CN111860626A - Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification - Google Patents
Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification Download PDFInfo
- Publication number
- CN111860626A CN111860626A CN202010637419.3A CN202010637419A CN111860626A CN 111860626 A CN111860626 A CN 111860626A CN 202010637419 A CN202010637419 A CN 202010637419A CN 111860626 A CN111860626 A CN 111860626A
- Authority
- CN
- China
- Prior art keywords
- detection
- soil
- water
- image
- aerial vehicle
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of water and soil detection, in particular to a water and soil conservation monitoring method and a system based on unmanned aerial vehicle remote sensing and object-oriented classification, wherein the method comprises the following steps: s10: obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed; s20: respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results; s30: scoring the image to be decided according to the classification result, and marking the image to be decided corresponding to the score lower than a preset scoring threshold value to obtain key detection data; s40: and acquiring unmanned aerial vehicle detection information from the key detection data, and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information. The invention has the effect of improving the efficiency of soil and water conservation detection.
Description
Technical Field
The invention relates to the technical field of water and soil detection, in particular to a water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification.
Background
At present, water and soil conservation (soilandand water conservation) is the work of preventing water and soil loss, protecting, improving and reasonably utilizing water and soil resources and establishing a good ecological environment. The unmanned aerial vehicle is unmanned flying equipment controlled remotely, the unmanned aerial vehicle technology is a technology for realizing tasks through radio control and terminal equipment program setting, and the technology is realized by the cooperation of a ground control system, a flying system and a task system.
The Chinese patent application with the publication number of CN107844802A discloses a water and soil conservation monitoring method based on unmanned aerial vehicle low-altitude remote sensing and object-oriented classification, which comprises the steps of carrying a visible light camera by an unmanned aerial vehicle to shoot a water and soil conservation monitoring target area, and collecting a control point; carrying out coordinate system registration, area integral adjustment and multi-view image dense matching on the original image picture to generate dense point cloud, further generating a TIN triangulation network, and generating a real three-dimensional model of the area to be detected through texture mapping; calculating and segmenting the three-dimensional model to obtain an actual optimal segmentation scale suitable for a soil and water conservation monitoring target area; determining characteristic parameter indexes participating in object-oriented classification, and performing supervision classification and extraction; and calculating the total classification precision and the Kappa coefficient by adopting a precision evaluation method and a confusion matrix based on the position information, and evaluating the classification precision of the model. The invention is suitable for soil and water conservation monitoring. The problems of poor applicability and low working efficiency of the existing monitoring method are solved.
The above prior art solutions have the following drawbacks:
in the engineering project for detecting water and soil conservation for a long time, when the water and soil loss is detected, the specific situation of the water and soil loss needs to be treated, and after the treatment is finished, the detection of the region needs to be periodically repeated, so that the working efficiency is influenced, and therefore, the improvement space is provided.
Disclosure of Invention
The invention aims to provide a water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification, which can improve the efficiency of water and soil conservation detection.
The above object of the present invention is achieved by the following technical solutions:
a water and soil conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification comprises the following steps:
s10: obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed;
s20: respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results;
S30: scoring the image to be decided according to the classification result, and marking the image to be decided corresponding to the score lower than a preset scoring threshold value to obtain key detection data;
s40: and acquiring unmanned aerial vehicle detection information from the key detection data, and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
By adopting the technical scheme, each image to be analyzed can be analyzed in a distributed and targeted manner by segmenting the historical water and soil detection image, so that the analysis efficiency and precision can be improved; classifying the images to be analyzed by using the water and soil detection result of each image to be analyzed, and correspondingly marking the images to be decided according to the classification result to obtain key detection data; through triggering the corresponding soil and water conservation detection message according to the key detection data, the key detection of the region with serious soil and water loss can be realized, so that the repeated detection of the whole soil and water conservation region is not needed, and the detection pertinence and the detection efficiency are also ensured.
The present invention in a preferred example may be further configured to: step S10 includes:
s11: acquiring a water and soil detection area map from the historical water and soil detection image, and acquiring area characteristic information from the water and soil detection area;
S12: and segmenting the historical water and soil detection image according to the regional characteristic information to obtain the image to be analyzed.
By adopting the technical scheme, the historical water and soil detection image is segmented according to the regional characteristic information, so that the integrity of the characteristics of the obtained image to be analyzed can be realized, and the precision of the subsequent analysis result is improved.
The present invention in a preferred example may be further configured to: step S20 includes:
s21: acquiring a corresponding detection index according to the image to be analyzed, and constructing a water and soil conservation simulation diagram according to the detection index;
s22: and comparing the image to be analyzed with the corresponding water and soil conservation simulation diagram, and acquiring a corresponding water and soil detection result according to the comparison result.
Through adopting above-mentioned technical scheme, through using the detection index that corresponds, simulate out corresponding soil and water and keep the mimic diagram, can correspond with waiting to analyze the image, through the mode that the picture is compared, can obtain soil and water testing result sooner and more accurately to analysis soil and water testing result's efficiency has been promoted.
The present invention in a preferred example may be further configured to: step S40 includes:
S41: acquiring unmanned aerial vehicle detection coordinates and corresponding unmanned aerial vehicle detection attitude information from the key detection data, and taking the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information as unmanned aerial vehicle detection information;
s42: and triggering the soil and water conservation detection message according to the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information.
By adopting the technical scheme, the unmanned aerial vehicle can be controlled to go to the corresponding position for detection by acquiring the detection coordinate of the unmanned aerial vehicle; by acquiring the corresponding unmanned aerial vehicle detection attitude information, the unmanned aerial vehicle detection result can be more accurate.
The present invention in a preferred example may be further configured to: step S42 includes:
s421: setting corresponding detection weights for the key detection data according to the scores, and setting the number of cyclic detections according to the detection weights;
s422: and detecting the key detection data according to the cyclic detection number.
Through adopting above-mentioned technical scheme, through setting up corresponding detection weight, through the circulation detection quantity that this detection weight set up to correspond, can set up the work load of corresponding detection according to the condition of soil erosion and water loss to detection efficiency has been promoted.
The second aim of the invention is realized by the following technical scheme:
a soil and water conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification comprises:
the image segmentation module is used for obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed;
the image classification module is used for respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results;
the marking module is used for scoring the image to be decided according to the classification result, marking the image to be decided corresponding to the score lower than a preset scoring threshold value, and obtaining key detection data;
and the circulating detection module is used for acquiring unmanned aerial vehicle detection information from the key detection data and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
By adopting the technical scheme, each image to be analyzed can be analyzed in a distributed and targeted manner by segmenting the historical water and soil detection image, so that the analysis efficiency and precision can be improved; classifying the images to be analyzed by using the water and soil detection result of each image to be analyzed, and correspondingly marking the images to be decided according to the classification result to obtain key detection data; through triggering the corresponding soil and water conservation detection message according to the key detection data, the key detection of the region with serious soil and water loss can be realized, so that the repeated detection of the whole soil and water conservation region is not needed, and the detection pertinence and the detection efficiency are also ensured.
In summary, the invention includes at least one of the following beneficial technical effects:
1. by segmenting the historical water and soil detection image, each image to be analyzed can be analyzed in a distributed and targeted manner, and the efficiency and the accuracy of analysis can be improved;
2. the corresponding soil and water conservation detection message is triggered according to the key detection data, so that the key detection of the region with serious soil and water loss can be realized, the repeated detection of the whole soil and water conservation region is not needed, the detection pertinence is ensured, and the detection efficiency is improved;
3. by using the corresponding detection indexes, the corresponding water and soil conservation simulation diagram is simulated, the water and soil conservation simulation diagram can correspond to the image to be analyzed, and a water and soil detection result can be obtained more quickly and accurately in a picture comparison mode, so that the efficiency of analyzing the water and soil detection result is improved;
4. through setting up corresponding detection weight, through the circulation detection quantity that this detection weight set up correspondence, can set up the work load of corresponding detection according to the condition of soil erosion and water loss to detection efficiency has been promoted.
Drawings
FIG. 1 is a flow chart of a soil and water conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification in an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an implementation of step S10 in the method for monitoring soil and water conservation based on unmanned aerial vehicle remote sensing and object-oriented classification according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an implementation of step S20 in the method for monitoring soil and water conservation based on unmanned aerial vehicle remote sensing and object-oriented classification according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating an implementation of step S40 in the method for monitoring soil and water conservation based on UAV remote sensing and object-oriented classification according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating the implementation of step S42 in the method for monitoring soil and water conservation based on UAV remote sensing and object-oriented classification according to an embodiment of the present invention;
fig. 6 is a schematic block diagram of a soil and water conservation monitoring device based on unmanned aerial vehicle remote sensing and object-oriented classification according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in an embodiment, as shown in fig. 1, the invention discloses a water and soil conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification, which specifically comprises the following steps:
s10: and obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed.
In this embodiment, the historical water and soil detection image refers to an area where the water and soil conservation needs to be detected by using the unmanned aerial vehicle remote sensing technology at the last time. The image to be analyzed is an image which needs to be analyzed for water and soil conservation and water and soil loss.
Specifically, after the area needing to be detected for the soil and water conservation condition is detected by adopting the unmanned aerial vehicle remote sensing technology, the historical soil and water detection image is obtained. Utensil check time measuring, can be through sending corresponding instruction to unmanned aerial vehicle terminal, set up corresponding flying height, airline and overlap ratio isoparametric, make unmanned aerial vehicle carry out the detection that soil and water kept to this region to obtain this historical survey image.
Further, a preset segmentation rule is obtained, and after the historical water and soil detection image is segmented, a plurality of images to be analyzed are obtained. The specific number of the images to be analyzed can be determined according to the size of the historical water and soil detection images and the segmentation rule.
S20: respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results.
In this embodiment, the soil and water detection result refers to a result of detecting soil and water conservation in the region represented by the image to be analyzed. The image to be decided is an image which needs to be judged whether important repeated detection is needed.
Specifically, the water and soil detection result of each image to be analyzed is obtained by detecting and analyzing the standard of the water and soil conservation degree and the corresponding image to be analyzed.
Further, the images to be analyzed are classified according to the water and soil detection result corresponding to each image to be analyzed, the specific classification standard can be that the images to be analyzed are graded according to the water and soil detection result, the graded result is graded, the graded grade is used as the classification standard, the images to be analyzed corresponding to the same grade are classified into one class, and then the corresponding images to be decided are obtained.
S30: and scoring the image to be decided according to the classification result, and marking the image to be decided corresponding to the score lower than a preset scoring threshold value to obtain key detection data.
In this embodiment, the important detection data is to determine the region of detection that needs to be repeatedly subjected to soil and water conservation again according to the score of the region corresponding to the image to be decided on in the soil and water detection result.
Specifically, a corresponding scoring criterion is set in advance, and the scoring threshold is set in the scoring criterion. Further, after the score corresponding to each type of classification result is obtained, the score is compared with the corresponding score threshold, and after the image to be decided corresponding to the score threshold is marked, the corresponding key detection data is obtained.
S40: and acquiring unmanned aerial vehicle detection information from the key detection data, and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
In this embodiment, the unmanned aerial vehicle detection information refers to the flight data when the unmanned aerial vehicle shoots and detects this important detection data when obtaining historical water and soil detection images. The soil and water conservation detection message is data used for controlling the unmanned aerial vehicle to repeatedly perform soil and water conservation detection on the area corresponding to the heavy-point detection data.
Specifically, when historical water and soil detection images are acquired through the unmanned aerial vehicle remote sensing technology, parameters of aerial photography of the unmanned aerial vehicle are acquired, and the parameters correspond to each image to be analyzed. Further, as the key detection data are obtained by classifying and marking the images to be analyzed, the corresponding unmanned aerial vehicle detection information is obtained through the incidence relation between the key detection data and the corresponding images to be analyzed.
Further, after the area corresponding to the important detection data is subjected to water and soil conservation processing, for example, soil quality improvement, green plant planting or other water and soil conservation related means are performed, the water and soil conservation detection message is triggered for detecting the improvement condition of water and soil conservation in the area.
In the embodiment, by segmenting the historical water and soil detection image, each image to be analyzed can be analyzed in a distributed and targeted manner, which is beneficial to improving the analysis efficiency and precision; classifying the images to be analyzed by using the water and soil detection result of each image to be analyzed, and correspondingly marking the images to be decided according to the classification result to obtain key detection data; through triggering the corresponding soil and water conservation detection message according to the key detection data, the key detection of the region with serious soil and water loss can be realized, so that the repeated detection of the whole soil and water conservation region is not needed, and the detection pertinence and the detection efficiency are also ensured.
In an embodiment, as shown in fig. 2, in step S10, namely acquiring a historical water and soil detection image, the historical water and soil detection image is segmented to obtain an image to be analyzed, which specifically includes the following steps:
s11: and acquiring a water and soil detection area map from the historical water and soil detection image, and acquiring area characteristic information from the water and soil detection area.
In this embodiment, the soil and water detection area map is a plan view of an area where soil and water conservation is required. The region feature information refers to a feature of a landscape of the region.
Specifically, an earth and water detection area map corresponding to the historical earth and water detection image may be acquired in the satellite map. Further, after the water and soil detection area map is acquired, the picture features of the water and soil detection area map are identified as the area feature information by a corresponding deep learning model, such as CNN, LSTM, or the like.
S12: and segmenting the historical water and soil detection image according to the regional characteristic information to obtain an image to be analyzed.
Further, the similarity comparison is carried out on the regional characteristic information, and the regional characteristic information which is the same or similar and is adjacent in position is divided into a category. When similarity is judged to be similar, a similarity threshold value is set, for example, 0.8, 0.85 or 0.9, and the regional characteristic information reaching the similarity threshold value is used as the similarity.
And further, according to the classification of the regional characteristic information, the classification is used as a segmentation rule, and the historical water and soil detection image is segmented according to the segmentation rule to obtain an image to be analyzed.
In an embodiment, as shown in fig. 3, in step S20, the method includes the following steps of respectively obtaining soil and water detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the soil and water detection results, and obtaining corresponding images to be decided according to the classification results:
s21: and acquiring corresponding detection indexes according to the image to be analyzed, and constructing a water and soil conservation simulation diagram according to the detection indexes.
In this embodiment, the detection index refers to a standard of the degree of water body retention. The water and soil conservation simulation diagram refers to a simulation diagram of the due landform of the region meeting the detection standard.
Specifically, the water and soil conservation condition standard of the region corresponding to the historical water and soil detection image is obtained, and is divided according to the standard of the image to be analyzed obtained through segmentation, so that the detection standard corresponding to each image to be analyzed is obtained.
Further, a water and soil conservation simulation diagram corresponding to each image to be analyzed is constructed through the detection standard, such as green plant coverage rate to be achieved. During construction, the water and soil detection area is used, the water and soil detection area is distinguished according to the standard of segmenting the image to be analyzed, an area base map corresponding to each image to be analyzed is obtained, and the landform condition meeting the standard is simulated in the area base map according to the detection standard and serves as a water and soil conservation model.
S22: and comparing the image to be analyzed with the corresponding water and soil conservation simulation diagram, and acquiring a corresponding water and soil detection result according to the comparison result.
Specifically, an image recognition technology is used for comparing the image to be analyzed with the water and soil conservation simulation diagram, and the comparison result is used as a corresponding water and soil detection result. Preferably, during the comparison, a key point or a key area, such as an area where green plants are mainly planted, may be selected in advance from the water and soil conservation simulation diagram, and during the comparison of the key point or the key area, a fitting value is increased according to an actual situation, that is, the influence of the similarity degree of the key point and the key area of the actual image to be analyzed and the key point and the key area of the water and soil conservation simulation diagram on the finally obtained water and soil detection result is increased, so that the water and soil detection result is more accurate.
In an embodiment, as shown in fig. 4, in step S40, the method includes the following steps:
S41: and acquiring unmanned detection coordinates and corresponding unmanned detection attitude information from the key detection data, and taking the unmanned detection coordinates and the unmanned detection attitude information as unmanned detection information.
In this embodiment, the unmanned aerial vehicle detection coordinate is the position that the unmanned aerial vehicle stops when carrying out the picture aerial photograph. The unmanned aerial vehicle detection attitude information refers to information of an inclination angle when the unmanned aerial vehicle carries out aerial photography.
Specifically, the position information of the unmanned aerial vehicle staying when shooting the image to be analyzed corresponding to the key detection data is obtained from the key detection data, wherein the position information is expressed by longitude and latitude coordinates and serves as the unmanned aerial vehicle detection coordinates. And the information of the inclination angle when shooting the key detection area data is obtained from the storage terminal of the unmanned aerial vehicle and is used as the unmanned aerial vehicle detection attitude information.
And further, the obtained unmanned aerial vehicle detection coordinates and unmanned aerial vehicle detection attitude information are used as unmanned aerial vehicle detection information.
S42: and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information.
Specifically, according to unmanned aerial vehicle detection coordinate and unmanned aerial vehicle detection gesture information, trigger soil and water conservation and detect the message, make unmanned aerial vehicle when detecting key detection data again, use the same position and gesture to shoot to guarantee the degree of accuracy of the result that redetects and obtain.
In an embodiment, as shown in fig. 5, in step S42, triggering the soil and water conservation detection message according to the detected coordinates of the drone and the detected attitude information of the drone includes the following steps:
s421: and setting corresponding detection weights for the gravity detection data according to the scores, and setting the number of cyclic detections according to the detection weights.
In this embodiment, the detection weight refers to the severity of soil erosion in the region corresponding to the important detection data. The cycle detection number refers to the number of repeated detections required for the repetitive detection data.
Specifically, the detection weight is set according to the score of the highlight detection data, so that the lower the score of the highlight detection data is, the higher the corresponding detection weight is.
Further, the detection weight with the lowest value is obtained, the number of the cyclic detection of the detection weight is set according to the actual situation, and the number of the cyclic detection corresponding to each key detection data is calculated according to the ratio of the detection weight between each key detection data.
S422: and detecting the repeated point detection data according to the cycle detection number.
Specifically, each important detection data is detected according to the number of cyclic detections of each important detection data, wherein each time of detection, a time threshold is preset, for example, 7 days, 10 days, 14 days, and the like, and every interval of the time threshold, the area corresponding to the number of important detections is detected.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two:
in an embodiment, a water and soil conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification is provided, and the water and soil conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification corresponds to the water and soil conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification in the above embodiments one to one. As shown in fig. 6, the water and soil conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification comprises an image segmentation module 10, an image classification module 20, a marking module 30 and a circulation detection module 40. The functional modules are explained in detail as follows:
the image segmentation module 10 is configured to obtain a historical water and soil detection image, and segment the historical water and soil detection image to obtain an image to be analyzed;
the image classification module 20 is configured to obtain water and soil detection results corresponding to the images to be analyzed, classify the images to be analyzed according to the water and soil detection results, and obtain corresponding images to be decided according to the classification results;
The marking module 30 is configured to score the image to be decided according to the classification result, and mark the image to be decided corresponding to the score lower than a preset score threshold to obtain key detection data;
and the circulation detection module 40 is used for acquiring unmanned aerial vehicle detection information from the key detection data and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
Preferably, the image segmentation module 10 comprises:
the characteristic obtaining submodule 11 is used for obtaining a water and soil detection area map from the historical water and soil detection image and obtaining area characteristic information from the water and soil detection area;
and the image segmentation submodule 12 is used for segmenting the historical water and soil detection image according to the regional characteristic information to obtain an image to be analyzed.
Preferably, the image classification module 20 comprises:
the simulation diagram construction sub-module 21 is configured to obtain a corresponding detection index according to the image to be analyzed, and construct a water and soil conservation simulation diagram according to the detection index;
and the detection submodule 22 is used for comparing the image to be analyzed with the corresponding water and soil conservation simulation diagram and acquiring a corresponding water and soil detection result according to the comparison result.
Preferably, the loop detection module 40 includes:
the parameter obtaining submodule 41 is configured to obtain an unmanned aerial vehicle detection coordinate and corresponding unmanned aerial vehicle detection attitude information from the key detection data, and use the unmanned aerial vehicle detection coordinate and the unmanned aerial vehicle detection attitude information as unmanned aerial vehicle detection information;
And the cyclic detection submodule 42 is used for triggering the soil and water conservation detection message according to the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information.
Preferably, the cycle detection sub-module 42 includes:
a number setting unit 421, configured to set a corresponding detection weight for the counterweight detection data according to the score, and set a number of cyclic detections according to the detection weight;
and a cycle detection unit 422, configured to detect the midpoint detection data according to the cycle detection number.
For specific limitations of the water and soil conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification, reference may be made to the above limitations on the water and soil conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification, which are not described herein again. All modules in the water and soil conservation monitoring system based on unmanned aerial vehicle remote sensing and object-oriented classification can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Claims (10)
1. A water and soil conservation monitoring method based on unmanned aerial vehicle remote sensing and object-oriented classification is characterized by comprising the following steps:
S10: obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed;
s20: respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results;
s30: scoring the image to be decided according to the classification result, and marking the image to be decided corresponding to the score lower than a preset scoring threshold value to obtain key detection data;
s40: and acquiring unmanned aerial vehicle detection information from the key detection data, and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
2. The method for soil and water conservation monitoring based on unmanned aerial vehicle remote sensing and object-oriented classification as claimed in claim 1, wherein step S10 includes:
s11: acquiring a water and soil detection area map from the historical water and soil detection image, and acquiring area characteristic information from the water and soil detection area;
s12: and segmenting the historical water and soil detection image according to the regional characteristic information to obtain the image to be analyzed.
3. The method for soil and water conservation monitoring based on unmanned aerial vehicle remote sensing and object-oriented classification as claimed in claim 1, wherein step S20 includes:
S21: acquiring a corresponding detection index according to the image to be analyzed, and constructing a water and soil conservation simulation diagram according to the detection index;
s22: and comparing the image to be analyzed with the corresponding water and soil conservation simulation diagram, and acquiring a corresponding water and soil detection result according to the comparison result.
4. The method for soil and water conservation monitoring based on unmanned aerial vehicle remote sensing and object-oriented classification as claimed in claim 1, wherein step S40 includes:
s41: acquiring unmanned aerial vehicle detection coordinates and corresponding unmanned aerial vehicle detection attitude information from the key detection data, and taking the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information as unmanned aerial vehicle detection information;
s42: and triggering the soil and water conservation detection message according to the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information.
5. The method for soil and water conservation monitoring based on unmanned aerial vehicle remote sensing and object-oriented classification as claimed in claim 4, wherein step S42 includes:
s421: setting corresponding detection weights for the key detection data according to the scores, and setting the number of cyclic detections according to the detection weights;
s422: and detecting the key detection data according to the cyclic detection number.
6. The utility model provides a soil and water conservation monitoring system based on unmanned aerial vehicle remote sensing and object oriented classification which characterized in that, soil and water conservation monitoring system based on unmanned aerial vehicle remote sensing and object oriented classification includes:
the image segmentation module is used for obtaining a historical water and soil detection image, and segmenting the historical water and soil detection image to obtain an image to be analyzed;
the image classification module is used for respectively obtaining water and soil detection results corresponding to the images to be analyzed, classifying the images to be analyzed according to the water and soil detection results, and obtaining corresponding images to be decided according to the classification results;
the marking module is used for scoring the image to be decided according to the classification result, marking the image to be decided corresponding to the score lower than a preset scoring threshold value, and obtaining key detection data;
and the circulating detection module is used for acquiring unmanned aerial vehicle detection information from the key detection data and triggering a soil and water conservation detection message according to the unmanned aerial vehicle detection information.
7. The system of claim 6, wherein the image segmentation module comprises:
The characteristic acquisition submodule is used for acquiring a water and soil detection area map from the historical water and soil detection image and acquiring area characteristic information from the water and soil detection area;
and the image segmentation submodule is used for segmenting the historical water and soil detection image according to the regional characteristic information to obtain the image to be analyzed.
8. The system of claim 6, wherein the image classification module comprises:
the simulation diagram construction sub-module is used for acquiring corresponding detection indexes according to the image to be analyzed and constructing a water and soil conservation simulation diagram according to the detection indexes;
and the detection submodule is used for comparing the image to be analyzed with the corresponding water and soil conservation simulation diagram and acquiring a corresponding water and soil detection result according to the comparison result.
9. The system of claim 6, wherein the cycle detection module comprises:
the parameter acquisition submodule is used for acquiring unmanned aerial vehicle detection coordinates and corresponding unmanned aerial vehicle detection attitude information from the key detection data, and taking the unmanned aerial vehicle detection coordinates and the unmanned aerial vehicle detection attitude information as the unmanned aerial vehicle detection information;
And the cyclic detection submodule is used for triggering the soil and water conservation detection message according to the unmanned aerial vehicle detection coordinate and the unmanned aerial vehicle detection attitude information.
10. The system of claim 6, wherein the cyclic detection sub-module comprises:
the quantity setting unit is used for setting corresponding detection weights for the key detection data according to the scores and setting the quantity of the cyclic detection according to the detection weights;
and the cycle detection unit is used for detecting the key detection data according to the cycle detection number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010637419.3A CN111860626B (en) | 2020-07-04 | 2020-07-04 | Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010637419.3A CN111860626B (en) | 2020-07-04 | 2020-07-04 | Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111860626A true CN111860626A (en) | 2020-10-30 |
| CN111860626B CN111860626B (en) | 2023-08-29 |
Family
ID=73153074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010637419.3A Active CN111860626B (en) | 2020-07-04 | 2020-07-04 | Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860626B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949420A (en) * | 2021-02-07 | 2021-06-11 | 湖北君邦环境技术有限责任公司 | Water and soil conservation monitoring method, device and system and readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105464038A (en) * | 2015-11-13 | 2016-04-06 | 杭州大地科技有限公司 | Review investigation method for water and soil loss distribution |
| KR101744662B1 (en) * | 2016-11-30 | 2017-06-09 | 주식회사 지오스토리 | System for classifying halophytes using hyper-spectral imaging |
| CN107844802A (en) * | 2017-10-19 | 2018-03-27 | 中国电建集团成都勘测设计研究院有限公司 | Water and soil conservation value method based on unmanned plane low-altitude remote sensing and object oriented classification |
| CN109187712A (en) * | 2018-09-27 | 2019-01-11 | 南京天博环境检测技术有限公司 | A kind of method that fullerene in atmosphere is observed by Mobile Online |
| CN109684929A (en) * | 2018-11-23 | 2019-04-26 | 中国电建集团成都勘测设计研究院有限公司 | Terrestrial plant ECOLOGICAL ENVIRONMENTAL MONITORING method based on multi-sources RS data fusion |
| CN110309933A (en) * | 2018-03-23 | 2019-10-08 | 广州极飞科技有限公司 | Plant plants data measuring method, work route method and device for planning, system |
| CN110806230A (en) * | 2018-08-06 | 2020-02-18 | 海鹰航空通用装备有限责任公司 | Ecological environment monitoring method based on unmanned aerial vehicle |
| KR20200056068A (en) * | 2018-11-14 | 2020-05-22 | 이병섭 | System for tracking an object in unmanned aerial vehicle based on mvs |
-
2020
- 2020-07-04 CN CN202010637419.3A patent/CN111860626B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105464038A (en) * | 2015-11-13 | 2016-04-06 | 杭州大地科技有限公司 | Review investigation method for water and soil loss distribution |
| KR101744662B1 (en) * | 2016-11-30 | 2017-06-09 | 주식회사 지오스토리 | System for classifying halophytes using hyper-spectral imaging |
| CN107844802A (en) * | 2017-10-19 | 2018-03-27 | 中国电建集团成都勘测设计研究院有限公司 | Water and soil conservation value method based on unmanned plane low-altitude remote sensing and object oriented classification |
| CN110309933A (en) * | 2018-03-23 | 2019-10-08 | 广州极飞科技有限公司 | Plant plants data measuring method, work route method and device for planning, system |
| CN110806230A (en) * | 2018-08-06 | 2020-02-18 | 海鹰航空通用装备有限责任公司 | Ecological environment monitoring method based on unmanned aerial vehicle |
| CN109187712A (en) * | 2018-09-27 | 2019-01-11 | 南京天博环境检测技术有限公司 | A kind of method that fullerene in atmosphere is observed by Mobile Online |
| KR20200056068A (en) * | 2018-11-14 | 2020-05-22 | 이병섭 | System for tracking an object in unmanned aerial vehicle based on mvs |
| CN109684929A (en) * | 2018-11-23 | 2019-04-26 | 中国电建集团成都勘测设计研究院有限公司 | Terrestrial plant ECOLOGICAL ENVIRONMENTAL MONITORING method based on multi-sources RS data fusion |
Non-Patent Citations (2)
| Title |
|---|
| 张雅文;许文盛;沈盛?王志刚;张平仓;: "无人机遥感技术在生产建设项目水土保持监测中的应用――方法构建", 中国水土保持科学, no. 01 * |
| 高振宇;门春春;朱玉龙;李腾锟;: "提高遥感监测工作效率的方法分析与探讨", 国土资源, no. 10 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949420A (en) * | 2021-02-07 | 2021-06-11 | 湖北君邦环境技术有限责任公司 | Water and soil conservation monitoring method, device and system and readable storage medium |
| CN112949420B (en) * | 2021-02-07 | 2022-06-14 | 湖北君邦环境技术有限责任公司 | Water and soil conservation monitoring method, device and system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111860626B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2014295972B2 (en) | System and method for detecting features in aerial images using disparity mapping and segmentation techniques | |
| Moya et al. | Detection of collapsed buildings from lidar data due to the 2016 Kumamoto earthquake in Japan | |
| KR101984259B1 (en) | Method and device for making a topographic map | |
| US20170177938A1 (en) | Automated detection of nitrogen deficiency in crop | |
| CN112818925B (en) | Urban building and crown identification method | |
| CN107092877A (en) | Remote sensing image roof contour extracting method based on basement bottom of the building vector | |
| EP3503025A1 (en) | Utilizing artificial intelligence with captured images to detect agricultural failure | |
| CN111666855B (en) | Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle and electronic equipment | |
| CN108801268A (en) | Localization method, device and the robot of target object | |
| CN109032174B (en) | Unmanned aerial vehicle operation route planning method and operation execution method | |
| CN111709988B (en) | Method and device for determining characteristic information of object, electronic equipment and storage medium | |
| CN109902018A (en) | A kind of acquisition methods of intelligent driving system test cases | |
| CN110287907A (en) | A kind of method for checking object and device | |
| KR102273063B1 (en) | System for monitoring dead tree and pest using probability map and image learning of orthoimage | |
| CN115546672A (en) | Forest picture processing method and system based on image processing | |
| KR102262382B1 (en) | large area space information system for image acquistion base Unmanned Aerial Vehicle | |
| CN112084989A (en) | Unmanned aerial vehicle and CNN-based large-range pine wood nematode withered vertical wood intelligent detection method | |
| CN111860626B (en) | Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification | |
| CN109579793B (en) | Terrain mapping method, apparatus, flight platform, computer device and storage medium | |
| CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| CN110276379A (en) | A kind of the condition of a disaster information rapid extracting method based on video image analysis | |
| CN113610009A (en) | Flood disaster unmanned aerial vehicle image information extraction system | |
| CN113378754A (en) | Construction site bare soil monitoring method | |
| Chuanxiang et al. | Automatic detection of aerial survey ground control points based on Yolov5-OBB | |
| CN115019216A (en) | Real-time ground object detection and positioning counting method, system and computer |
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 |