CN112580595B - Double-cropping rice Tian Yaogan identification method based on Shaapelet - Google Patents
Double-cropping rice Tian Yaogan identification method based on Shaapelet Download PDFInfo
- Publication number
- CN112580595B CN112580595B CN202011598570.7A CN202011598570A CN112580595B CN 112580595 B CN112580595 B CN 112580595B CN 202011598570 A CN202011598570 A CN 202011598570A CN 112580595 B CN112580595 B CN 112580595B
- Authority
- CN
- China
- Prior art keywords
- double
- time sequence
- cropping rice
- shapelet
- yaogan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 59
- 235000009566 rice Nutrition 0.000 title claims abstract description 59
- 238000009355 double cropping Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 28
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 58
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 12
- 238000011160 research Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012952 Resampling Methods 0.000 claims description 2
- 230000005855 radiation Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract 1
- 230000007704 transition Effects 0.000 abstract 1
- 235000013339 cereals Nutrition 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Pretreatment Of Seeds And Plants (AREA)
Abstract
A method for identifying double cropping rice Tian Yaogan based on a Shapelet, the method comprising the steps of: 1, preparing and preprocessing data to form a paddy vegetation index time sequence data set in a research area; 2, determining key points of the time sequence according to the growth period of the double-cropping rice, and acquiring a plurality of subsequences of the vegetation index time sequence by taking the key points as endpoints to form a shape candidate set; 3, carrying out importance evaluation on the candidate shapelets, and selecting K optimal shapelets; 4 Shapelet transitions. Calculating the distances between all the time sequences and K shapelets, and converting each time sequence into a vector consisting of K distances; 5, constructing a convolutional neural network classifier, and training the convolutional neural network by using a training sample; and 6, introducing the converted time sequence into a classifier for learning, identifying the paddy field type, and generating a double-cropping paddy field distribution map. The remote sensing identification of the double-cropping rice field is carried out by adopting the method based on the Shaapelet, so that the identification precision of the double-cropping rice field can be effectively improved, and an effective means is provided for the rapid monitoring of the planting area of the double-cropping rice.
Description
Technical Field
The invention relates to the field of double-cropping rice planting, in particular to a double-cropping rice Tian Yaogan identification method based on a Shaapelet.
Background
Rice is one of the most important grain crops in China, the research of a rice planting system is developed, the rice planting change is accurately identified, and the method has important significance for formulating regional grain policies and ensuring national grain safety.
The full-growth period of the rice comprises 7 main growth periods including a seedling stage, a tillering stage, a jointing stage, a booting stage, a heading stage, a grouting stage, a maturation stage and the like, and each growth period has different spectral characteristics. The difference of spectrum characteristics of rice and other crops can be identified by extracting growth characteristics of rice in different growth periods through multi-time-phase remote sensing data, and accurate identification of a rice planting system is realized. The identification of the regional scale rice planting system by adopting remote sensing time sequence data is a difficulty in current research. Firstly, the differences of rice varieties, local climates and terrains lead to the space-time heterogeneity of rice climatic features on a regional scale; secondly, cloud shadow problems, weather influences and noise introduced by sensors cause distortion of remote sensing time sequence data, so that deviation of rice weather characteristics is caused.
Shapelet refers to a sequence of time-series that is distinguishable. The time series Shapelet based approach has the following two advantages: (1) The Shapelet can fully explain the difference between the growth characteristics of crops such as rice and the like and the growth of other crops, has stronger identification, and can be effectively used for crop identification; (2) The similarity between subsequences of the Shapelet comparison time series reduces the amount of computation and retains sufficient growth characteristics to identify the crop type. Therefore, the time sequence classification method based on the shape can effectively solve the problems existing in the current multi-temporal remote sensing data crop identification.
Disclosure of Invention
Aiming at the defects of the existing work, the invention provides a double-cropping rice Tian Yaogan identification method based on a shape.
The invention discloses a double-cropping rice Tian Yaogan identification method based on a Shaapelet, which comprises the following steps of:
step 1: preparing and preprocessing data to form a paddy vegetation index time sequence data set in a research area;
Step 2: determining key points of the time sequence according to the growth period of the double-cropping rice, and acquiring a plurality of subsequences of the vegetation index time sequence by taking the key points as endpoints to form a shape candidate set;
step 3: carrying out importance evaluation on candidate shapelets, and selecting K optimal shapelets;
Step 4: shapelet conversion. Calculating the distances between all the time sequences and K shapelets, taking each time sequence as an object, taking the distances between the time sequences and the K shapelets as K attributes of each object, and converting each time sequence into a vector consisting of K attribute values;
step 5: constructing a convolutional neural network classifier, and training the convolutional neural network by using training samples;
step 6: and (5) introducing the converted time sequence into a classifier, identifying the rice field type, and generating a double-cropping rice distribution map.
In the step 1, the specific steps are as follows:
And collecting remote sensing data with higher quality, and obtaining a vegetation index time sequence data set of the research area through preprocessing such as geometric correction, radiation correction, merging and clipping, S-G filtering processing and the like.
In the step 2, the specific steps are as follows:
And determining a key time point according to double-cropping rice transplanting, tillering, jointing, booting, heading and maturing time. And extracting subsequences of the vegetation index time sequence by a sliding window method, indirectly controlling the length of the subsequences by changing and adjusting the size of the window, deleting the subsequences which do not contain key points, and forming a shape candidate set.
In the step 3, the specific steps are as follows:
1) Determining the relevance of 2 shapelets by using Pearson relevance coefficients, and generating a relevance matrix of a Shapelet candidate set;
2) Using the formula Calculating the information gain of each candidate Shapelet, and sequencing;
3) Screening K optimal shapelets according to the result of the information gain of the shapelets and the correlation matrix;
where IG represents the information gain of the Shapelet, entropy is entropy, C represents the total class, N i the number of samples for each class, N is the total number of samples, N 1、N2 and E 1、E2 are the number of 2 mutually disjoint subsets of samples and entropy, respectively, into which the dataset is partitioned by the shape. K is 1/2-2/3 of the key point number.
In the step 4, the distance between the time sequence T i and the shape k is calculated by using the formula
In the step 5, the specific steps are as follows:
And in the Python IDLE, a scikit-learn packet is called to construct a convolutional neural network classifier, training data is imported, and the classifier is trained.
In the step 6, the specific steps are as follows:
the converted time sequence is imported into a classifier, paddy fields are identified, and gdal is called in a Python IDLE to generate GTiff files.
The scheme of the invention has at least the following beneficial effects:
The invention provides a double-cropping rice Tian Yaogan identification method based on a shape set, which is characterized in that paddy field vegetation index grid data are converted into vegetation index time sequence data, the shape set is screened by adopting a Pearson correlation coefficient matrix and information gain method, and a neural network classifier is constructed to effectively classify the paddy field vegetation index time sequence data, so that double-cropping rice fields are identified. The adoption of the shape method can effectively overcome the vegetation index curve difference caused by the variety and management difference of the rice, and increase the accuracy of double-cropping rice identification; the Shaapelet screening scheme adopting the Pearson correlation coefficient and the information gain reduces the calculated amount and keeps the growth characteristics of the identified double-cropping rice field; the classification method based on the neural network is also beneficial to improving the identification precision of the double-cropping rice fields.
Drawings
FIG. 1 is a schematic flow chart of a double cropping rice Tian Yaogan identification method based on a Shaapelet of the present invention.
Fig. 2 is a schematic diagram of the extraction of key points of the time series proposed by the present invention.
Fig. 3 is the 8 best shapelets extracted from the double cropping rice field identification in 2018 of new fukan county.
Fig. 4 is a diagram of a double cropping rice field in 2018 of Xinganxian county.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to facilitate the detailed explanation of the double-cropping rice Tian Yaogan identification method based on the shape set, the definitions of time sequence and subsequence, time sequence-to-subsequence distance, split point, entropy, information gain, shape set and the like are introduced.
Definition 1: time sequence and subsequence: for a time sequence T of length m, each sub-sequence S of T is successively truncated starting from an arbitrary position of T. Wherein, the length of the subsequence is set as l, the starting point is P, and the subsequence is expressed as S= { t p,tp+1,…,tp+l-1 }, and P is more than or equal to 1 and less than or equal to m-l+1.
Definition 2: time sequence to subsequence distance: the distance between a shorter time series sub-sequence and a longer time series needs to be calculated from time series to sub-sequence. The short time series is slid over the long series to obtain the shortest distance between them, called the time series-to-subsequence distance, and is defined as
Definition 3: splitting point: a split point is a tuple (s, t), s representing a subsequence, t representing a threshold value of distance. A split point (s, t) splits the dataset D into two disjoint subsets, where D left＝{x:x∈D,subdist(s,x)≤t},Dright = { x: x e D, subdist (s, x) > t }.
Definition 4: entropy: assuming that the data set D contains N time series, the number of classes is C, class C i has N i instances in the data set D, and N 1+n2+…+nc =n, the entropy of the data set D is defined as:
definition 5: information gain: an information gain of a splitting point (s, t) is
Definition 6: a shape in dataset D is a tuple (S, T) consisting of a subsequence S of an instance T in D and a threshold T of split points, which attempts to split dataset D into two different groups. A Shaapelet is the subsequence in all split points that best distinguishes between the different classes.
For a further understanding and appreciation of the structural features and advantages achieved by the present invention, the following description is provided in connection with the accompanying drawings, which are presently preferred embodiments and are incorporated in the accompanying drawings, in which:
as shown in fig. 1, the identification method of double-cropping rice Tian Yaogan based on Shapelet according to the present invention includes the following steps:
First, EVI (enhanced vegetation index) data (MOD 13Q 1) of the paddy field MODIS in the study area are collected. The period 23 EVI data in 2018 in the dataset is selected to construct an EVI time series set. Data is downloaded from the NASA website (https:// lads web nascom NASA. Gov /). Mosaic, shearing, projection and resampling are carried out on MOD13Q1 data by MRT (MODIS Reprojection Tool) software, and EVI data is reconstructed by S-G filtering, so that a research area EVI time sequence data set is generated. In the Python IDLE, call gdal reads EVI data and stores it as a two-dimensional array. The spatial resolution of MOD13Q1 data is 250m, and mixed pixels of double-cropping rice and single-cropping rice are generated in the paddy field type learning process, so that paddy fields are classified into three types of double-cropping rice, single-cropping rice and single-double-cropping rice in the embodiment;
Secondly, determining key points of the time sequence (see figure 2) according to the growth period (see table 1) of the double-cropping rice and the time points of MOD13Q1 data, and acquiring subsequences of the time sequence in a sliding time window mode to generate a shape candidate set;
TABLE 1 double cropping Rice growth period
| Variety of species | Transplanting period | Tillering stage | Period of jointing | Heading stage | Spike alignment period | Maturity stage |
| Early rice | 4.20 | 5.8 | 5.28 | 6.6 | 6.12 | 7.12 |
| Late rice | 7.20 | 8.6 | 8.28 | 9.7 | 9.19 | 11.2 |
Thirdly, firstly calculating a Shaapelet candidate set Pearson correlation matrix, and selecting subsequences with the same length on a longer Shaapelet and calculating Pearson coefficients of the Shaapelet with the shorter length; according to the formula Calculating the information gain of each candidate Shapelet, and sequencing; selecting 8 shapelets with highest information gain (see fig. 3);
Fourth, according to the 8 optimal shapelets generated in the third step, adopting a formula The distance of each time series from this 8 shapelets is calculated, converting the time series into a vector of 8 attribute values, T i＝[disi,1,disi,2,…,disi,8. The expression method not only maintains the advantages of the classification of the shape time sequence data, but also reduces the data quantity, simplifies the operation, reduces the operation cost, simultaneously maintains the precedence relationship of the time sequence data, and ensures the classification precision;
Fifthly, in the Python IDLE, a scikit-learn package is called to construct a convolutional neural network classifier, training data is imported, and the classifier is trained. The convolutional neural network related parameters are set as follows: setting 3 convolution layers with the size of 3×3, and setting 64, 128 and 256 filters for each layer; setting 3 pooling layers, wherein the size is set to be 3 multiplied by 3; setting a full connection layer with the size of 1 multiplied by 3, and classifying by adopting a Softmax function; the learning rate is set to 0.01; parameter updating is carried out by adopting an SGD (Stochastic GRADIENT DESCENT) function to reduce the value of a loss function, in an SFG (sequential forward generation) optimization algorithm, the batch value is set to be 64, the weight attenuation factor is set to be 0.001, and the iteration value is set to be 10000;
And sixthly, importing the converted time sequence into the convolutional neural network classifier, identifying the paddy field type, calling gdal in a Python IDLE, converting the classification result into GTiff files, wherein the classification result is shown in figure 4, the classification accuracy is 0.87%, and the kappa coefficient is 0.89.
In addition to the embodiments described above, other embodiments of the invention are possible. All technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (7)
1. A double-cropping rice Tian Yaogan identification method based on a Shaapelet is characterized by comprising the following steps of: the method comprises the following steps:
step 1: preparing and preprocessing data to form a paddy vegetation index time sequence data set in a research area;
Step 2: determining key points of the time sequence according to the growth period of the double-cropping rice, and acquiring a plurality of subsequences of the vegetation index time sequence by taking the key points as endpoints to form a shape candidate set;
step 3: carrying out importance evaluation on candidate shapelets, and selecting K optimal shapelets;
step 4: shapelet conversion; calculating the distances between all the time sequences and K shapelets, taking each time sequence as an object, taking the distances between the time sequences and the K shapelets as K attributes of each object, and converting each time sequence into a vector consisting of K attribute values;
step 5: constructing a convolutional neural network classifier, and training the convolutional neural network by using training samples;
step 6: and (5) introducing the converted time sequence into a classifier, identifying the type of the paddy field, and generating a double-cropping paddy field distribution map.
2. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: in the step 1, geometric correction, radiation correction, mosaic, cutting, projection and resampling are carried out on remote sensing data of a research area, a vegetation index is calculated, and in a Python IDLE, S-G filtering is adopted to generate a time sequence data set of the vegetation index of the research area.
3. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: in the step 2, key points of the time sequence are determined according to the growth period of the double-cropping rice, the key points are taken as endpoints, and a plurality of subsequences of the vegetation index time sequence are obtained through sliding a time window to form a shape candidate set.
4. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: the step 3 comprises the following steps:
Firstly, calculating a Pearson correlation matrix of a Shaapelet candidate set;
Secondly, calculating and sequencing the information gain IG of each candidate shape; the calculation formula is as follows:
wherein: entropy is entropy, N is total sample number, the shape divides the data set into 2 mutually disjoint subsets, N1, N2 are the sample numbers of the two subsets, and E 1,E2 is the entropy of the two subsets, respectively;
thirdly, K shapelets with highest information gain are selected by combining the Pearson correlation coefficient matrix.
5. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: in step 4, a Shapelet conversion is carried out; according to the formulaAnd calculating the distances between all the time sequences and K shape elements, taking each time sequence as an object, taking the distances between the K shape elements and the time sequences as K attributes of each object, and converting each time sequence into a vector consisting of K attribute values.
6. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: in step 5, in the Python IDLE, a scikit-learn packet is called to construct a convolutional neural network classifier, training data is imported, and the classifier is trained.
7. A method for identifying double cropping rice Tian Yaogan based on Shapelet according to claim 1, wherein: in step 6, in the Python IDLE, the rice field vegetation index time sequence to be identified after the Shaapelet conversion is imported into a convolutional neural network classifier, double-cropping rice fields are identified, and gdal packets are called to generate GTiff type data and double-cropping rice field distribution diagrams.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011598570.7A CN112580595B (en) | 2020-12-30 | 2020-12-30 | Double-cropping rice Tian Yaogan identification method based on Shaapelet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011598570.7A CN112580595B (en) | 2020-12-30 | 2020-12-30 | Double-cropping rice Tian Yaogan identification method based on Shaapelet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112580595A CN112580595A (en) | 2021-03-30 |
| CN112580595B true CN112580595B (en) | 2024-06-21 |
Family
ID=75144164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011598570.7A Active CN112580595B (en) | 2020-12-30 | 2020-12-30 | Double-cropping rice Tian Yaogan identification method based on Shaapelet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112580595B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563720B (en) * | 2023-07-12 | 2023-10-03 | 华中师范大学 | Automatic generation method of single and double crop rice samples based on collaborative optical-microwave phenological characteristics |
| CN117407733B (en) * | 2023-12-12 | 2024-04-02 | 南昌科晨电力试验研究有限公司 | Flow anomaly detection method and system based on countermeasure generation shapelet |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127229A (en) * | 2016-06-16 | 2016-11-16 | 南京大学 | A kind of computer data sorting technique based on time series classification |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160217379A1 (en) * | 2015-01-27 | 2016-07-28 | University Of Southern California | Shapelet-Based Oilfield Equipment Failure Prediction and Detection |
| CN106355143A (en) * | 2016-08-25 | 2017-01-25 | 中国农业大学 | Seed maize field identification method and system based on multi-source and multi-temporal high resolution remote sensing data |
| US10586105B2 (en) * | 2016-12-30 | 2020-03-10 | International Business Machines Corporation | Method and system for crop type identification using satellite observation and weather data |
| CN109614904A (en) * | 2018-12-03 | 2019-04-12 | 东北大学 | An activity recognition method based on shapelet multi-sensor fusion |
-
2020
- 2020-12-30 CN CN202011598570.7A patent/CN112580595B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127229A (en) * | 2016-06-16 | 2016-11-16 | 南京大学 | A kind of computer data sorting technique based on time series classification |
Non-Patent Citations (1)
| Title |
|---|
| 水稻地上部干物质积累动态的定量模拟;李艳大;汤亮;陈青春;张玉屏;曹卫星;朱艳;;应用生态学报;20100615(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112580595A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183209B (en) | Regional crop classification method and system based on multidimensional feature fusion | |
| CN110414738B (en) | Crop yield prediction method and system | |
| CN111950530B (en) | Multi-feature optimization and fusion method for crop planting structure extraction | |
| CN112580595B (en) | Double-cropping rice Tian Yaogan identification method based on Shaapelet | |
| CN110175931B (en) | Method for rapidly extracting crop planting area and phenological information in large range | |
| CN112395914A (en) | Method for identifying land parcel crops by fusing remote sensing image time sequence and textural features | |
| CN113869370A (en) | Tree species refined classification method based on deep learning algorithm and time sequence sentinel image | |
| CN116227758B (en) | Agricultural product maturity prediction method and system based on remote sensing technology and deep learning | |
| CN116543316A (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
| CN114494909A (en) | Method and system for generating spatial distribution diagram of soybean growing season | |
| CN113408370B (en) | Forest change remote sensing detection method based on adaptive parameter genetic algorithm | |
| CN114491108A (en) | Online classification system and method based on multi-source remote sensing application data | |
| CN111666914A (en) | Cultivated land identification method, system, equipment and storage medium based on distance between curves | |
| CN118015462A (en) | Cotton planting area extraction method and device based on remote sensing image | |
| Jamil et al. | Ensemble of classifiers based soil evaluation for crop cultivation | |
| CN113723281B (en) | High-resolution image classification method based on local adaptive scale ensemble learning | |
| CN115328969A (en) | Crop yield analysis method based on meteorological data | |
| CN115146789A (en) | Winter wheat distribution extraction method and system based on phenological analysis and image segmentation | |
| CN114782835A (en) | Crop lodging area ratio detection method and device | |
| CN112651455A (en) | Traffic flow missing value filling method based on non-negative matrix factorization and dynamic time warping algorithm | |
| CN117952497B (en) | Agricultural logistics management system | |
| CN117788200B (en) | Agricultural product maturity prediction system based on multisource remote sensing data | |
| CN118799743B (en) | Natural field type detection method based on multi-task learning | |
| CN117172385B (en) | Sugarcane high-sugar-content harvest period prediction method and system | |
| CN114862955B (en) | Rapid visual positioning method for industrial robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |