include: Acquire multiple remote sensing images of the kelp farming area corresponding to multiple first time intervals during the kelp harvesting period; Based on each of the remote sensing images, determine the first measured kelp farming area for each of the first time intervals; Determine the second measured kelp cultivation area for at least one second time interval within the kelp harvesting period; Based on each of the first measured kelp farming areas and at least one second measured kelp farming area, the predicted kelp farming areas for the first time interval and the second time interval are determined.

2. The method for monitoring kelp farming area according to claim 1, characterized in that, The step of determining the first measured kelp cultivation area for each of the first time intervals based on each of the remote sensing images includes: Each of the aforementioned remote sensing images is divided into multiple image units; Determine the ground features corresponding to each image unit; In each of the remote sensing images, the area of ​​the corresponding region in the kelp farming area corresponding to the image unit with the land feature being kelp is summed to obtain the first measured kelp farming area.

3. The method for monitoring kelp farming area according to claim 2, characterized in that, The determination of the second measured kelp cultivation area within at least one second time interval during the kelp harvesting period includes: The multiple remote sensing images are sorted according to the order of their corresponding first time intervals; The second measured kelp farming area is determined in the second time interval between each two adjacent remote sensing images corresponding to the first time interval.

4. The method for monitoring kelp farming area according to claim 3, characterized in that, Determining the second measured kelp aquaculture area within the second time interval located between each pair of adjacent remote sensing images corresponding to the first time interval includes: Determine the binarized data corresponding to the first-ranked remote sensing image in each pair of adjacent remote sensing images, wherein in the binarized data, the image unit corresponding to the land feature is kelp corresponds to a first value, and the image unit corresponding to the land feature is not kelp corresponds to a second value. Repeat the following steps until the second measured kelp cultivation area for all second time intervals between each pair of adjacent remote sensing images corresponding to the first time interval is calculated: The image unit corresponding to the first value in the binarized data of the current time interval is taken as the target image unit, and the current time interval is either the first time interval or the second time interval; Calculate the number of target image units in each of the image units adjacent to each target image unit; If the number is less than a preset number, update the binarized data so that the target image units in each adjacent image unit whose number is less than the preset number correspond to the second value; The second measured kelp farming area for the next time interval is determined based on the updated binarized data, and the updated binarized data is used as the binarized data for the next time interval, wherein the next time interval is the second time interval located after the current time interval.

5. The method for monitoring kelp farming area according to claim 4, characterized in that, The preset quantity is a variable, and it is negatively correlated with the kelp harvesting speed in the kelp farming area.

6. The method for monitoring kelp farming area according to claim 1, characterized in that, The step of determining the predicted kelp cultivation area for the first time interval and the second time interval based on each of the first measured kelp cultivation areas and at least one second measured kelp cultivation area includes: Based on each of the first measured kelp farming areas and at least one second measured kelp farming area, a nonlinear fitting formula for kelp farming area is constructed. The predicted kelp farming area is determined based on the nonlinear fitting formula for the kelp farming area in the first time interval and the second time interval.

7. The method for monitoring the kelp farming area according to any one of claims 1 to 6, characterized in that, The monitoring method for the kelp farming area also includes: Based on the predicted kelp farming area, spatial distribution data of kelp in the kelp farming area for the first time interval and the second time interval are obtained.

8. A monitoring device for kelp farming area, characterized in that, The monitoring device for the kelp farming area includes: The acquisition module is configured to acquire multiple remote sensing images of the kelp farming area corresponding to multiple first time intervals during the kelp harvesting period; The first determining module is configured to determine the first measured kelp farming area for each of the first time intervals based on each of the remote sensing images. The second determining module is configured to determine the second measured kelp farming area for at least one second time interval during the kelp harvesting period; The third determining module is configured to determine the predicted kelp farming area for the first time interval and the second time interval based on each of the first measured kelp farming areas and at least one second measured kelp farming area.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for monitoring the kelp farming area as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for monitoring the kelp farming area as described in any one of claims 1 to 7.

Images