CN115371571A - Oat relative height estimation method and system - Google Patents
Oat relative height estimation method and system Download PDFInfo
- Publication number
- CN115371571A CN115371571A CN202210971457.1A CN202210971457A CN115371571A CN 115371571 A CN115371571 A CN 115371571A CN 202210971457 A CN202210971457 A CN 202210971457A CN 115371571 A CN115371571 A CN 115371571A
- Authority
- CN
- China
- Prior art keywords
- height
- oat
- calculated
- image
- measured
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B17/00—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations
- G01B17/02—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations for measuring thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
A method and a system for estimating the relative height of oats comprise the following steps: obtaining an original image of a region to be monitored and obtaining a measurement height by using an ultrasonic sensing measurement method; determining the accuracy of the measured height by rechecking the measured height; the rechecking comprises historical data comparison and current data comparison. According to the method, firstly, the ultrasonic sensing measurement mode is utilized, the relatively accurate measurement height can be obtained, but due to the fact that the ultrasonic sensing measurement mode and other plants can be mixed, rechecking processing is needed, historical data, namely the calculation height, which need to be passed through in the method, is obtained, and the canopy diameter which is mainly referred to by current data is rechecked, so that the accuracy of the object with the measured height is guaranteed.
Description
Technical Field
The application relates to a method and a system for estimating relative height of oat.
Background
Oat, an annual grass plant, is pleasantly cool, thermolabile and highly adaptable. The oat has high nutritive value and various utilization modes. In China, the oat planting area and the large-scale production area are also increased year by year. How to obtain the large-scale oat yield in time and the growth are of great importance to the development of animal husbandry. At present, the commonly used crop growth monitoring methods mainly include an artificial observation method, a machine vision and digital image processing method, a remote sensing monitoring method and the like. In the remote sensing monitoring method, the unmanned aerial vehicle is used as an important component of high-resolution remote sensing data, the timeliness is strong, the spatial resolution is high, the data volume is large, the cloud layer interference is small, and the crop change can be monitored for a long time and the crop growth condition can be reflected. At present, the growth remote sensing system based on the unmanned aerial vehicle image technology is widely applied to crops such as wheat, rice and potatoes, but researches on oat crops are only reported, the main reasons are that the oat is difficult to identify, has small difference and is difficult to identify when interference exists, and the like, and in the oat growth process, the height of the oat can basically represent the growth stage and the growth condition of the oat, so that the monitoring on the oat is particularly important.
Disclosure of Invention
In order to solve the above problems, the present application discloses, in one aspect, a method for estimating a relative height of oats, comprising the steps of: obtaining an original image of a region to be monitored and obtaining a measurement height by using an ultrasonic sensing measurement method; checking the measured height to determine the accuracy of the measured height; the rechecking comprises historical data comparison and current data comparison. According to the method, firstly, the ultrasonic sensing measurement mode is utilized, the relatively accurate measurement height can be obtained, but due to the fact that the ultrasonic sensing measurement mode and other plants can be mixed, rechecking processing needs to be carried out, historical data, namely the calculation height, which need to be passed through in the method, are calculated, and the canopy diameter which is mainly indicated by current data is rechecked, so that the accuracy of a height measurement object is guaranteed.
Preferably, the historical data is compared with a calculated height, and the calculated height is obtained as follows:
establishing different construction growth algorithms based on regions, wherein the growth algorithms are obtained according to the following modes: by setting the designated flight height of the monitoring unmanned aerial vehicle, regular oat growth is tracked from the beginning of sowing; calculating historical data of the growth speed of the regional target plants through the time difference of the growth tracking so as to obtain a growth algorithm based on the region;
and calculating to obtain the calculated height of the oat in the area to be monitored according to a growth algorithm, expanding the calculated height to obtain a height threshold value, and if the measured height is not within the height threshold value, excluding the oat plant. The calculation height is obtained through historical data, the calculation height is actually historical data, the data is obtained through tracing by regions, time and the like, and then the data is used as a judgment reference to avoid misidentification as much as possible.
Preferably, the specified flying height is 100m.
Preferably, the height threshold is between 0.5 times the calculated height and 1.5 times the calculated height.
Preferably, the method further comprises the following optimization processing for the region:
processing image data of an original image to obtain a DSM image;
judging the area where the oats are located according to the vegetation index, and extracting the area where the oats are located in the DSM image to obtain a primary identification image;
obtaining the oat measurement height in a determined area in the primary identification image in an ultrasonic sensing measurement mode, and measuring and calculating the oat height by taking the measurement height as a base value;
and performing re-screening on the primarily recognized image, wherein the calculated height combined with the regional information is combined with the primarily recognized image synchronously generated after the unmanned aerial vehicle processes, the oat range calculated in each region is used as a search window, the corresponding position of the oat range in the primarily recognized image is searched, then a pixel is expanded outwards to form a new calculation window, region-by-region comparison is performed according to the mode, the land utilization type survey data, the calculated heights of the image and the oat are utilized, re-screening is performed on the corrected recognized image, and the position of the oat is finally determined to obtain the optimized image.
Preferably, the original image and the ultrasonic sensing measurement are all realized by unmanned aerial vehicle measurement: oat height acquisition is carried out through unmanned aerial vehicle's ultrasonic sensor and is measured the height.
Preferably, the status data comparison further includes a calculated height, the calculated height performs preliminary identification on the oats according to the canopy diameter of the oats obtained by the preliminary identification image and obtains the calculated height according to the canopy height, the calculated height is highly matched with the measured height of the oats, and if the calculated height is within a set range, the plant corresponding to the canopy is set as one of the oats. According to the method and the device, the diameter of the canopy is used as a judgment basis, and the height is calculated in an auxiliary manner, so that whether the canopy is the canopy or not can be judged more accurately, the accuracy of plant identification is improved, and the error of plant number identification is avoided as much as possible.
Preferably, the height matching firstly expands the estimated height to obtain an estimated range, the estimated range is 0.7 times of the estimated height to 1.3 times of the estimated height, and then whether the measured height is within the estimated range is verified.
Preferably, a distribution map of oat plants is drawn according to the identification result of the canopy, the number of plants in a set unit range is calculated, and statistical data of the relative height of the oat is obtained through statistics.
On the other hand, the application also discloses an oat relative height estimation system, which comprises the following modules:
the measuring module is used for obtaining an original image of an area to be monitored and obtaining a measuring height by using an ultrasonic sensing measuring method;
the rechecking module is used for rechecking the measured height to determine the accuracy of the measured height; the rechecking comprises historical data comparison and current data comparison.
The application has the following advantages: according to the method, firstly, the ultrasonic sensing measurement mode is utilized, the relatively accurate measurement height can be obtained, but due to the fact that the ultrasonic sensing measurement mode and other plants can be mixed, rechecking processing is needed, historical data, namely the calculation height, which need to be passed through in the method, is obtained, and the canopy diameter which is mainly referred to by current data is rechecked, so that the accuracy of the object with the measured height is guaranteed.
Detailed Description
In order to clearly illustrate the technical features of the present solution, the present application will be explained in detail through the following embodiments.
In a first embodiment, a method for estimating relative oat height comprises the steps of:
s101, obtaining an original image of an area to be monitored through an unmanned aerial vehicle;
the experiment is carried out by image and data acquisition by the RTK + image control technology in the Xinjiang province; firstly, performing linear scanning on ground conditions by using RTK (real-time kinematic), then pouring materials into a server for rendering and generating, and finally obtaining a high-precision three-dimensional oat image.
S102, processing image data of the original image to obtain a DSM image;
the unmanned aerial vehicle image is used for processing two image data, namely a visible light image provided by a common digital camera and a multispectral image provided by a RedEdge camera, so that a DSM image is obtained.
S103, judging the area where the oats are located according to the vegetation index, and extracting the area where the oats are located in the DSM image to obtain a primary identification image;
in the image processing process, vegetation indexes are mainly used for extracting vegetation areas, and non-oat planting areas are set as backgrounds, so that the influence of the non-oat planting areas on oat plant identification is eliminated. And taking the vegetation index image of the non-vegetation area eliminated as an input image, obtaining an initially identified oat plant image by utilizing a Count Crops tool of ENVI5.5 software, and carrying out secondary or multiple processing on a generated result, so that the identification precision of the oat is improved, and the initially identified image is obtained.
S104, obtaining oat measurement height in the preliminary identification image in an unmanned aerial vehicle ultrasonic sensing measurement mode, and measuring the oat range, the oat height and the number of plants by taking the measurement height as a base value:
s1041 further comprises calculating a height, the calculated height being obtained as follows:
establishing different construction growth algorithms based on regions, wherein the growth algorithms are obtained according to the following modes: setting the designated flying height of the monitoring unmanned aerial vehicle to be 100m, and carrying out regular oat growth tracking from sowing; calculating historical data of the growth speed of the regional target plants through the time difference of the growth tracking so as to obtain a region-based growth algorithm;
calculating to obtain the calculated height of the oat in the area to be monitored according to a growth algorithm, and expanding the calculated height to obtain a height threshold value, wherein the height threshold value is between 0.5 time of the calculated height and 1.5 times of the calculated height.
S1042 further includes a process of re-screening: combining the calculated height combined with the regional information with a primary recognition image synchronously generated after the unmanned aerial vehicle processes, taking an oat range calculated in each region as a search window, searching the corresponding position of the oat range in the primary recognition image, then expanding a pixel outwards to form a new calculation window, comparing the oat range by region according to the mode, re-screening the corrected recognition image by utilizing the land use type survey data and the calculated heights of the image and the oat, and finally determining the position of the oat to obtain an optimized image.
And S1043, further comprising calculating height, performing preliminary identification on the oat according to the canopy diameter (in the presence) of the oat obtained by the preliminary identification image, obtaining the calculated height according to the canopy height, performing height matching on the calculated height and the measured height of the oat, and setting the plant corresponding to the canopy as one oat if the calculated height is within a set range. The height matching firstly expands the calculated height to obtain a calculated range, wherein the calculated range is from 0.7 time of the calculated height to 1.3 times of the calculated height, and then whether the measured height is within the calculated range is verified. Through verification, the accuracy of the measurement height can be shown, a distribution diagram of the oat plants is drawn according to the identification result of the canopy, the number of the plants in a set unit range is calculated, and then a normalization coefficient of the plant distribution is obtained, wherein a Kappa coefficient is generally adopted.
If the calculation mode of calculating the height based on the height of the oat canopy is increased, under the condition of detecting the same 325 samples, the overall accuracy is improved to 98.91% from 91.46%, and the Kappa coefficient is improved to 0.982 from 0.857.
In a second embodiment, an oat relative height estimation system comprises the following modules:
the measuring module is used for obtaining an original image of a region to be monitored and obtaining a measuring height by using an ultrasonic sensing measuring method;
the rechecking module is used for rechecking the measured height so as to determine the accuracy of the measured height; the rechecking comprises historical data comparison and current data comparison.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
Claims (10)
1. An oat relative height estimation method is characterized by comprising the following steps: the method comprises the following steps:
obtaining an original image of a region to be monitored and obtaining a measurement height by using an ultrasonic sensing measurement method;
checking the measured height to determine the accuracy of the measured height;
the rechecking comprises historical data comparison and current data comparison.
2. The method for estimating relative height of oats in accordance with claim 1, wherein: the historical data is compared with a calculated height, and the calculated height is obtained according to the following mode:
establishing different construction growth algorithms based on regions, wherein the growth algorithms are obtained according to the following modes: the designated flight height of the monitoring unmanned aerial vehicle is set, and regular oat growth is tracked from sowing; calculating historical data of the growth speed of the regional target plants through the time difference of the growth tracking so as to obtain a growth algorithm based on the region;
and calculating to obtain the calculated height of the oat in the area to be monitored according to a growth algorithm, expanding the calculated height to obtain a height threshold value, and if the measured height is not within the height threshold value, excluding the oat plant.
3. The method for estimating relative height of oats as claimed in claim 2, wherein: the specified flying height is 100m.
4. The method for estimating relative height of oats as claimed in claim 2, wherein: the height threshold is between 0.5 times the calculated height and 1.5 times the calculated height.
5. The method for estimating relative oat height according to claim 1, wherein: and further comprises the optimization processing of the regions:
processing image data of the original image to obtain a DSM image;
judging the area where the oats are located according to the vegetation index, and extracting the area where the oats are located in the DSM image to obtain a primary identification image;
obtaining the oat measurement height in a determined area in the primary identification image in an ultrasonic sensing measurement mode, and measuring and calculating the oat height by taking the measurement height as a base value;
and performing re-screening on the primarily recognized image, wherein the calculated height combined with the regional information is combined with the primarily recognized image synchronously generated after the unmanned aerial vehicle processes, the oat range calculated in each region is used as a search window, the corresponding position of the oat range in the primarily recognized image is searched, then a pixel is expanded outwards to form a new calculation window, region-by-region comparison is performed according to the mode, the land utilization type survey data, the calculated heights of the image and the oat are utilized, re-screening is performed on the corrected recognized image, and the position of the oat is finally determined to obtain the optimized image.
6. The method of estimating relative oat height according to claim 5, wherein: the original image and the ultrasonic sensing measurement are all realized by unmanned aerial vehicle measurement: oat height acquisition is carried out through unmanned aerial vehicle's ultrasonic sensor and is measured the height.
7. The method for estimating relative oat height according to claim 1, wherein: the status data comparison also comprises a calculated height, the calculated height is used for carrying out preliminary identification on the oat according to the canopy diameter of the oat obtained by the preliminary identification image and obtaining the calculated height according to the canopy height, the calculated height is matched with the measured height of the oat in height, and if the calculated height is within a set range, the plant corresponding to the canopy is set as an oat.
8. The method of estimating relative oat height according to claim 7, wherein: the height matching firstly expands the calculated height to obtain a calculated range, wherein the calculated range is from 0.7 time of calculated height to 1.3 times of calculated height, and then whether the measured height is within the calculated range is verified.
9. The method of claim 8, wherein the relative height of oats is estimated by: and drawing a distribution map of the oat plants according to the identification result of the canopy, calculating the number of the plants in the set unit range, and counting to obtain statistical data of the relative heights of the oats.
10. An oat relative height estimation system, comprising: the system comprises the following modules:
the measuring module is used for obtaining an original image of a region to be monitored and obtaining a measuring height by using an ultrasonic sensing measuring method;
the rechecking module is used for rechecking the measured height to determine the accuracy of the measured height; the rechecking comprises historical data comparison and current data comparison.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210971457.1A CN115371571A (en) | 2022-08-16 | 2022-08-16 | Oat relative height estimation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210971457.1A CN115371571A (en) | 2022-08-16 | 2022-08-16 | Oat relative height estimation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115371571A true CN115371571A (en) | 2022-11-22 |
Family
ID=84065856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210971457.1A Pending CN115371571A (en) | 2022-08-16 | 2022-08-16 | Oat relative height estimation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115371571A (en) |
-
2022
- 2022-08-16 CN CN202210971457.1A patent/CN115371571A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221311B (en) | Method for automatically extracting tree height of high-canopy-closure forest stand based on TLS and UAV | |
| CN112258331B (en) | Crop planting growth and environment intelligent monitoring analysis system based on big data | |
| CN112819846B (en) | Multi-load remote sensing image-based rice yield estimation method for cloudy and rainy areas | |
| CN103186773B (en) | A kind of early stage seedling field line recognizer based on one dimension Hough conversion and expert system | |
| CN111781608A (en) | Moving target detection method and system based on FMCW laser radar | |
| Jichen et al. | Development of real-time laser-scanning system to detect tree canopy characteristics for variable-rate pesticide application | |
| Lin et al. | Automatic detection of plant rows for a transplanter in paddy field using faster r-cnn | |
| CN115731268A (en) | Unmanned aerial vehicle multi-target tracking method based on visual/millimeter wave radar information fusion | |
| CN111815717A (en) | Multi-sensor fusion external parameter combination semi-autonomous calibration method | |
| Shi et al. | Automatic corn plant location and spacing measurement using laser line-scan technique | |
| CN109978047A (en) | A kind of wheat stem tiller number extracting method | |
| CN113920106B (en) | Corn growth vigor three-dimensional reconstruction and stem thickness measurement method based on RGB-D camera | |
| CN111539473A (en) | Orchard inter-row leading line extraction method based on 3D Lidar | |
| CN108764157A (en) | Building laser footpoint extracting method and system based on normal vector Gaussian Profile | |
| CN112066977A (en) | Photoelectric measurement network multi-target matching and cataloguing method | |
| CN114694047A (en) | Corn sowing quality evaluation method and device | |
| Wu et al. | Plant 3D reconstruction based on LiDAR and multi-view sequence images | |
| CN114689038A (en) | Fruit detection positioning and orchard map construction method based on machine vision | |
| CN111340884B (en) | Dual-target positioning and identity identification method for binocular heterogeneous camera and RFID | |
| CN109960972A (en) | A kind of farm-forestry crop recognition methods based on middle high-resolution timing remotely-sensed data | |
| CN111814585A (en) | Unmanned aerial vehicle near-ground-to-air crop seedling condition remote sensing monitoring method and device and storage medium | |
| CN115371571A (en) | Oat relative height estimation method and system | |
| CN116576863A (en) | Corn data acquisition robot crop inter-row navigation path identification method, computer equipment and medium | |
| CN115359374A (en) | Oat identification method and system | |
| CN116626040A (en) | Method for detecting lesions of track and tunnel |
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 |