CN112215714A - Rice ear detection method and device based on unmanned aerial vehicle - Google Patents
Rice ear detection method and device based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN112215714A CN112215714A CN202010937248.6A CN202010937248A CN112215714A CN 112215714 A CN112215714 A CN 112215714A CN 202010937248 A CN202010937248 A CN 202010937248A CN 112215714 A CN112215714 A CN 112215714A
- Authority
- CN
- China
- Prior art keywords
- rice
- unmanned aerial
- aerial vehicle
- ear
- image
- 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
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 157
- 235000009566 rice Nutrition 0.000 title claims abstract description 157
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 156
- 238000009826 distribution Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 37
- 210000005069 ears Anatomy 0.000 claims abstract description 36
- 238000010586 diagram Methods 0.000 claims abstract description 19
- 238000009395 breeding Methods 0.000 claims abstract description 14
- 230000001488 breeding effect Effects 0.000 claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 14
- 238000009499 grossing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 230000001131 transforming effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 2
- 239000010902 straw Substances 0.000 abstract description 5
- 238000013527 convolutional neural network Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a rice ear detection method and a device based on an unmanned aerial vehicle, wherein the method comprises the following steps: extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring a rice ear image coordinate; performing coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram. According to the method, image acquisition can be realized through the light unmanned aerial vehicle, a camera of a large unmanned aerial vehicle carrying a telephoto lens is not required to be used for acquiring the image, the telephoto lens is prevented from being influenced by the shaking of the unmanned aerial vehicle during flying, and the flying efficiency is improved. In addition, when unmanned aerial vehicle flying height was lower, the wind pressure that light-duty unmanned aerial vehicle paddle produced was little, can not acutely wave the rice straw of below to can avoid the image that obtains excessively fuzzy.
Description
Technical Field
The invention relates to the technical field of crop image information, in particular to a rice ear detection method and device based on an unmanned aerial vehicle.
Background
The shape, size and color of the rice ears can be regarded as dominant expression of genes, and the number of the rice ears in a unit area is also commonly used for estimating the yield of the rice. With the development of computer digital image processing technology, the rice detection method which is recorded and automated by camera shooting is widely applied to agricultural production and phenotypic research. Most of the early studies only collected and concentrated rice images in a limited scene, and the acquisition of image data was limited to a limited and single scene. In order to get rid of the limitation of fixed shooting, the unmanned aerial vehicle is regarded as a flexible high-throughput platform for efficiently acquiring image data in a wide range. The unmanned aerial vehicle platform makes observation efficiency promote greatly with suitable image processing technique.
At present, the image acquisition is limited by the trade-off between flying height and picture resolution, and an expensive large unmanned aerial vehicle with a long-focus lens mounted camera has to be used. When the flying height of the unmanned aerial vehicle is low, although an image with high resolution can be obtained, the wind pressure generated by the blades of the large unmanned aerial vehicle can shake the rice straws below the unmanned aerial vehicle, so that the obtained image is fuzzy. After the flying height of the unmanned aerial vehicle rises, the image resolution ratio is ensured by using the lens at the telephoto end, and the image acquired by the lens at the telephoto end is easy to be affected by the shaking of the unmanned aerial vehicle during flying, so that the flying efficiency is reduced while the flying stability is ensured.
Disclosure of Invention
The embodiment of the invention provides a rice ear detection method and device based on an unmanned aerial vehicle, which are used for overcoming the defects in the prior art.
The embodiment of the invention provides a rice ear detection method based on an unmanned aerial vehicle, which comprises the following steps: according to the rice ear detection method based on the unmanned aerial vehicle, the corresponding rice ear area is extracted according to each aerial image acquired by the unmanned aerial vehicle, and the rice ear image coordinates are obtained; transforming the coordinates of the obtained rice ear images according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
According to an embodiment of the invention, the method for detecting the rice ears based on the unmanned aerial vehicle extracts the corresponding rice ear areas according to each aerial image acquired by the unmanned aerial vehicle, and comprises the following steps: inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area; the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
According to an embodiment of the invention, before performing coordinate transformation on the obtained ear images according to the pose information of each aerial image of the unmanned aerial vehicle, the method for detecting ears of rice based on the unmanned aerial vehicle further comprises: recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother; determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing; and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
According to the method for detecting the rice ears based on the unmanned aerial vehicle, after the coordinate transformation is carried out on the obtained rice ear images, the method further comprises the following steps: and (4) removing the weight of the rice ear areas of all aerial images by adopting a density clustering algorithm based on space.
According to an embodiment of the invention, the method for detecting the rice ears based on the unmanned aerial vehicle, which generates the rice ear distribution map in the world coordinate system, comprises the following steps: and transforming the detected ear region image coordinates to a horizontal axis mercator coordinate system to generate an ear distribution diagram of the geographic position.
The embodiment of the invention also provides an ear of rice detection device based on the unmanned aerial vehicle, which comprises: the detection module is used for extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle and acquiring rice ear image coordinates; the drawing and mapping module is used for carrying out coordinate transformation on the obtained rice ear images according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and the processing module is used for obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
According to the rice ear detection device based on the unmanned aerial vehicle, the detection module is specifically used for: inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area; the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
According to the rice ear detection device based on the unmanned aerial vehicle, the drawing module is further used for: recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother; determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing; and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the steps of the unmanned aerial vehicle-based rice ear detection method are realized.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for detecting ears of rice based on an unmanned aerial vehicle as described in any one of the above.
According to the method and the device for detecting the rice ears based on the unmanned aerial vehicle, the obtained rice ear areas are spliced according to the pose information of the unmanned aerial vehicle of each aerial image to generate the rice ear distribution map, the splicing after image acquisition can be realized through the light unmanned aerial vehicle, and a large unmanned aerial vehicle is not required to carry a camera of a telephoto lens to acquire the image, so that the influence of the telephoto lens on the swinging of the unmanned aerial vehicle in the flying process is avoided, and the reduction of the flying efficiency is avoided. In addition, when unmanned aerial vehicle flying height was lower, the rice straw of below can not violently be waved to the wind pressure that light-duty unmanned aerial vehicle paddle produced to the excessive image that can avoid obtaining is fuzzy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting ears of rice based on an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an unmanned aerial vehicle-based ear of rice detection device provided by an embodiment of the invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
The following describes a rice ear detection method and device based on an unmanned aerial vehicle according to an embodiment of the invention with reference to fig. 1 to 3. Fig. 1 is a schematic flow chart of a method for detecting ears of rice based on an unmanned aerial vehicle according to an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a method for detecting ears of rice based on an unmanned aerial vehicle, including:
101. and extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring the coordinates of the rice ear image.
The embodiment of the invention can be realized based on a light unmanned aerial vehicle, firstly, the unmanned aerial vehicle takes an aerial photograph of an area to be analyzed to obtain a plurality of aerial photographs which can cover the whole area to be analyzed, and simultaneously records a flight track, wherein the flight track records GPS coordinates of a camera center in the flight process and attitude information of the unmanned aerial vehicle, namely pose information of the unmanned aerial vehicle. Based on the existing image analysis method, such as a neural network, the rice ear area is extracted from each aerial image, and the coordinates of each pixel point in the area are obtained.
102. And carrying out coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system.
And obtaining the pose information of each rice ear area according to the position information and the posture information of the unmanned aerial vehicle. And performing coordinate transformation according to all the rice ear areas with known poses, and splicing the rice ear areas into a world coordinate system to generate a rice ear distribution map.
103. And obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
According to the existing breeding model, the estimated quantity of the rice ears can be obtained based on the rice ear distribution diagram, and corresponding breeding curves can be obtained according to multiple aerial photographs in different breeding periods. For example, the number of ears is 50% and 70% of the whole area according to the whole rice area and ear distribution. In this case, the yield of rice ears can be predicted before harvesting, which is generally considered as a sign of the entire entering into and leaving from ears and a sign of the entering into maturity of rice.
According to the rice ear detection method based on the unmanned aerial vehicle, the coordinate transformation is carried out on the obtained rice ear images according to the unmanned aerial vehicle position and posture information of each aerial image to generate the rice ear distribution map, the image can be processed after being collected through the light unmanned aerial vehicle, and a large unmanned aerial vehicle is not required to carry a camera of a long-focus lens to obtain the images, so that the influence of the long-focus lens on the swinging of the unmanned aerial vehicle in the flying process is avoided, and the reduction of the flying efficiency is avoided. In addition, when unmanned aerial vehicle flying height was lower, the rice straw of below can not be shaken to the wind pressure that light-duty unmanned aerial vehicle paddle produced to the image that can avoid obtaining is fuzzy.
Based on the content of the above embodiment, as an optional embodiment, the extracting, according to each aerial image acquired by the unmanned aerial vehicle, a corresponding ear region includes: inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area; the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
The rice ear detection based on deep learning uses a high-precision example segmentation network, and takes Mask R-CNN as a main detection model. The Mask R-CNN network has high-precision pixel-level segmentation capability, and the feature pyramid network and the convolutional neural network of the main part of the Mask R-CNN network perform scaling sampling on targets with different scales, so that the multi-scale of image features is ensured, and the small targets also have high detection precision. Through the tuning of network hyper-parameters and a carefully prepared data set, the trained model can detect the rice ears in an unstructured field scene, has enough generalization capability and can process rice of different varieties.
Based on the content of the foregoing embodiment, as an optional embodiment, before transforming the coordinates of the obtained ear image according to the pose information of the unmanned aerial vehicle of each aerial image, the method further includes: recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother; determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing; and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
Since the sensors typically contain noise, the flight trajectory is not smooth. A Kalman smoother based on a three-dimensional motion model is used for smoothing the flight trajectory of the unmanned aerial vehicle and filtering sensor noise existing in the trajectory. When the track is recorded, the corresponding aerial image and the corresponding timestamp information are recorded besides the pose information. And determining the pose corresponding to the aerial image according to the corresponding timestamp and the pose of the track point after calibration on the smooth flight track.
According to the rice ear detection method based on the unmanned aerial vehicle, the influence of the error of the sensor of the unmanned aerial vehicle can be avoided, and the accurate position of each aerial image can be obtained, so that the accuracy of the finally obtained rice ear distribution map is improved.
Based on the content of the foregoing embodiment, as an optional embodiment, after transforming the obtained ear image coordinates, the method further includes: and (4) removing the weight of the rice ear areas of all aerial images by adopting a density clustering algorithm based on space.
Since the aerial images for detecting and plotting the ear profiles are designed to ensure that all detection targets are contained as much as possible, the overlapping portions between the images allow the same ear to be detected multiple times and plotted in the profiles. In the subsequent treatment, a clustering algorithm DBSCAN based on spatial density distribution is adopted to remove the weight of the rice ears in the distribution map according to spatial coordinates. The rice ear area after the weight removal is used for forming a rice ear distribution diagram at the splicing position. And finally, fitting a breeding model to obtain the final rice ear number and growth change curve.
Based on the content of the foregoing embodiment, as an alternative embodiment, the generating the distribution map of the rice ears in the world coordinate system includes: and transforming the detected ear region image coordinates to a horizontal axis mercator coordinate system to generate an ear distribution diagram of the geographic position.
The embodiment of the invention provides a coordinate transformation method, which is used for transforming the detected ear image coordinates to a horizontal axis mercator coordinate system to generate an ear distribution map of a real geographic position.
The following describes the rice ear detection device based on the unmanned aerial vehicle according to the embodiment of the present invention, and the rice ear detection device based on the unmanned aerial vehicle described below and the rice ear detection method based on the unmanned aerial vehicle described above may be referred to in correspondence with each other.
Fig. 2 is a schematic structural diagram of an ear of rice detection device based on an unmanned aerial vehicle according to an embodiment of the present invention, and as shown in fig. 2, the ear of rice detection device based on an unmanned aerial vehicle includes: a detection module 201, a charting module 202 and a processing module 203. The detection module 201 is configured to extract a corresponding ear region according to each aerial image acquired by the unmanned aerial vehicle, and acquire an ear image coordinate; the drawing module 202 is used for transforming the coordinates of the obtained rice ear images according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; the processing module 203 is used for obtaining the number of the rice ears through a preset breeding model according to the rice ear distribution diagram.
Based on the content of the foregoing embodiment, as an optional embodiment, the detection module 201 is specifically configured to: inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area; the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
Based on the content of the foregoing embodiments, as an alternative embodiment, the charting module 202 is further configured to: recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother; determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing; and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
The device embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
According to the rice ear detection device based on the unmanned aerial vehicle, the obtained rice ear areas are spliced according to the unmanned aerial vehicle position and posture information of each aerial image to generate the rice ear distribution map, the splicing after image acquisition can be realized through the light unmanned aerial vehicle, and a large unmanned aerial vehicle is not required to carry a camera of a telephoto lens to acquire the image, so that the influence of the telephoto lens on the swinging of the unmanned aerial vehicle in the flying process is avoided, and the reduction of the flying efficiency is avoided. In addition, when unmanned aerial vehicle flying height was lower, the rice straw of below can not be shaken to the wind pressure that light-duty unmanned aerial vehicle paddle produced to the image that can avoid obtaining is fuzzy.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a communication bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the communication bus 304. Processor 301 may invoke logic instructions in memory 303 to perform a drone-based ear detection method comprising: extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring a rice ear image coordinate; performing coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is capable of executing the method for detecting ears of rice based on a drone provided by the above-mentioned method embodiments, where the method includes: extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring a rice ear image coordinate; performing coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
In yet another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the method for detecting ears of rice based on a drone provided in the foregoing embodiments, and the method includes: extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring a rice ear image coordinate; performing coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system; and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An unmanned aerial vehicle-based rice ear detection method is characterized by comprising the following steps:
extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle, and acquiring a rice ear image coordinate;
performing coordinate transformation on the obtained rice ear image according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system;
and obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
2. The method for detecting ears of rice based on unmanned aerial vehicle as claimed in claim 1, wherein the extracting corresponding ear of rice region according to each aerial image collected by unmanned aerial vehicle comprises:
inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area;
the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
3. The method for detecting ears of rice based on unmanned aerial vehicles according to claim 1, wherein before the coordinate transformation of the obtained ear of rice image according to the pose information of unmanned aerial vehicle of each aerial image, the method further comprises:
recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother;
determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing;
and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
4. The method for detecting ears of rice based on unmanned aerial vehicle as claimed in claim 1, further comprising, after performing coordinate transformation on the obtained ear of rice image:
and (4) removing the weight of the rice ear areas of all aerial images by adopting a density clustering algorithm based on space.
5. The method for detecting rice ears based on unmanned aerial vehicle as claimed in claim 1, wherein the generating of the rice ear distribution map in the world coordinate system comprises:
and transforming the detected ear region image coordinates to a horizontal axis mercator coordinate system to generate an ear distribution diagram of the geographic position.
6. The utility model provides an ear of rice detection device based on unmanned aerial vehicle which characterized in that includes:
the detection module is used for extracting a corresponding rice ear area according to each aerial image acquired by the unmanned aerial vehicle and acquiring rice ear image coordinates;
the drawing module is used for carrying out coordinate transformation on the obtained rice ear images according to the unmanned aerial vehicle pose information of each aerial image to generate a rice ear distribution map in a world coordinate system;
and the processing module is used for obtaining the quantity of the rice ears through a preset breeding model according to the rice ear distribution diagram.
7. The unmanned aerial vehicle-based ear of rice detection device of claim 6, wherein the detection module is specifically configured to:
inputting an aerial image acquired by an unmanned aerial vehicle into a preset Mask R-CNN network model to obtain a corresponding rice ear area;
the Mask R-CNN network model is obtained by training according to a sample aerial image with a rice ear area label.
8. The unmanned aerial vehicle-based ear of rice detection device of claim 6, wherein the mapping module is further configured to:
recording timestamp information of each track point, and smoothing the flight track of the unmanned aerial vehicle by adopting a Kalman smoother;
determining track points after calibration in the track after smoothing according to the time stamps corresponding to the track points before smoothing;
and determining the pose corresponding to the aerial image according to the pose of the calibrated track point.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method for detecting ears of rice based on unmanned aerial vehicle as claimed in one of claims 1 to 5.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for detecting ears of rice based on drone according to one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010937248.6A CN112215714B (en) | 2020-09-08 | 2020-09-08 | Unmanned aerial vehicle-based rice spike detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010937248.6A CN112215714B (en) | 2020-09-08 | 2020-09-08 | Unmanned aerial vehicle-based rice spike detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112215714A true CN112215714A (en) | 2021-01-12 |
| CN112215714B CN112215714B (en) | 2024-05-10 |
Family
ID=74049247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010937248.6A Active CN112215714B (en) | 2020-09-08 | 2020-09-08 | Unmanned aerial vehicle-based rice spike detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215714B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742204A (en) * | 2022-04-08 | 2022-07-12 | 黑龙江惠达科技发展有限公司 | Method and device for detecting straw coverage rate |
| WO2022252366A1 (en) * | 2021-06-02 | 2022-12-08 | 中国科学院分子植物科学卓越创新中心 | Processing method and apparatus for whole-spike image |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832655A (en) * | 2017-02-21 | 2018-03-23 | 石河子大学 | A kind of take photo by plane system and output of cotton estimating and measuring method based on unmanned plane imaging near the ground |
| KR20180096966A (en) * | 2017-02-22 | 2018-08-30 | 전남대학교산학협력단 | Automatic Counting Method of Rice Plant by Centroid of Closed Rice Plant Contour Image |
| CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
| CN110047142A (en) * | 2019-03-19 | 2019-07-23 | 中国科学院深圳先进技术研究院 | No-manned plane three-dimensional map constructing method, device, computer equipment and storage medium |
| US20190228225A1 (en) * | 2018-01-23 | 2019-07-25 | X Development Llc | Crop boundary detection in images |
| CN110222903A (en) * | 2019-06-13 | 2019-09-10 | 苏州市农业科学院 | A kind of Rice Yield Prediction method and system based on unmanned aerial vehicle remote sensing |
| CN110751099A (en) * | 2019-10-22 | 2020-02-04 | 东南大学 | Unmanned aerial vehicle aerial video track high-precision extraction method based on deep learning |
| CN110766690A (en) * | 2019-11-07 | 2020-02-07 | 四川农业大学 | Wheat ear detection and counting method based on deep learning point supervision thought |
| CN110991297A (en) * | 2019-11-26 | 2020-04-10 | 中国科学院光电研究院 | Target positioning method and system based on scene monitoring |
| CN111241939A (en) * | 2019-12-31 | 2020-06-05 | 沈阳农业大学 | Rice yield estimation method based on unmanned aerial vehicle digital image |
| CN111582234A (en) * | 2020-05-22 | 2020-08-25 | 莫登奎 | UAV and deep learning-based large-range oil tea forest fruit intelligent detection and counting method |
-
2020
- 2020-09-08 CN CN202010937248.6A patent/CN112215714B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832655A (en) * | 2017-02-21 | 2018-03-23 | 石河子大学 | A kind of take photo by plane system and output of cotton estimating and measuring method based on unmanned plane imaging near the ground |
| KR20180096966A (en) * | 2017-02-22 | 2018-08-30 | 전남대학교산학협력단 | Automatic Counting Method of Rice Plant by Centroid of Closed Rice Plant Contour Image |
| US20190228225A1 (en) * | 2018-01-23 | 2019-07-25 | X Development Llc | Crop boundary detection in images |
| CN110047142A (en) * | 2019-03-19 | 2019-07-23 | 中国科学院深圳先进技术研究院 | No-manned plane three-dimensional map constructing method, device, computer equipment and storage medium |
| CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
| CN110222903A (en) * | 2019-06-13 | 2019-09-10 | 苏州市农业科学院 | A kind of Rice Yield Prediction method and system based on unmanned aerial vehicle remote sensing |
| CN110751099A (en) * | 2019-10-22 | 2020-02-04 | 东南大学 | Unmanned aerial vehicle aerial video track high-precision extraction method based on deep learning |
| CN110766690A (en) * | 2019-11-07 | 2020-02-07 | 四川农业大学 | Wheat ear detection and counting method based on deep learning point supervision thought |
| CN110991297A (en) * | 2019-11-26 | 2020-04-10 | 中国科学院光电研究院 | Target positioning method and system based on scene monitoring |
| CN111241939A (en) * | 2019-12-31 | 2020-06-05 | 沈阳农业大学 | Rice yield estimation method based on unmanned aerial vehicle digital image |
| CN111582234A (en) * | 2020-05-22 | 2020-08-25 | 莫登奎 | UAV and deep learning-based large-range oil tea forest fruit intelligent detection and counting method |
Non-Patent Citations (1)
| Title |
|---|
| 李昂;王洋;曹英丽;于丰华;许童羽;肖文;: "基于无人机高清数码影像的水稻产量估算", 沈阳农业大学学报, no. 05 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022252366A1 (en) * | 2021-06-02 | 2022-12-08 | 中国科学院分子植物科学卓越创新中心 | Processing method and apparatus for whole-spike image |
| CN114742204A (en) * | 2022-04-08 | 2022-07-12 | 黑龙江惠达科技发展有限公司 | Method and device for detecting straw coverage rate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112215714B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Strawberry yield prediction based on a deep neural network using high-resolution aerial orthoimages | |
| CN104766058B (en) | A kind of method and apparatus for obtaining lane line | |
| EP3125151A2 (en) | Inventory, growth, and risk prediction using image processing | |
| CN111666855B (en) | Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle and electronic equipment | |
| CN107918776B (en) | Land planning method and system based on machine vision and electronic equipment | |
| CN108898065B (en) | Deep network ship target detection method with candidate area rapid screening and scale self-adaption | |
| CN111553200A (en) | Image detection and identification method and device | |
| CN110110797B (en) | Water surface target training set automatic acquisition method based on multi-sensor fusion | |
| CN112215714B (en) | Unmanned aerial vehicle-based rice spike detection method and device | |
| CN113743385A (en) | Unmanned ship water surface target detection method and device and unmanned ship | |
| CN112184734A (en) | Long-time animal posture recognition system based on infrared images and wearable optical fibers | |
| CN115908268A (en) | Method and device for measuring biomass of underwater fish body in real time | |
| CN114119574A (en) | Picking point detection model construction method and picking point positioning method based on machine vision | |
| CN115578423A (en) | Fish key point detection, individual tracking and biomass estimation method and system based on deep learning | |
| CN117593766B (en) | Investigation method for wild animal population number based on unmanned aerial vehicle shooting image processing | |
| Xiang et al. | Measuring stem diameter of sorghum plants in the field using a high-throughput stereo vision system | |
| CN110163103A (en) | A kind of live pig Activity recognition method and apparatus based on video image | |
| CN116580310B (en) | Crop growth condition monitoring method based on image recognition | |
| CN116486290B (en) | Unmanned aerial vehicle monitoring and tracking method and device, electronic equipment and storage medium | |
| CN112417378A (en) | Eriocheir sinensis quality estimation method based on unmanned aerial vehicle image processing | |
| CN116739739A (en) | Loan amount evaluation method and device, electronic equipment and storage medium | |
| CN115294562B (en) | Intelligent sensing method for operation environment of plant protection robot | |
| WO2022061496A1 (en) | Object boundary extraction method and apparatus, mobile platform and storage medium | |
| CN115236643A (en) | Sensor calibration method, system, device, electronic equipment and medium | |
| CN114140428A (en) | Method and system for detecting and identifying larch caterpillars based on YOLOv5 |
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 |