Time sequence model-based remote sensing image steel storage yard identification statistical method and system
Through the remote sensing image recognition and statistics system based on the timing model, using satellite remote sensing images and clustering algorithms, the problem of difficult to efficiently monitor steel yards in traditional ground investigations is solved, and accurate identification and statistics of steel yards are achieved, and steel management and anti-theft are improved. scientific nature.
Patent Information
- Application Number
- CN202411204882.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-24
AI Technical Summary
Traditional ground investigations are difficult to efficiently and accurately monitor the distribution and quantity changes of different types of steel in steel yards, increase or decrease in incoming and shipment, and it is difficult to prevent theft.
Using a remote sensing image recognition and statistical system based on the timing model, a steel yard recognition statistical model is established through satellite remote sensing image acquisition, data processing and feature extraction, and a K-Means clustering algorithm and least squares method are used to identify and count the steel stack. Efficient identification and statistics of fields.
It realizes efficient and accurate identification and statistics of steel yards, solves the problem of inefficient identification and statistics in traditional methods, and improves the scientific nature of steel management and theft prevention.
Smart Images
Figure CN119181028A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a remote sensing image steel yard identification and statistics system, method, electronic equipment and storage medium based on a time series model. Background Art
[0002] Accurately obtaining the characteristics and quantity of different steel materials stored in large steel yards at different times will help relevant departments to carry out steel inspections, which is of great significance for the scientific management of steel inflow and outflow and theft prevention. Traditional ground surveys are difficult to efficiently monitor the distribution of different types of steel materials in steel yards at different times, the increase and decrease of inflow and outflow, and theft prevention issues on a large scale.
[0003] Therefore, there is an urgent need for a method that can efficiently and accurately identify and count steel yards. Summary of the invention
[0004] The purpose of the embodiments of the present invention is to provide a remote sensing image steel yard identification and statistics system, method, electronic device and storage medium based on a time series model, so as to solve the problem that the existing technology cannot efficiently and accurately perform steel yard identification and statistics.
[0005] To achieve the above object, an embodiment of the present invention provides a statistical method for steel yard identification based on remote sensing images based on a time series model, and the method specifically includes:
[0006] Collect satellite remote sensing images of steel yards in a certain time sequence;
[0007] Performing data processing on the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing image of the steel stockyard;
[0008] Establishing a steel yard identification statistical model, inputting the time series steel yard satellite remote sensing image into the steel yard identification statistical model for training, and obtaining an optimal steel yard identification statistical model;
[0009] The satellite remote sensing image of the steel material yard to be identified and counted is input into the optimal steel material yard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel material yard to be identified and counted.
[0010] On the basis of the above technical solution, the present invention can also be improved as follows:
[0011] Furthermore, the data processing of the steel yard satellite remote sensing image to obtain a plurality of time series steel yard satellite remote sensing images corresponding to the steel yard satellite remote sensing images includes:
[0012] Feature extraction is performed on the satellite remote sensing image of the steel material yard to obtain feature points corresponding to the satellite remote sensing image of the steel material yard.
[0013] Furthermore, the extracting features of the satellite remote sensing image of the steel stockyard to obtain feature points corresponding to the satellite remote sensing image of the steel stockyard includes:
[0014] Acquire the target area based on texture features;
[0015] Convolving the scale parameters and the direction parameters of the satellite remote sensing image of the steel stockyard in the target area, and extracting the local maximum points and the local minimum points of the image as the invariant feature points of the satellite remote sensing image of the steel stockyard;
[0016] Eliminating spatial errors of invariant feature points by means of translation vectors, and performing fitting matching on the invariant feature points;
[0017] Based on the invariant feature points, the remote sensing feature points are screened one by one to obtain a set of steel yard feature points.
[0018] Furthermore, the data processing of the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing images of the steel stockyard also includes:
[0019] The characteristic points of the steel yard corresponding to time T are obtained, and a time series satellite remote sensing image of the steel yard at time T is constructed based on the characteristic points of the steel yard corresponding to time T.
[0020] Furthermore, the step of inputting the satellite remote sensing image of the steel stockyard to be identified and counted into the optimal steel stockyard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel stockyard to be identified and counted includes:
[0021] Using the K-Means clustering algorithm, the characteristics of different types of steel at different time stages are divided into different types of steel sub-feature libraries and scale quantity sub-feature libraries.
[0022] Furthermore, the step of inputting the satellite remote sensing image of the steel stockyard to be identified and counted into the optimal steel stockyard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel stockyard to be identified and counted further includes:
[0023] The Euclidean distance from each object to each cluster center is calculated by formula (1);
[0024]
[0025] Where, X i represents the i-th object, C j is the jth cluster center, Xit is the tth attribute of the ith object, 1≤t≤m, C jt is the tth attribute of the jth cluster center.
[0026] Furthermore, the step of inputting the satellite remote sensing image of the steel stockyard to be identified and counted into the optimal steel stockyard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel stockyard to be identified and counted further includes:
[0027] Compare the Euclidean distance from each object to each cluster center in turn, and assign the object to the cluster with the closest Euclidean distance to obtain k clusters {S1, S2, S3, ..., S k}.
[0028] A remote sensing image steel yard identification and statistics system based on a time series model, comprising:
[0029] The acquisition module is used to collect satellite remote sensing images of steel yards in a certain time sequence;
[0030] A preprocessing module is used to perform data processing on the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing images of the steel stockyard;
[0031] A construction module is used to establish a steel yard identification statistical model, input the time series steel yard satellite remote sensing image into the steel yard identification statistical model for training, and obtain an optimal steel yard identification statistical model;
[0032] The identification and statistics module is used to input the satellite remote sensing image of the steel yard to be identified and counted into the optimal steel yard identification and statistics model to obtain the identification and statistics results corresponding to the satellite remote sensing image of the steel yard to be identified and counted.
[0033] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method are implemented when the processor executes the computer program.
[0034] A non-transitory computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.
[0035] The embodiments of the present invention have the following advantages:
[0036] The remote sensing image steel yard identification and statistics method based on the time series model in the present invention solves the problem that the steel yard identification and statistics cannot be performed efficiently and accurately in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.
[0038] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.
[0039] Figure 1 It is a flow chart of the statistical method for steel stockyard identification based on remote sensing images based on a time series model of the present invention;
[0040] Figure 2 This is a structural diagram of the remote sensing image steel yard identification and statistics system based on the time series model of the present invention;
[0041] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention.
[0042] The accompanying drawings are denoted as follows:
[0043] Acquisition module 10 , preprocessing module 20 , construction module 30 , identification and statistics module 40 , electronic device 50 , processor 501 , memory 502 , and bus 503 . DETAILED DESCRIPTION
[0044] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0045] Figure 1 FIG. 1 is a flow chart of an embodiment of a statistical method for identifying steel stockyards using remote sensing images based on a time series model of the present invention. Figure 1 As shown, a statistical method for identifying steel yards in remote sensing images based on a time series model provided by an embodiment of the present invention includes the following steps:
[0046] S101, collecting satellite remote sensing images of steel yards in a certain time sequence;
[0047] Specifically: A satellite remote sensing image time series dataset of steel yards is established based on the satellite remote sensing images of steel yards. The satellite remote sensing image time series dataset of steel yards includes various types of steel and their changes in different time ranges.
[0048] S102, performing data processing on the satellite remote sensing image of the steel stockyard to obtain a time series of satellite remote sensing images of the steel stockyard corresponding to a plurality of satellite remote sensing images of the steel stockyard;
[0049] Specifically, feature extraction is performed on the satellite remote sensing image of the steel material yard to obtain feature points corresponding to the satellite remote sensing image of the steel material yard.
[0050] The target area is obtained based on texture features, different texture features and structural characteristics are distinguished through the gray-level co-occurrence matrix, and the target area is extracted according to the uniformity of grayscale;
[0051] Extracting feature points by a scale-space method, convolving the scale parameter and the direction parameter of the satellite remote sensing image of the steel yard in the target area, and extracting the local maximum point and the local minimum point of the image as the invariant feature points of the satellite remote sensing image of the steel yard;
[0052] Eliminating spatial errors of invariant feature points by translation vectors, matching the model and the image by hausdorff distance, eliminating spatial errors by translation transformation of the invariant feature points, and fitting and matching the invariant feature points;
[0053] Based on the invariant feature points, the remote sensing feature points are screened one by one, the fitted and matched invariant feature points are sorted in sequence to form an invariant feature point library, and the remote sensing feature points are screened in sequence by comparing the feature points to obtain a steel yard feature point set.
[0054] The characteristic points of the steel yard corresponding to time T are obtained, and a time series satellite remote sensing image of the steel yard at time T is constructed based on the characteristic points of the steel yard corresponding to time T.
[0055] Several steel yard satellite remote sensing images (T, T+l,…,T+T1,T+T2) (T2>T1) constitute a time series steel yard satellite remote sensing image.
[0056] S103, establishing a steel stockyard identification statistical model, inputting the time series satellite remote sensing images of the steel stockyard into the steel stockyard identification statistical model for training, and obtaining an optimal steel stockyard identification statistical model;
[0057] Specifically, the time series satellite remote sensing images of steel stockyards are divided into a training set, a validation set and a test set;
[0058] Training the steel yard identification statistical model based on the training set;
[0059] Performing a performance evaluation on the trained steel stockyard identification statistical model based on the validation set to obtain a steel stockyard identification statistical model that meets performance requirements;
[0060] The prediction results of the steel material yard identification statistical model that meet the performance conditions are evaluated based on the test set to obtain an evaluation index corresponding to the steel material yard identification statistical model.
[0061] Based on the validation set, the performance of the trained steel yard identification statistical model is evaluated to obtain a steel yard identification statistical model that meets the performance conditions; based on the test set, the similarity calculation result of the steel yard identification statistical model that meets the performance conditions is evaluated to obtain an evaluation index corresponding to the steel yard identification statistical model. The performance of the steel yard identification statistical model is evaluated to obtain a percentage score (i.e., the highest score is 100 points and the lowest score is 0 points), and based on the percentage score, a steel yard identification statistical model with a score greater than a set value is determined, for example, a steel yard identification statistical model with a score greater than 90 points is a steel yard identification statistical model that meets the performance conditions;
[0062] An evaluation index is calculated for a steel yard identification statistical model that meets performance conditions to obtain the evaluation index of the steel yard identification statistical model, and an evaluation value corresponding to each evaluation index is calculated to obtain the evaluation value, which is used to represent the capability value of the steel yard identification statistical model based on the evaluation index.
[0063] S104, inputting the satellite remote sensing image of the steel stockyard to be identified and counted into the optimal steel stockyard identification statistical model to obtain the identification statistical results corresponding to the satellite remote sensing image of the steel stockyard to be identified and counted;
[0064] Specifically, the K-Means clustering algorithm is used to divide the characteristics of different types of steel at different time stages into different types of steel sub-feature libraries and scale quantity sub-feature libraries. The Kmeans algorithm is the most commonly used clustering algorithm. The main idea is: given the K value and K initial cluster center points, each point (that is, data record) is assigned to the cluster represented by the cluster center point closest to it. After all points are assigned, the center point of a cluster is recalculated based on all points in a cluster (taking the average value), and then the steps of assigning points and updating cluster center points are iteratively performed until the change of the cluster center point is small, or the specified number of iterations is reached.
[0065] Assume that a given data sample X contains n objects X = {X1, X2, X3, ..., X n}, where each object has attributes of m dimensions. The goal of the Kmeans algorithm is to cluster n objects into specified k clusters based on the similarity between the objects. Each object belongs to and only belongs to one cluster with the smallest distance to the cluster center. For Kmeans, first, it is necessary to initialize k cluster centers {C1, C2, C3, ..., C k}, 1<k≤n,;
[0066] The Euclidean distance from each object to each cluster center is calculated by formula (1);
[0067]
[0068] Where, X i represents the i-th object, C j is the jth cluster center, X it is the tth attribute of the ith object, 1≤t≤m, C jt is the tth attribute of the jth cluster center.
[0069] Compare the Euclidean distance from each object to each cluster center in turn, and assign the object to the cluster with the closest Euclidean distance to obtain k clusters {S1, S2, S3, ..., S k}.
[0070] Based on the recognition statistical results, a least squares statistical analysis model is established to solve the problem of feature point selection and statistical threshold in the identification of multiple types of steel in the steel yard. The least squares method is a commonly used algorithm for fitting regression lines. It is calculated by minimizing the sum of squares of the vertical errors between each data point and the predicted straight line, that is, by minimizing the sum of squares of the errors, the fitting object is infinitely close to the target object. This is the core idea of the least squares method. The optimized objective function is as follows:
[0071]
[0072] Use various optimization methods to solve the w vector and obtain the relevant parameters in the linear model, and then use the point-by-point prediction method to obtain the corresponding prediction results.
[0073] The remote sensing image steel yard identification and statistical method based on the time series model collects satellite remote sensing images of steel yards in a certain time sequence; performs data processing on the satellite remote sensing images of steel yards to obtain a number of time series satellite remote sensing images of steel yards corresponding to the satellite remote sensing images of steel yards; establishes a steel yard identification and statistical model, inputs the time series satellite remote sensing images of steel yards into the steel yard identification and statistical model for training, and obtains the optimal steel yard identification and statistical model; inputs the steel yard satellite remote sensing images to be identified and statistically analyzed into the optimal steel yard identification and statistically analyzed model, and obtains the identification and statistical results corresponding to the steel yard satellite remote sensing images to be identified and statistically analyzed. The problem that the existing technology cannot efficiently and accurately perform steel yard identification and statistical analysis is solved.
[0074] Figure 2 FIG. 1 is a flow chart of an embodiment of a remote sensing image steel yard identification and statistics system based on a time series model of the present invention; Figure 2 As shown, a remote sensing image steel yard identification and statistics system based on a time series model provided by an embodiment of the present invention includes the following steps:
[0075] The acquisition module 10 is used to acquire satellite remote sensing images of the steel yard in a certain time sequence;
[0076] A preprocessing module 20 is used to perform data processing on the steel yard satellite remote sensing image to obtain a plurality of time series steel yard satellite remote sensing images corresponding to the steel yard satellite remote sensing images;
[0077] The pre-processing module 20 is also used for:
[0078] Feature extraction is performed on the satellite remote sensing image of the steel material yard to obtain feature points corresponding to the satellite remote sensing image of the steel material yard.
[0079] Acquire the target area based on texture features;
[0080] Convolving the scale parameters and the direction parameters of the satellite remote sensing image of the steel stockyard in the target area, and extracting the local maximum points and the local minimum points of the image as the invariant feature points of the satellite remote sensing image of the steel stockyard;
[0081] Eliminating spatial errors of invariant feature points by means of translation vectors, and performing fitting matching on the invariant feature points;
[0082] Based on the invariant feature points, the remote sensing feature points are screened one by one to obtain a set of steel yard feature points.
[0083] The characteristic points of the steel yard corresponding to time T are obtained, and a time series satellite remote sensing image of the steel yard at time T is constructed based on the characteristic points of the steel yard corresponding to time T.
[0084] A construction module 30 is used to establish a steel stockyard identification statistical model, input the time series steel stockyard satellite remote sensing image into the steel stockyard identification statistical model for training, and obtain an optimal steel stockyard identification statistical model;
[0085] The identification and statistics module 40 is used to input the satellite remote sensing image of the steel yard to be identified and counted into the optimal steel yard identification and statistics model to obtain the identification and statistics results corresponding to the satellite remote sensing image of the steel yard to be identified and counted.
[0086] The identification statistics module 40 is also used for:
[0087] Using the K-Means clustering algorithm, the characteristics of different types of steel at different time stages are divided into different types of steel sub-feature libraries and scale quantity sub-feature libraries.
[0088] The Euclidean distance from each object to each cluster center is calculated by formula (1);
[0089]
[0090] Where, X i represents the i-th object, C j is the jth cluster center, X it is the tth attribute of the ith object, 1≤t≤m, C jt is the tth attribute of the jth cluster center.
[0091] Compare the Euclidean distance from each object to each cluster center in turn, and assign the object to the cluster with the closest Euclidean distance to obtain k clusters {S1, S2, S3, ..., S k}.
[0092] The invention discloses a remote sensing image steel yard identification and statistics system based on a time series model. The acquisition module 10 collects steel yard satellite remote sensing images in a certain time sequence; the preprocessing module 20 processes the steel yard satellite remote sensing images to obtain a number of time series steel yard satellite remote sensing images corresponding to the steel yard satellite remote sensing images; the construction module 30 establishes a steel yard identification and statistics model, and the time series steel yard satellite remote sensing images are input into the steel yard identification and statistics model for training to obtain an optimal steel yard identification and statistics model; the steel yard satellite remote sensing images to be identified and counted are input into the optimal steel yard identification and statistics model through the identification and statistics module 40 to obtain the identification and statistics results corresponding to the steel yard satellite remote sensing images to be identified and counted. The remote sensing image steel yard identification and statistics method based on a time series model solves the problem that the existing technology cannot efficiently and accurately perform steel yard identification and statistics.
[0093] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503;
[0094] The processor 501 and the memory 502 communicate with each other via the bus 503;
[0095] The processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above-mentioned method embodiments, for example, including: collecting satellite remote sensing images of steel yards in a certain time sequence; performing data processing on the satellite remote sensing images of the steel yards to obtain a number of time series satellite remote sensing images of steel yards corresponding to the satellite remote sensing images of the steel yards; establishing a steel yard recognition statistical model, inputting the time series satellite remote sensing images of the steel yards into the steel yard recognition statistical model for training, and obtaining an optimal steel yard recognition statistical model; inputting the satellite remote sensing images of the steel yards to be recognized and counted into the optimal steel yard recognition statistical model, and obtaining recognition statistical results corresponding to the satellite remote sensing images of the steel yards to be recognized and counted.
[0096] The present embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments, for example, including: collecting satellite remote sensing images of steel yards in a certain time sequence; performing data processing on the satellite remote sensing images of the steel yards to obtain a number of time series satellite remote sensing images of steel yards corresponding to the satellite remote sensing images of the steel yards; establishing a steel yard recognition statistical model, inputting the time series satellite remote sensing images of the steel yards into the steel yard recognition statistical model for training, and obtaining an optimal steel yard recognition statistical model; inputting the steel yard satellite remote sensing images to be recognized and counted into the optimal steel yard recognition statistical model, and obtaining recognition statistical results corresponding to the steel yard satellite remote sensing images to be recognized and counted.
[0097] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.
[0098] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.
[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.
[0100] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.
Claims
1. A statistical method for steel yard identification in remote sensing images based on a time series model, characterized in that: The statistical method for steel yard identification based on remote sensing images of a time series model specifically includes: Collect satellite remote sensing images of steel yards in a certain time sequence; Performing data processing on the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing image of the steel stockyard; Establishing a steel yard identification statistical model, inputting the time series steel yard satellite remote sensing image into the steel yard identification statistical model for training, and obtaining an optimal steel yard identification statistical model; The satellite remote sensing image of the steel material yard to be identified and counted is input into the optimal steel material yard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel material yard to be identified and counted.
2. The statistical method for steel stockyard identification based on remote sensing images of claim 1 is characterized in that: The data processing of the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing image of the steel stockyard includes: Feature extraction is performed on the satellite remote sensing image of the steel material yard to obtain feature points corresponding to the satellite remote sensing image of the steel material yard.
3. According to claim 2, the statistical method for identifying steel stockyards using remote sensing images based on a time series model is characterized in that: The step of extracting features from the satellite remote sensing image of the steel material yard to obtain feature points corresponding to the satellite remote sensing image of the steel material yard includes: Acquire the target area based on texture features; Convolving the scale parameters and the direction parameters of the satellite remote sensing image of the steel stockyard in the target area, and extracting the local maximum points and the local minimum points of the image as the invariant feature points of the satellite remote sensing image of the steel stockyard; Eliminating spatial errors of invariant feature points by means of translation vectors, and performing fitting matching on the invariant feature points; Based on the invariant feature points, the remote sensing feature points are screened one by one to obtain a set of steel yard feature points.
4. According to claim 3, the statistical method for steel stockyard identification based on remote sensing images based on time series model is characterized in that: The data processing of the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing images of the steel stockyard also includes: The characteristic points of the steel yard corresponding to time T are obtained, and a time series satellite remote sensing image of the steel yard at time T is constructed based on the characteristic points of the steel yard corresponding to time T.
5. According to claim 1, the statistical method for steel stockyard identification based on remote sensing images based on time series model is characterized in that: The step of inputting the satellite remote sensing image of the steel material yard to be identified and counted into the optimal steel material yard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel material yard to be identified and counted includes: Using the K-Means clustering algorithm, the characteristics of different types of steel at different time stages are divided into different types of steel sub-feature libraries and scale quantity sub-feature libraries.
6. The statistical method for steel stockyard identification based on remote sensing images of claim 5 is characterized by: The step of inputting the satellite remote sensing image of the steel material yard to be identified and counted into the optimal steel material yard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel material yard to be identified and counted also includes: The Euclidean distance from each object to each cluster center is calculated by formula (1); Where, X i represents the i-th object, C j is the jth cluster center, X it is the tth attribute of the ith object, 1≤t≤m, C jt is the tth attribute of the jth cluster center.
7. The statistical method for steel stockyard identification based on remote sensing images of claim 6 is characterized by: The step of inputting the satellite remote sensing image of the steel material yard to be identified and counted into the optimal steel material yard identification and statistical model to obtain the identification and statistical results corresponding to the satellite remote sensing image of the steel material yard to be identified and counted also includes: Compare the Euclidean distance from each object to each cluster center in turn, and assign the object to the cluster with the closest Euclidean distance to obtain k clusters {S1, S2, S3, ..., S k }.
8. A remote sensing image steel yard identification and statistics system based on a time series model, characterized in that: include: The acquisition module is used to collect satellite remote sensing images of steel yards in a certain time sequence; A preprocessing module is used to perform data processing on the satellite remote sensing image of the steel stockyard to obtain a plurality of time series satellite remote sensing images of the steel stockyard corresponding to the satellite remote sensing images of the steel stockyard; A construction module is used to establish a steel yard identification statistical model, input the time series steel yard satellite remote sensing image into the steel yard identification statistical model for training, and obtain an optimal steel yard identification statistical model; The identification and statistics module is used to input the satellite remote sensing image of the steel yard to be identified and counted into the optimal steel yard identification and statistics model to obtain the identification and statistics results corresponding to the satellite remote sensing image of the steel yard to be identified and counted.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A non-transitory computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.