CN112036313A - Tobacco planting area detection method, device and equipment and readable storage medium - Google Patents
Tobacco planting area detection method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN112036313A CN112036313A CN202010899556.4A CN202010899556A CN112036313A CN 112036313 A CN112036313 A CN 112036313A CN 202010899556 A CN202010899556 A CN 202010899556A CN 112036313 A CN112036313 A CN 112036313A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- remote sensing
- planting area
- sensing image
- extraction result
- 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.)
- Pending
Links
Images
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Abstract
The application belongs to the technical field of image processing, and provides a method, a device, equipment and a readable storage medium for detecting tobacco planting area, wherein the method comprises the following steps: collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images; preprocessing the multi-source remote sensing image; carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result; and fusing the cultivated land plot extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected. This application not only can promote the detection precision of tobacco planting area, and high-efficient easy-to-go extensive applicability.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method, a device and equipment for detecting tobacco planting area and a readable storage medium.
Background
The area and the yield of Chinese tobacco are the first in the world, and the tobacco plays a special role in national economy as a special economic crop. For a long time, the tobacco planting area is important economic information of national macro management and decision, is an important basis for managing and guiding tobacco production, optimizing layout and standardizing planting, and has important significance for effectively controlling the total amount of tobacco leaves and maintaining the order of tobacco market.
Traditionally, the supervision of tobacco leaf planting area by tobacco competent departments mainly uses satellite positioning technology to carry out geographical coordinate positioning on the tobacco leaf planting plots and measure the plot area to calculate the planting area, and this way only can carry out local spot check, and is time-consuming, laborious, high in cost and low in precision.
Disclosure of Invention
The application mainly aims to provide a method, a device and equipment for detecting tobacco planting area and a readable storage medium, and aims to solve the technical problems that a traditional mode for detecting the tobacco planting area only can be used for local spot check, and is time-consuming, labor-consuming, high in cost and low in precision.
In a first aspect, the present application provides a method for detecting a tobacco planting area, the method including:
collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images;
preprocessing the multi-source remote sensing image;
carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result;
and fusing the cultivated land plot extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected.
In a second aspect, the present application further provides a tobacco planting area detection device, the device includes:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, and the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images;
the preprocessing module is used for preprocessing the multi-source remote sensing image;
the extraction module is used for extracting cultivated land plots according to the preprocessed high-resolution remote sensing images to obtain cultivated land plot extraction results, and extracting tobacco information according to the preprocessed medium-low resolution remote sensing images to obtain tobacco information extraction results;
and the fusion module is used for fusing the farmland land block extraction result and the tobacco information extraction result so as to determine the tobacco planting area of the tobacco planting area to be detected.
In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the tobacco planting area detecting method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the tobacco planting area detection method as described above.
The application discloses a method, a device and equipment for detecting tobacco planting area and a readable storage medium, firstly collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images; then preprocessing the multi-source remote sensing image; carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result; and finally, fusing the cultivated land parcel extraction result and the tobacco information extraction result, thereby determining the tobacco planting area of the tobacco planting area to be detected. Because the cultivated land parcel extraction result based on the high-resolution remote sensing image has high extraction precision of the shape feature of the parcel, and the tobacco information extraction result based on the medium-low resolution remote sensing image considers the phenological feature of the tobacco, the attribute precision of the extraction result is higher, the cultivated land parcel extraction result and the tobacco information extraction result are fused, the shape precision of the tobacco parcel is ensured, the attribute precision of the tobacco parcel is ensured, and the purpose of improving the tobacco spatial distribution precision is finally achieved, so that the detection precision of the tobacco planting area is improved, the method is efficient and feasible, and the method is suitable for the application in large-area and small-area areas and has wide applicability.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting a tobacco planting area according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of the visibility of the vegetation coverage and the mulch film and the evolution trend thereof according to the embodiment of the present application;
fig. 3 is a flowchart illustrating a process of obtaining land use parcel information from a preprocessed high-resolution remote sensing image by using a deep learning algorithm according to an embodiment of the present application;
FIG. 4 is a diagram illustrating an example of a spatial distribution fusion process for tobacco according to an embodiment of the present disclosure;
fig. 5 is a schematic block diagram of a tobacco planting area detection device provided in an embodiment of the present application;
fig. 6 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a method, a device and equipment for detecting tobacco planting area and a computer readable storage medium. The method is mainly applied to tobacco planting area detection equipment, and the tobacco planting area detection equipment can be equipment with a data processing function, such as a Personal Computer (PC), a server and the like.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for detecting a tobacco planting area according to an embodiment of the present application.
As shown in fig. 1, the method for detecting the planting area of tobacco includes steps S101 to S104.
Step S101, collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images.
Wherein, for convenient understanding, the tobacco phenological characteristics are firstly analyzed and introduced:
1) tobacco production environment: the average air temperature in the tobacco growing season (5-9 months) is 22.3 ℃, the rainfall is 625mm, the accumulated temperature is 3410 ℃, the sunshine hours are 814h, and the sunshine percentage is 42%, and the tobacco growing season belongs to a proper region for tobacco growth.
2) Tobacco phenological characteristics: corn has very similar spectral characteristics to tobacco and is the crop most difficult to distinguish from tobacco. The spectral curves of the corn and the tobacco are basically consistent on the remote sensing image in the vigorous growth period, which is not beneficial to the distinction of the corn and the tobacco. However, the phenological climate of the tobacco and the corn has great difference, and the corn and the tobacco can be easily distinguished by utilizing multi-temporal remote sensing images based on the phenological climate difference. Generally, the sowing time of the spring corns in southern areas is 3 to 4 ten days of the year, the sowing is firstly carried out and then the mulching is carried out, the spring corns are matured at the beginning of 9 months at the bottom of 8 months, the sowing time of the spring corns is 5 to 6 ten days of the year in summer, the air temperature is high, the mulching film does not need to be covered generally, the spring corns are matured at the beginning of 11 months at the bottom of 10 months, the mulching film is covered during tobacco transplanting, and the time difference of nearly one month exists between the sowing time of the spring corns and the mulching film covering time of the spring corns. The tobacco transplanting time is generally from the bottom of 4 months to the end of 5 middle days of the month, the tobacco leaves are harvested and baked at the beginning of 8 months, and the phenological histories of the corns and the tobacco are shown in table 1.
TABLE 1 phenological comparison of tobacco and maize
3) Key time phase selection
When the mulching film is used as the tobacco field identification mark, the time selection of the remote sensing image is very important. Mulching films are covered during tobacco transplanting and spring corn sowing, and due to the fact that the mulching time of the mulching films is different for a long time, conditions are provided for distinguishing tobacco fields from corns. For ease of illustration, the visibility of the mulch needs to be defined. Vegetation coverage is the percentage of the vertical projected area of vegetation (including leaves, stems, branches) per unit area. With reference to the method for defining the vegetation coverage, the visibility of the mulching film is defined as the percentage of the area of the mulching film per unit area observed from top to bottom in the vertical direction.
As shown in fig. 2, fig. 2 is a schematic view of vegetation coverage and mulch visibility and evolution trend thereof. The vegetation coverage and the mulching film coverage of the tobacco field and the corn are gradually evolved along with the time, and the selection of proper remote sensing monitoring time according to the evolution rule becomes the key for distinguishing the tobacco field and the corn. And (4) obtaining the evolution trend curve of the vegetation coverage and the mulching film visibility according to the growth phenological period simulation of the tobacco and the spring corn. The visibility of the mulching films of the tobacco and the corn is gradually reduced along with the time, and the vegetation coverage is firstly increased and then reduced. In the period from the last ten days of 5 months to the beginning of 6 months, the vegetation coverage of the tobacco and the corn and the visibility of the mulching film are in proper proportion, and the time is the optimal period suitable for remote sensing distinguishing. If the time period is earlier than the time period, the visibility of the mulching films of the tobacco and the corn is large, and the remote sensing image is mainly reflected as the spectrum of the mulching film, so that the spectrum confusion between the tobacco mulching film and the corn mulching film is caused; if the time is later than the period, the vegetation coverage of the tobacco and the corn is relatively high, the remote sensing image is mainly reflected as the spectrum of the vegetation, and the spectrum confusion between the tobacco and the corn leaves is caused; only in the period from 5 late ten days to 6 months, the tobacco on the remote sensing image is mainly expressed as the mulching film characteristic, and the corn is expressed as the vegetation characteristic, so that the tobacco area remote sensing monitoring method is favorable for distinguishing the tobacco area remote sensing image and the corn area remote sensing monitoring method is an optimal period suitable for remote sensing monitoring of the tobacco area.
Thus, based on the above-described analyzed characteristic of the phenological characteristic of tobacco, a period from late 5 months to early 6 months is set as a predetermined phenological period, for example, from 20 days in 5 months to 5 days in 6 months.
Firstly, collecting a multi-source remote sensing image of a tobacco planting area to be detected in a preset tobacco phenological period.
In an embodiment, the collecting a multi-source remote sensing image of a tobacco planting area to be detected in a preset tobacco phenological period specifically includes: when a tobacco planting area detection task is received, extracting geographical position information of a tobacco planting area to be detected and a preset tobacco phenological period from the tobacco planting area detection task; and controlling a plurality of different remote sensing satellites to shoot remote sensing images of the tobacco planting area to be detected in a preset tobacco phenological period at the same time according to the geographic position information to obtain a multi-source remote sensing image.
The method comprises the steps that communication connection between the tobacco planting area detection equipment and various different remote sensing satellites is established in advance, relevant workers can trigger corresponding tobacco planting area detection tasks on the tobacco planting area detection equipment, the tobacco planting area detection tasks carry geographical position information of tobacco planting areas to be detected and preset tobacco phenological periods, and the geographical position information can be the longitude and latitude of the tobacco planting areas to be detected.
The growing period of tobacco is long, and images of a single satellite are difficult to cover the complete growing period, so when a tobacco planting area detection task is received by tobacco planting area detection equipment, according to geographical position information of a tobacco planting area to be detected, a plurality of different remote sensing satellites are controlled to simultaneously shoot remote sensing images of the tobacco planting area to be detected in a preset tobacco phenological period, and multi-source remote sensing images are obtained.
And S102, preprocessing the multi-source remote sensing image.
After the multi-source remote sensing image is collected, the collected multi-source remote sensing image needs to be preprocessed.
In an embodiment, the preprocessing the multi-source remote sensing image specifically includes: atmospheric correction is carried out on the multi-source remote sensing image; and performing geometric correction on the multi-source remote sensing image after atmospheric correction.
The method can directly obtain atmospheric compensation parameters from the remote sensing image (observation pixel spectrum), and the calculation formula is as follows:
ρ′＝(ρ1+ρ2+...+ρn)/n
the QUAC model is based on experience and takes the average reflectance of collected spectra of end members of different substances, such as the field of view, where n represents the number of end members.
And then, geometrically correcting the multisource remote sensing image subjected to atmospheric correction, wherein the geometric correction corrects and eliminates the deformation generated when the characteristics of geometric positions, shapes, sizes, orientations and the like of all objects on the original image caused by the factors of photographic material deformation, objective lens distortion, atmospheric refraction, earth curvature, earth rotation, terrain relief and the like in the imaging of the remote sensing image are inconsistent with the expression requirements in a reference system through a series of mathematical models, and the spatial positions of the remote sensing images from different remote sensing satellites are kept consistent. Specifically, the geometric correction is performed by using control points, which is to use a mathematical model to approximately describe the geometric distortion process of the remote sensing image, and use some corresponding points (i.e. control point data pairs) between the distorted remote sensing image and the standard map to obtain the geometric distortion model, and then use the model to perform the geometric distortion correction.
Step S103, cultivated land plot extraction is carried out on the preprocessed high-resolution remote sensing image to obtain cultivated land plot extraction results, and tobacco information extraction is carried out on the preprocessed medium-low resolution remote sensing image to obtain tobacco information extraction results.
And then, carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result.
In an embodiment, the extracting cultivated land parcel to the preprocessed high-resolution remote sensing image to obtain the cultivated land parcel extraction result specifically includes: acquiring land use plot information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm; and dividing and extracting cultivated land plots on the preprocessed high-resolution remote sensing image according to the land utilization plot information to obtain cultivated land plot extraction results.
In order to ensure the extraction precision of the cultivated land plots, a deep learning algorithm is adopted to improve the dividing precision of the cultivated land plots. Firstly, obtaining land utilization land parcel information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm, and dividing and extracting cultivated land parcels on the preprocessed high-resolution remote sensing image according to the land utilization land parcel information to obtain cultivated land parcel extraction results.
The method comprises the following steps of dividing and extracting cultivated land plots on a preprocessed high-resolution remote sensing image according to land utilization plot information, and specifically adopting an ArcGIS-based artificial visual interpretation extraction method, namely modifying the preprocessed high-resolution remote sensing image by plots by using ArcGIS software according to the land utilization plot information, wherein the main modification content comprises the following steps: the method has the advantages that the method endows the plots with attributes (such as arable land, water areas, buildings, forest lands, crops and the like), the shapes of the plots, the combined broken small plots, the plots with large cutting areas, the newly added omitted plots and the deleted plots which are automatically and incorrectly segmented, so that the accuracy of division of the arable land plots is further improved, and the extraction accuracy of the arable land plots is further improved.
In an embodiment, the obtaining land use parcel information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm specifically includes: carrying out image segmentation on the preprocessed high-resolution remote sensing image to obtain a linear ground object and other ground object objects; predicting the linear ground object and the other ground object respectively by utilizing a preset Convolutional Neural Network (CNN) model to obtain a prediction result of the linear ground object and a prediction result of the other ground object; and fusing the prediction result of the linear ground object and the prediction results of the other ground objects to acquire land utilization land information.
As shown in fig. 3, fig. 3 is a flowchart illustrating a process of obtaining land use parcel information from a preprocessed high-resolution remote sensing image by using a deep learning algorithm. That is, since the shape features of different features are different, the preprocessed high-resolution remote sensing image can be segmented into two types of objects by using a multi-scale segmentation method according to the shape features of different features: linear terrain objects (e.g., roads, rivers, etc.) and other terrain objects; then, training and predicting the linear ground object objects and other ground object objects respectively by adopting input windows with different sizes through a Convolutional Neural Network (CNN) model to obtain two prediction results, and finally, performing decision fusion on the two prediction results to automatically acquire land utilization land parcel information.
In an embodiment, the tobacco information extraction is performed on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result, which specifically comprises: dividing the preprocessed medium-low resolution remote sensing image into remote sensing images belonging to three key phenological periods; respectively carrying out land utilization classification on the remote sensing images belonging to each key phenological period by using a supervision classification method so as to obtain a land utilization classification result graph of each key phenological period; and according to the distribution characteristics of the tobacco phenological periods, combining the land utilization classification result graph of each key phenological period to extract the tobacco spatial distribution characteristics, so as to obtain a tobacco information extraction result.
In order to quickly and accurately obtain the tobacco information extraction result, the preprocessed medium-low resolution remote sensing image is divided into remote sensing images belonging to three key phenological periods based on the analysis result of the tobacco phenological period characteristics. For example, according to the shooting date of the preprocessed medium-low resolution remote sensing image, the preprocessed medium-low resolution remote sensing image is divided into a remote sensing image of a key phenological period 1, a remote sensing image of a key phenological period 2 and a remote sensing image of a key phenological period 3 in time sequence from front to back, for example, a remote sensing image of 5 months, 20 days to 5 months, 25 days is used as the remote sensing image of the key phenological period 1, a remote sensing image of 5 months, 26 days to 5 months, 30 days is used as the remote sensing image of the key phenological period 2, and a remote sensing image of 6 months, 1 day to 6 months, 5 days is used as the remote sensing image of the key phenological period 3.
And then, extracting a land use classification result by respectively utilizing a supervision classification method based on the remote sensing images of the three key phenological periods, and then extracting the spatial distribution characteristics of the tobacco by utilizing a change monitoring method.
1) Land use classification information extraction based on a supervision classification method: the supervised classification method is a technology for classifying images to be classified by establishing a statistical recognition function as a theoretical basis and according to a typical sample training method, namely, according to samples provided by a known training area, by selecting characteristic parameters, solving the characteristic parameters to serve as a decision rule and establishing a discriminant function to classify the images to be classified. If the judgment criterion meets the requirement of classification precision, the criterion is satisfied; otherwise, the decision rule of classification needs to be re-established until the requirement of classification precision is met. The method mainly comprises a minimum distance method, a maximum likelihood method, a mahalanobis distance method and the like.
Taking a minimum distance method (the minimum distance method is a classification method with simple principle and convenient application, calculating a mean vector and a standard deviation vector of each class by using training sample data, then taking the mean vector as the central position of the class in a feature space, calculating the distance from each pixel in an input image to each class of center, and classifying the pixel into which class the distance is minimum), firstly, selecting the training sample on the remote sensing image belonging to each key phenological period according to the classification type (water body, vegetation, building and the like), and then respectively carrying out land use classification on the remote sensing image belonging to each key phenological period by adopting a minimum distance algorithm according to the selected training sample to obtain land use classification result graphs of the three key phenological periods.
2) Extracting tobacco spatial distribution characteristics based on a change monitoring method: according to the distribution characteristics of the tobacco phenological periods, on the basis of the land utilization classification result graph of each key phenological period, the tobacco distribution characteristics are rapidly extracted. Specifically, whether tobacco mulch features exist in a land use classification result map corresponding to the key phenological period 1, whether tobacco mulch features exist in a land use classification result map corresponding to the key phenological period 2, and whether tobacco vegetation features exist in a land use classification result map corresponding to the key phenological period 3 are respectively judged, if tobacco mulch features exist in a land use classification result map corresponding to the key phenological period 1, tobacco mulch features exist in a land use classification result map corresponding to the key phenological period 2, and tobacco vegetation features exist in a land use classification result map corresponding to the key phenological period 3, tobacco mulch features existing in a land use classification result map corresponding to the key phenological period 1, tobacco mulch features existing in a land use classification result map corresponding to the key phenological period 2, and tobacco vegetation features existing in a land use classification result map corresponding to the key phenological period 3 are combined, and (4) rapidly extracting the spatial distribution characteristics of the tobacco to obtain a tobacco information extraction result.
And step S104, fusing the cultivated land parcel extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected.
It should be noted that, the cultivated land plot extraction result obtained based on the high-resolution remote sensing image and the tobacco information extraction result obtained based on the medium-low resolution remote sensing image both belong to the spatial distribution result of tobacco, but both have respective advantages and disadvantages.
Specifically, the cultivated land plot extraction result based on the high-resolution remote sensing image has the advantages that the shape feature extraction precision of the plot is high, but the attribute extraction precision of the plot is relatively low due to the fact that the phenological features of tobacco are not considered, namely, the extracted plot result is not completely a tobacco planting area, and other crops such as corn and soybean can be contained in the extracted plot result. The tobacco information extraction result based on the medium-low resolution remote sensing image has the advantages that the phenological characteristics of tobacco are considered, the attribute precision of the extraction result is high, but the attribute precision is limited by the resolution problem of the image, and the spatial distribution shape precision of the tobacco land is relatively low. Therefore, the two results are effectively fused, and the tobacco planting area result with high shape and attribute precision is extracted. Specifically, as shown in fig. 4, the cultivated land parcel extraction result and the tobacco information extraction result are intersected to obtain a tobacco spatial distribution fusion result, which is used as the tobacco planting area.
The tobacco planting area detection method provided by the embodiment comprises the steps of firstly collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images; then preprocessing the multi-source remote sensing image; carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result; and finally, fusing the cultivated land parcel extraction result and the tobacco information extraction result, thereby determining the tobacco planting area of the tobacco planting area to be detected. Because the cultivated land parcel extraction result based on the high-resolution remote sensing image has high extraction precision of the shape feature of the parcel, and the tobacco information extraction result based on the medium-low resolution remote sensing image considers the phenological feature of the tobacco, the attribute precision of the extraction result is higher, the cultivated land parcel extraction result and the tobacco information extraction result are fused, the shape precision of the tobacco parcel is ensured, the attribute precision of the tobacco parcel is ensured, and the purpose of improving the tobacco spatial distribution precision is finally achieved, so that the detection precision of the tobacco planting area is improved, the method is efficient and feasible, and the method is suitable for the application in large-area and small-area areas and has wide applicability.
Referring to fig. 5, fig. 5 is a schematic block diagram of a tobacco planting area detection device according to an embodiment of the present application.
As shown in fig. 5, the tobacco planting area detecting device 400 includes: an acquisition module 401, a pre-processing module 402, an extraction module 403, and a fusion module 404.
The acquisition module 401 is used for acquiring multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images;
a preprocessing module 402, configured to preprocess the multi-source remote sensing image;
an extraction module 403, configured to extract cultivated land plots from the preprocessed high-resolution remote sensing images to obtain cultivated land plot extraction results, and extract tobacco information from the preprocessed medium-low resolution remote sensing images to obtain tobacco information extraction results;
and a fusion module 404, configured to fuse the cultivated land parcel extraction result and the tobacco information extraction result to determine a tobacco planting area of the to-be-detected tobacco planting area.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the device and each module and unit described above may refer to the corresponding processes in the foregoing embodiment of the method for detecting the planting area of tobacco, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program, which can be run on a computer device as shown in fig. 6.
Referring to fig. 6, fig. 6 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a Personal Computer (PC), a server, or the like having a data processing function.
As shown in fig. 6, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the methods of detecting a tobacco planting area.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program in the non-volatile storage medium, and the computer program, when executed by the processor, causes the processor to perform any one of the methods for detecting a tobacco planting area.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images; preprocessing the multi-source remote sensing image; carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result; and fusing the cultivated land plot extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected.
In some embodiments, the processor implements the preprocessing of the multi-source remote sensing image, including:
atmospheric correction is carried out on the multi-source remote sensing image;
and performing geometric correction on the multi-source remote sensing image after atmospheric correction.
In some embodiments, the processor implements the farmland land block extraction on the preprocessed high-resolution remote sensing image to obtain a farmland land block extraction result, and the method includes:
acquiring land use plot information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm;
and dividing and extracting cultivated land plots on the preprocessed high-resolution remote sensing image according to the land utilization plot information to obtain cultivated land plot extraction results.
In some embodiments, the processor implements the deep learning algorithm to obtain land use plot information from the preprocessed high-resolution remote sensing image, and the method includes:
carrying out image segmentation on the preprocessed high-resolution remote sensing image to obtain a linear ground object and other ground object objects;
predicting the linear ground object and the other ground object respectively by utilizing a preset Convolutional Neural Network (CNN) model to obtain a prediction result of the linear ground object and a prediction result of the other ground object;
and fusing the prediction result of the linear ground object and the prediction results of the other ground objects to acquire land utilization land information.
In some embodiments, the extracting the tobacco information from the preprocessed medium-low resolution remote sensing image by the processor to obtain a tobacco information extraction result includes:
dividing the preprocessed medium-low resolution remote sensing image into remote sensing images belonging to three key phenological periods;
respectively carrying out land utilization classification on the remote sensing images belonging to each key phenological period by using a supervision classification method so as to obtain a land utilization classification result graph of each key phenological period;
and according to the distribution characteristics of the tobacco phenological periods, combining the land utilization classification result graph of each key phenological period to extract the tobacco spatial distribution characteristics, so as to obtain a tobacco information extraction result.
In some embodiments, the fusing the arable land block extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected by the processor includes:
intersecting the cultivated land plot extraction result and the tobacco information extraction result to obtain a tobacco space distribution fusion result which is used as the tobacco planting area.
In some embodiments, the acquiring a multi-source remote sensing image of a to-be-detected tobacco planting area in a preset tobacco phenological period by the processor includes:
when a tobacco planting area detection task is received, extracting geographical position information of a tobacco planting area to be detected and a preset tobacco phenological period from the tobacco planting area detection task;
and controlling a plurality of different remote sensing satellites to shoot remote sensing images of the tobacco planting area to be detected in a preset tobacco phenological period at the same time according to the geographic position information to obtain a multi-source remote sensing image.
The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed, a method implemented by the computer program instructions may refer to various embodiments of the method for detecting a tobacco planting area of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A tobacco planting area detection method is characterized by comprising the following steps:
collecting multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, wherein the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images;
preprocessing the multi-source remote sensing image;
carrying out cultivated land plot extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land plot extraction result, and carrying out tobacco information extraction on the preprocessed medium-low resolution remote sensing image to obtain a tobacco information extraction result;
and fusing the cultivated land plot extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected.
2. The method for detecting the planting area of the tobacco according to claim 1, wherein the preprocessing the multi-source remote sensing image comprises:
atmospheric correction is carried out on the multi-source remote sensing image;
and performing geometric correction on the multi-source remote sensing image after atmospheric correction.
3. The method for detecting the planting area of the tobacco according to claim 1, wherein the step of performing cultivated land block extraction on the preprocessed high-resolution remote sensing image to obtain a cultivated land block extraction result comprises the following steps:
acquiring land use plot information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm;
and dividing and extracting cultivated land plots on the preprocessed high-resolution remote sensing image according to the land utilization plot information to obtain cultivated land plot extraction results.
4. The method for detecting the planting area of the tobacco according to claim 3, wherein the step of acquiring land utilization plot information from the preprocessed high-resolution remote sensing image by using a deep learning algorithm comprises the following steps:
carrying out image segmentation on the preprocessed high-resolution remote sensing image to obtain a linear ground object and other ground object objects;
predicting the linear ground object and the other ground object respectively by utilizing a preset Convolutional Neural Network (CNN) model to obtain a prediction result of the linear ground object and a prediction result of the other ground object;
and fusing the prediction result of the linear ground object and the prediction results of the other ground objects to acquire land utilization land information.
5. The method for detecting the planting area of the tobacco according to claim 1, wherein the extracting the tobacco information from the preprocessed medium-low resolution remote sensing image to obtain the tobacco information extraction result comprises:
dividing the preprocessed medium-low resolution remote sensing image into remote sensing images belonging to three key phenological periods;
respectively carrying out land utilization classification on the remote sensing images belonging to each key phenological period by using a supervision classification method so as to obtain a land utilization classification result graph of each key phenological period;
and according to the distribution characteristics of the tobacco phenological periods, combining the land utilization classification result graph of each key phenological period to extract the tobacco spatial distribution characteristics, so as to obtain a tobacco information extraction result.
6. The method for detecting the tobacco planting area according to claim 1, wherein the fusing the cultivated land parcel extraction result and the tobacco information extraction result to determine the tobacco planting area of the tobacco planting area to be detected comprises:
intersecting the cultivated land plot extraction result and the tobacco information extraction result to obtain a tobacco space distribution fusion result which is used as the tobacco planting area.
7. The method for detecting the planting area of the tobacco according to claim 1, wherein the collecting the multi-source remote sensing image of the tobacco planting area to be detected in a preset tobacco phenological period comprises:
when a tobacco planting area detection task is received, extracting geographical position information of a tobacco planting area to be detected and a preset tobacco phenological period from the tobacco planting area detection task;
and controlling a plurality of different remote sensing satellites to shoot remote sensing images of the tobacco planting area to be detected in a preset tobacco phenological period at the same time according to the geographic position information to obtain a multi-source remote sensing image.
8. The utility model provides a tobacco planting area detection device which characterized in that, tobacco planting area detection device includes:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring multi-source remote sensing images of a tobacco planting area to be detected in a preset tobacco phenological period, and the multi-source remote sensing images comprise high-resolution remote sensing images and medium-low resolution remote sensing images;
the preprocessing module is used for preprocessing the multi-source remote sensing image;
the extraction module is used for extracting cultivated land plots according to the preprocessed high-resolution remote sensing images to obtain cultivated land plot extraction results, and extracting tobacco information according to the preprocessed medium-low resolution remote sensing images to obtain tobacco information extraction results;
and the fusion module is used for fusing the farmland land block extraction result and the tobacco information extraction result so as to determine the tobacco planting area of the tobacco planting area to be detected.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, carries out the steps of the method of detecting a planting area of tobacco as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of detecting tobacco planting area of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010899556.4A CN112036313A (en) | 2020-08-31 | 2020-08-31 | Tobacco planting area detection method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010899556.4A CN112036313A (en) | 2020-08-31 | 2020-08-31 | Tobacco planting area detection method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112036313A true CN112036313A (en) | 2020-12-04 |
Family
ID=73587754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010899556.4A Pending CN112036313A (en) | 2020-08-31 | 2020-08-31 | Tobacco planting area detection method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112036313A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082546A (en) * | 2022-06-22 | 2022-09-20 | 中科三清科技有限公司 | Method and device for determining pollutant discharge amount, electronic equipment and medium |
| CN116246175A (en) * | 2023-05-05 | 2023-06-09 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175209A (en) * | 2010-12-07 | 2011-09-07 | 北京师范大学 | Effective sampling method for crop cultivated area measurement under support of historical remote sensing product data |
| CN105550707A (en) * | 2015-12-11 | 2016-05-04 | 中国烟草总公司广东省公司 | Classified extraction method of tobacco field remote sensing data |
-
2020
- 2020-08-31 CN CN202010899556.4A patent/CN112036313A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175209A (en) * | 2010-12-07 | 2011-09-07 | 北京师范大学 | Effective sampling method for crop cultivated area measurement under support of historical remote sensing product data |
| CN105550707A (en) * | 2015-12-11 | 2016-05-04 | 中国烟草总公司广东省公司 | Classified extraction method of tobacco field remote sensing data |
Non-Patent Citations (1)
| Title |
|---|
| 李天坤: "基于面向对象分类方法的烟草种植面积提取研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082546A (en) * | 2022-06-22 | 2022-09-20 | 中科三清科技有限公司 | Method and device for determining pollutant discharge amount, electronic equipment and medium |
| CN115082546B (en) * | 2022-06-22 | 2023-03-21 | 中科三清科技有限公司 | Method and device for determining pollutant discharge amount, electronic equipment and medium |
| CN116246175A (en) * | 2023-05-05 | 2023-06-09 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
| CN116246175B (en) * | 2023-05-05 | 2023-07-14 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| El Hajj et al. | Integrating SPOT-5 time series, crop growth modeling and expert knowledge for monitoring agricultural practices—The case of sugarcane harvest on Reunion Island | |
| Zhong et al. | Phenology-based crop classification algorithm and its implications on agricultural water use assessments in California’s Central Valley | |
| Conrad et al. | Satellite based calculation of spatially distributed crop water requirements for cotton and wheat cultivation in Fergana Valley, Uzbekistan | |
| CN107527014A (en) | Crops planting area RS statistics scheme of sample survey design method at county level | |
| Kordi et al. | Crop classification based on phenology information by using time series of optical and synthetic-aperture radar images | |
| Gandharum et al. | Remote sensing versus the area sampling frame method in paddy rice acreage estimation in Indramayu regency, West Java province, Indonesia | |
| Erdogan et al. | Modelling the impact of land-cover change on potential soil loss in the Taita Hills, Kenya, between 1987 and 2003 using remote-sensing and geospatial data | |
| Liu et al. | Optimal MODIS data processing for accurate multi-year paddy rice area mapping in China | |
| CN107680098A (en) | A kind of recognition methods of sugarcane sugarcane section feature | |
| Liu et al. | Estimating maize seedling number with UAV RGB images and advanced image processing methods | |
| Kang et al. | Support vector machine classification of crop lands using sentinel-2 imagery | |
| CN112036313A (en) | Tobacco planting area detection method, device and equipment and readable storage medium | |
| CN108596029A (en) | Crop classification method, apparatus, computer equipment and storage medium | |
| CN115761486A (en) | Rice planting area judgment method and system based on multi-stage rice field image characteristics | |
| Paolini et al. | Classification of different irrigation systems at field scale using time-series of remote sensing data | |
| Liu et al. | Evaluating how lodging affects maize yield estimation based on UAV observations | |
| Zhu et al. | UAV flight height impacts on wheat biomass estimation via machine and deep learning | |
| Singla et al. | Spatiotemporal analysis of LANDSAT Data for Crop Yield Prediction. | |
| Gers et al. | Using SPOT4 satellite imagery to monitor area harvested by small scale sugarcane farmers at Umfolozi | |
| CN115205688A (en) | Tea tree planting area extraction method and system | |
| Nafarin et al. | Relationship between normalized difference vegetation index (NDVI) and Rice growth phases in Danda Jaya swamp irrigation area regency Barito Kuala | |
| Zhou et al. | Monitoring intra-annual and interannual variability in spatial distribution of plastic-mulched citrus in cloudy and rainy areas using multisource remote sensing data | |
| Shen et al. | High-throughput phenotyping of individual plant height in an oilseed rape population based on Mask-RCNN and UAV images | |
| Bai et al. | Estimating leaf age of maize seedlings using UAV-based RGB and multispectral images | |
| CN114067158B (en) | Farmland use state monitoring system and method applying multi-source remote sensing data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201204 |
|
| RJ01 | Rejection of invention patent application after publication |