CN113643231A - Crop emergence quality detection method based on depth image - Google Patents
Crop emergence quality detection method based on depth image Download PDFInfo
- Publication number
- CN113643231A CN113643231A CN202110705485.4A CN202110705485A CN113643231A CN 113643231 A CN113643231 A CN 113643231A CN 202110705485 A CN202110705485 A CN 202110705485A CN 113643231 A CN113643231 A CN 113643231A
- Authority
- CN
- China
- Prior art keywords
- crop
- image
- row
- point
- taking
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000009825 accumulation Methods 0.000 claims abstract description 11
- 238000009826 distribution Methods 0.000 claims description 11
- 238000009331 sowing Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000012010 growth Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000010899 nucleation Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 244000038559 crop plants Species 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000003102 growth factor Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of agricultural plant protection detection, and particularly relates to a crop emergence quality detection method based on a depth image. The method comprises the steps of obtaining a depth image through a depth camera, processing the depth image to obtain an elevation image, further obtaining a crop row, fitting the crop row to obtain an accurate crop row inclination angle, intercepting a local image on the basis of the crop row, conducting transverse one-dimensional accumulation and projection on the local image of the crop row to obtain a crop row height characteristic step-by-step curve, and further obtaining the crop height of the crop row; and then the positions on the rows of the crops are mapped into the original image to obtain the coordinates of each crop in the crops, so that the row spacing, the seed spacing and the seeding uniformity of seeding can be judged, and the seeding condition can be evaluated.
Description
Technical Field
The invention belongs to the technical field of agricultural plant protection detection, and particularly relates to a crop emergence quality detection method based on a depth image.
Background
At present, agricultural production gradually realizes the precision and the intellectuality, and the agricultural production gradually moves towards the robotized development, and the machine operation can effectively reduce the production cost and improve the operating efficiency of farmland when replacing people to participate in agricultural labor. And the sowing quality of the machine is detected, and the guarantee of the sowing quality of the crops has important significance for guaranteeing the yield of the crops. The rapid detection of the seedling position information by using a computer technology is one of important research directions of field precision agriculture.
Traditional seedling position detection mainly takes visual evaluation as the main thing, and this method mainly relies on artifical visual, needs the measurement personnel to visualize line by line when implementing, and not only detection efficiency is low, hinders in addition that the human eye discernment often has the deviation of certain degree, and detection accuracy is not high, is difficult to realize complete detection to great landmass. The computer vision measuring method based on the visible light image introduces machine vision, has the advantages of high efficiency and high precision, but has less information amount and only comprises two-dimensional information such as crop positions, canopy diameters and the like. In addition, the method is based on the object identification of the two-dimensional image, and has great difficulty in the field crop environment due to the differentiation and complexity of the field topography and the environment.
Disclosure of Invention
Aiming at the defects and problems that a computer vision measuring method based on a visible light image has small information amount and has higher operation difficulty in a field crop environment, the invention provides a crop emergence quality detection method based on a depth image.
The technical scheme adopted by the invention for solving the technical problems is as follows: a crop emergence quality detection method based on a depth image comprises the following steps:
step one, acquiring a crop elevation image
1. Installing a depth camera above the crop canopy in a vertical overlook mode within the effective range of the depth camera, and acquiring a depth image through the depth camera;
2. carrying out median filtering on the depth image to eliminate image holes;
3. reading the maximum gray scale in the image with the holes eliminated, and taking the maximum gray scale as the maximum depth value D of the imagemax；
4. Subtracting D from each pixel gray level in the depth imagemaxTranslating the coordinate origin of the depth image from the camera position to the deepest part of the image along the Z-axis direction, then taking a negative value for the gray level of the image, and reversing the Z axis to obtain an elevation image;
step two, fitting the row positions of the crops
1. Filtering a curve of each image line in the elevation image, eliminating noise and simultaneously keeping the curve shape;
2. acquiring a maximum value point of each image line as a characteristic point, and drawing the maximum value point on a blank image with the same size of an original image, so that only one characteristic point is reserved on each image line of each crop line to obtain a characteristic point image;
3. performing transverse one-dimensional accumulation and projection on the characteristic point image to obtain a characteristic one-dimensional curve;
4. taking the mode of the characteristic one-dimensional curve as the number of crop rows contained in the image;
5. selecting a central point at the position close to the center of each crop row to perform slope search to obtain an accurate inclination angle;
6. intercepting a local image through an accurate inclination angle obtained through multiple iterations and a corresponding central point thereof, and performing least square straight line fitting on characteristic points in the local image to obtain an optimal point inclination type of a crop row;
step three, acquiring the position and height of the crop on the row
1. Determining the height h and the width w based on the optimal point slope of the crop row, and carrying out screenshot on the original depth image according to the height h and the width w to obtain a local image of the crop row;
h＝H
in the formula: h is the original depth image height;
2. performing transverse one-dimensional accumulation and projection on the local images of the crop rows to obtain a crop row height characteristic distribution curve;
3. acquiring a maximum value point in an elevation characteristic distribution curve, taking the abscissa of the maximum value point as a crop position, and taking the ordinate of the maximum value point as a crop height;
step four, mapping the position of the crop row to the original image
The crop is arranged on the crop row, and the central point O (x) of the crop row iso,yo) The distance of the point is L pixels, the actual coordinate P (x, y) of the crop is obtained by calculation according to the inclination angle alpha of the crop row vertical to the direction, the coordinate of each crop is marked on the original image, the coordinate of the crop is obtained by calculation,
x＝x0+L×sinα
y＝y0+L×cosα；
step five, evaluating the seedling emergence quality of crops
Calculating to obtain the seedling spacing according to the crop coordinates, and judging the sowing uniformity and the miss-sowing condition; and calculating the row spacing, the uniformity among rows, whether the crop rows are parallel or whether a single crop row is straight and the characteristic distribution of the height of the crop according to the fitting result of the crop rows, and evaluating the growth condition of the crop seedlings.
The crop emergence quality detection method based on the depth image comprises the following steps of selecting a central point at a position close to the center of each crop row for slope search:
(1) determining an iteration angle corresponding to the iteration times by taking the central point as an origin, taking a half of the distance between two adjacent central points as a width, taking the number of pixels in the image column as a height, taking the step number, the iteration times and the precision, and sequentially intercepting local images with different lengths and different directions and consistent sizes by taking the iteration angle as a rotation angle step length and taking the vertical direction as a rotation starting point;
(2) respectively carrying out longitudinal one-dimensional accumulation and projection on the local images, and taking extreme points of the local images;
(3) for the local images intercepted from the same central point, the rotation angle corresponding to the local image with the maximum extreme point is the inclination angle of the crop row where the central point is located;
(4) and (4) reducing the step length of the rotation angle by taking the inclination angle obtained in the step (3) as a reference, and repeating the steps (1) - (3) for multiple times to obtain the accurate inclination angle.
The invention has the beneficial effects that: the method comprises the steps of obtaining a depth image by using a depth image through a depth camera, processing the depth image to obtain an elevation image, further obtaining a crop row, fitting the crop row to obtain an accurate crop row inclination angle, intercepting a local image on the basis of the crop row, performing transverse one-dimensional accumulation and projection on the local image of the crop row to obtain a crop row height characteristic step-by-step curve, and further obtaining the crop height of the crop row; and then the positions on the rows of the crops are mapped into the original image to obtain the coordinates of each crop in the crops, so that the row spacing, the seed spacing and the seeding uniformity of seeding can be judged, and the seeding condition can be evaluated. According to the method, the field crop distribution can be quickly and simply obtained according to the convexity displayed by the depth image, the height distribution characteristics of the crop seedlings are obtained, the position and the height of the crop can be accurately detected, and a more diversified data basis is provided for evaluation.
Drawings
FIG. 1 is a graph of the elevation profile before and after smoothing.
FIG. 2 shows the effect of the present invention on the simulation of the rows and the detection of the positions of the crops.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
Example 1: the embodiment provides a crop emergence quality detection method based on a depth image, which can accurately detect the position and height of a crop and effectively evaluate the sowing quality. The method is specifically as follows.
Firstly, a depth camera is installed to obtain a depth image; the method comprises the steps that the installation position and the installation angle of a depth camera need to be limited, the distance between a crop canopy and a ground plane and the depth camera is within the effective range of the depth camera, then the depth camera is installed at a vertical overlooking angle, and a depth image is obtained through the depth camera; then, carrying out median filtering on the depth image to eliminate image holes;
reading the maximum gray scale in the image after eliminating the image holes, and taking the maximum gray scale as the maximum depth value D of the imagemax；
Subtracting D from each pixel gray level in the depth imagemaxTranslating the coordinate origin of the depth image from the camera position to the deepest part of the image along the Z-axis direction; and taking a negative value for the image gray scale, and reversing the Z axis to obtain the elevation image.
Filtering the curve of each image row in the elevation image by using a Savitzky-Golay filter, eliminating noise and simultaneously keeping the curve shape; acquiring a maximum value point of each image line as a characteristic point, and drawing the maximum value point on a blank image with the same size of an original image, so that only one characteristic point is reserved on each image line of each crop line to obtain a characteristic point image; performing transverse one-dimensional accumulation and projection on the characteristic point image to obtain a characteristic one-dimensional curve; taking the mode of the characteristic one-dimensional curve as the number of crop rows contained in the image; selecting a central point at the position close to the center of each crop row for slope search, wherein the method comprises the following steps of;
(1) determining an iteration angle corresponding to the iteration times by taking the central point as an origin, 1/2 adjacent to the distance between the two central points as a width, the number of pixels in the image column as a height, the step number, the iteration times and the precision, and sequentially intercepting local images with different lengths and consistent sizes by taking the iteration angle as a rotation angle step length and taking the vertical direction as a rotation starting point;
the iteration angle is obtained on the basis of a first iteration angle, the first iteration angle is [ -90 ° ] step length, the second iteration angle is the first iteration angle/the second iteration step number, and the iteration angles after different iterations are obtained by analogy.
(2) Respectively carrying out longitudinal one-dimensional accumulation and projection on the local images, and taking extreme points of the local images;
(3) for the local images intercepted from the same central point, the rotation angle corresponding to the local image with the maximum extreme point is the inclination angle of the crop row where the central point is located;
(4) and (4) reducing the step length of the rotation angle by taking the inclination angle obtained in the step (3) as a reference, and repeating the steps (1) - (3) for multiple times to obtain the accurate inclination angle.
And intercepting a local image through the accurate inclination angle obtained by multiple iterations and the corresponding central point of the accurate inclination angle, and performing least square straight line fitting on the characteristic points in the local image to obtain the optimal point inclination type of the crop row.
Determining the height h and the width w of the image based on the optimal point slope of the crop row obtained in the previous step, and carrying out screenshot on the original depth image according to the height h and the width w to obtain a local image of the crop row;
h＝H
in the formula: h is the original depth image height.
The local images of the crop rows are subjected to transverse one-dimensional accumulation and projection to obtain a crop row height characteristic distribution curve, as shown in fig. 1, each peak in the curve represents a crop, and the crop height can be reflected.
And acquiring a maximum value point in the elevation characteristic distribution curve, taking the abscissa of the maximum value point as the crop position, and taking the ordinate of the maximum value point as the crop height.
The crop is arranged on the crop row, and the central point O (x) of the crop row iso,yo) The distance of the point is L pixels, the actual coordinate P (x, y) of the crop is obtained by calculation according to the inclination angle alpha of the crop row perpendicular to the direction, and the coordinate of each crop is marked on the original image, as shown in FIG. 2, the line in the graph represents the crop row, and the point represents the crop position; is calculated toTo the coordinates of the crop plants, the plant growth factor,
x＝x0+L×sinα
y＝y0+L×cosα；
calculating to obtain the seedling spacing according to the crop coordinates, and judging the sowing uniformity and the miss-sowing condition; and calculating the row spacing, the uniformity among rows, whether the crop rows are parallel or whether a single crop row is straight and the characteristic distribution of the height of the crop according to the fitting result of the crop rows, and evaluating the growth condition of the crop seedlings.
The method can accurately detect the position and height of the crop, embodies the seeding and emergence conditions of the crop from a three-dimensional angle, and provides a new method and thought for evaluating the emergence of the crop.
Claims (3)
1. A crop emergence quality detection method based on a depth image is characterized in that: the method comprises the following steps:
step one, acquiring a crop elevation image
(1) Installing a depth camera above the crop canopy in a vertical overlook mode within the effective range of the depth camera, and acquiring a depth image through the depth camera;
(2) carrying out median filtering on the depth image to eliminate image holes;
(3) reading the maximum gray scale in the image with the holes eliminated, and taking the maximum gray scale as the maximum depth value D of the imagemax；
(4) Subtracting D from each pixel gray level in the depth imagemaxTranslating the coordinate origin of the depth image from the camera position to the deepest part of the image along the Z-axis direction, then taking a negative value for the gray level of the image, and reversing the Z axis to obtain an elevation image;
step two, fitting the row positions of the crops
(1) Filtering a curve of each image line in the elevation image, eliminating noise and simultaneously keeping the curve shape;
(2) acquiring a maximum value point of each image line as a characteristic point, and drawing the maximum value point on a blank image with the same size of an original image, so that only one characteristic point is reserved on each image line of each crop line to obtain a characteristic point image;
(3) performing transverse one-dimensional accumulation and projection on the characteristic point image to obtain a characteristic one-dimensional curve;
(4) taking the mode of the characteristic one-dimensional curve as the number of crop rows contained in the image;
(5) selecting a central point at the position close to the center of each crop row to perform slope search to obtain an accurate inclination angle;
(6) intercepting a local image through an accurate inclination angle obtained through multiple iterations and a corresponding central point thereof, and performing least square straight line fitting on characteristic points in the local image to obtain an optimal point inclination type of a crop row;
step three, acquiring the position and height of the crop on the row
(1) Determining the height h and the width w based on the optimal point slope of the crop row, and carrying out screenshot on the original depth image according to the height h and the width w to obtain a local image of the crop row;
h＝H
in the formula: h is the original depth image height;
(2) performing transverse one-dimensional accumulation and projection on the local images of the crop rows to obtain a crop row height characteristic distribution curve;
(3) acquiring a maximum value point in an elevation characteristic distribution curve, taking the abscissa of the maximum value point as a crop position, and taking the ordinate of the maximum value point as a crop height;
step four, mapping the position of the crop row to the original image
The crop is arranged on the crop row, and the central point O (x) of the crop row iso,yo) The distance of the point is L pixels, the actual coordinate P (x, y) of the crop is obtained by calculation according to the inclination angle alpha of the crop row vertical to the direction, the coordinate of each crop is marked on the original image, the coordinate of the crop is obtained by calculation,
x＝x0+L×sinα
y＝y0+L×cosα；
step five, evaluating the seedling emergence quality of crops
Calculating to obtain the seedling spacing according to the crop coordinates, and judging the sowing uniformity and the miss-sowing condition; and calculating the row spacing, the uniformity among rows, whether the crop rows are parallel or whether a single crop row is straight and the characteristic distribution of the height of the crop according to the fitting result of the crop rows, and evaluating the growth condition of the crop seedlings.
2. The depth image-based crop emergence quality detection method according to claim 1, characterized in that: the method for selecting the center point to perform slope search for the position of each crop row close to the center comprises the following steps:
(1) determining an iteration angle corresponding to the iteration times by taking the central point as an origin, taking a half of the distance between two adjacent central points as a width, taking the number of pixels in the image column as a height, taking the step number, the iteration times and the precision, and sequentially intercepting local images with different lengths and different directions and consistent sizes by taking the iteration angle as a rotation angle step length and taking the vertical direction as a rotation starting point;
(2) respectively carrying out longitudinal one-dimensional accumulation and projection on the local images, and taking extreme points of the local images;
(3) for the local images intercepted from the same central point, the rotation angle corresponding to the local image with the maximum extreme point is the inclination angle of the crop row where the central point is located;
(4) and (4) reducing the step length of the rotation angle by taking the inclination angle obtained in the step (3) as a reference, and repeating the steps (1) - (3) for multiple times to obtain the accurate inclination angle.
3. The depth image-based crop emergence quality detection method according to claim 1, characterized in that: and in the second step, a Savitzky-Golay filter is used for filtering the curve of each image line in the elevation image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705485.4A CN113643231B (en) | 2021-06-24 | 2021-06-24 | Crop seedling emergence quality detection method based on depth image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705485.4A CN113643231B (en) | 2021-06-24 | 2021-06-24 | Crop seedling emergence quality detection method based on depth image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113643231A true CN113643231A (en) | 2021-11-12 |
| CN113643231B CN113643231B (en) | 2024-04-09 |
Family
ID=78416230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110705485.4A Active CN113643231B (en) | 2021-06-24 | 2021-06-24 | Crop seedling emergence quality detection method based on depth image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643231B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04336383A (en) * | 1991-05-13 | 1992-11-24 | Kubota Corp | Crops array detection device for operation machine |
| US20040264761A1 (en) * | 2003-04-30 | 2004-12-30 | Deere & Company | System and method for detecting crop rows in an agricultural field |
| CN101807252A (en) * | 2010-03-24 | 2010-08-18 | 中国农业大学 | Crop row center line extraction method and system |
| CN110232389A (en) * | 2019-06-13 | 2019-09-13 | 内蒙古大学 | A kind of stereoscopic vision air navigation aid based on green crop feature extraction invariance |
| WO2020000043A1 (en) * | 2018-06-28 | 2020-01-02 | University Of Southern Queensland | Plant growth feature monitoring |
| CN111739031A (en) * | 2020-06-19 | 2020-10-02 | 华南农业大学 | Crop canopy segmentation method based on depth information |
| CN112614147A (en) * | 2020-12-24 | 2021-04-06 | 中国农业科学院作物科学研究所 | Method and system for estimating plant density of crop at seedling stage based on RGB image |
| CN112686859A (en) * | 2020-12-30 | 2021-04-20 | 中国农业大学 | Crop CWSI detection method based on thermal infrared and RGB-D camera |
-
2021
- 2021-06-24 CN CN202110705485.4A patent/CN113643231B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04336383A (en) * | 1991-05-13 | 1992-11-24 | Kubota Corp | Crops array detection device for operation machine |
| US20040264761A1 (en) * | 2003-04-30 | 2004-12-30 | Deere & Company | System and method for detecting crop rows in an agricultural field |
| CN101807252A (en) * | 2010-03-24 | 2010-08-18 | 中国农业大学 | Crop row center line extraction method and system |
| WO2020000043A1 (en) * | 2018-06-28 | 2020-01-02 | University Of Southern Queensland | Plant growth feature monitoring |
| CN110232389A (en) * | 2019-06-13 | 2019-09-13 | 内蒙古大学 | A kind of stereoscopic vision air navigation aid based on green crop feature extraction invariance |
| CN111739031A (en) * | 2020-06-19 | 2020-10-02 | 华南农业大学 | Crop canopy segmentation method based on depth information |
| CN112614147A (en) * | 2020-12-24 | 2021-04-06 | 中国农业科学院作物科学研究所 | Method and system for estimating plant density of crop at seedling stage based on RGB image |
| CN112686859A (en) * | 2020-12-30 | 2021-04-20 | 中国农业大学 | Crop CWSI detection method based on thermal infrared and RGB-D camera |
Non-Patent Citations (2)
| Title |
|---|
| 翟志强;朱忠祥;杜岳峰;张硕;毛恩荣;: "基于Census变换的双目视觉作物行识别方法", 农业工程学报, no. 11, 8 June 2016 (2016-06-08), pages 213 - 221 * |
| 赵瑞娇;李民赞;张漫;刘刚;: "基于改进Hough变换的农田作物行快速检测算法", 农业机械学报, no. 07, 25 July 2009 (2009-07-25), pages 169 - 171 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113643231B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Golbach et al. | Validation of plant part measurements using a 3D reconstruction method suitable for high-throughput seedling phenotyping | |
| CN109146948B (en) | Crop growth phenotype parameter quantification and yield correlation analysis method based on vision | |
| Bao et al. | Field-based architectural traits characterisation of maize plant using time-of-flight 3D imaging | |
| Vázquez-Arellano et al. | Determination of stem position and height of reconstructed maize plants using a time-of-flight camera | |
| CN114283203B (en) | Calibration method and system of multi-camera system | |
| Zhang et al. | Estimating plant distance in maize using Unmanned Aerial Vehicle (UAV) | |
| CN115272187A (en) | Vehicle-mounted dynamic field frame-to-frame relevance based field rice and wheat lodging global evaluation method | |
| CN115908708B (en) | Kinect-based plant population global three-dimensional reconstruction method | |
| CN112614147A (en) | Method and system for estimating plant density of crop at seedling stage based on RGB image | |
| Li et al. | Image detection and verification of visual navigation route during cotton field management period | |
| CN110610438B (en) | Crop canopy petiole included angle calculation method and system | |
| CN116977960A (en) | Rice seedling row detection method based on example segmentation | |
| CN113920106B (en) | Corn growth vigor three-dimensional reconstruction and stem thickness measurement method based on RGB-D camera | |
| Hu et al. | Phenotyping of poplar seedling leaves based on a 3D visualization method | |
| Harandi et al. | How to make sense of 3D representations for plant phenotyping: a compendium of processing and analysis techniques | |
| CN117437223A (en) | Intelligent defect detection method for high-speed board-to-board connector | |
| CN113643231A (en) | Crop emergence quality detection method based on depth image | |
| Li | 3D machine vision system for robotic weeding and plant phenotyping | |
| CN108764294B (en) | Line number automatic detection method based on corn ear symmetry | |
| CN102288776A (en) | Corn plant growth rate measuring device and method | |
| Chien et al. | Non-destructive growth measurement of selected vegetable seedlings using orthogonal images | |
| CN117115811A (en) | High-precision determining method for potato crop ridge line independent of unmanned aerial vehicle | |
| CN116051537A (en) | Crop plant height measurement method based on monocular depth estimation | |
| CN111886982B (en) | Detection method of dry land planting operation quality real-time detection system | |
| Chen et al. | Measurement of the distance from grain divider to harvesting boundary based on dynamic regions of interest. |
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 |