CN111028233A - Corn seedling stage mechanical weeding identification method and device based on machine vision - Google Patents
Corn seedling stage mechanical weeding identification method and device based on machine vision Download PDFInfo
- Publication number
- CN111028233A CN111028233A CN202010019478.4A CN202010019478A CN111028233A CN 111028233 A CN111028233 A CN 111028233A CN 202010019478 A CN202010019478 A CN 202010019478A CN 111028233 A CN111028233 A CN 111028233A
- Authority
- CN
- China
- Prior art keywords
- weeding
- corn
- mechanical
- machine vision
- 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.)
- Pending
Links
- 238000009333 weeding Methods 0.000 title claims abstract description 66
- 240000008042 Zea mays Species 0.000 title claims abstract description 30
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 29
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 27
- 235000005822 corn Nutrition 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 19
- 241001057636 Dracaena deremensis Species 0.000 claims abstract description 24
- 239000012636 effector Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 241001464837 Viridiplantae Species 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 2
- 235000009973 maize Nutrition 0.000 claims description 2
- 241000196324 Embryophyta Species 0.000 abstract description 19
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 230000035699 permeability Effects 0.000 description 2
- 244000237956 Amaranthus retroflexus Species 0.000 description 1
- 235000013479 Amaranthus retroflexus Nutrition 0.000 description 1
- 208000003643 Callosities Diseases 0.000 description 1
- 241000217446 Calystegia sepium Species 0.000 description 1
- 240000006162 Chenopodium quinoa Species 0.000 description 1
- 244000075634 Cyperus rotundus Species 0.000 description 1
- 235000016854 Cyperus rotundus Nutrition 0.000 description 1
- 244000152970 Digitaria sanguinalis Species 0.000 description 1
- 235000010823 Digitaria sanguinalis Nutrition 0.000 description 1
- 244000133098 Echinacea angustifolia Species 0.000 description 1
- 244000025670 Eleusine indica Species 0.000 description 1
- 235000014716 Eleusine indica Nutrition 0.000 description 1
- 235000014820 Galium aparine Nutrition 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 206010020649 Hyperkeratosis Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 244000234609 Portulaca oleracea Species 0.000 description 1
- 235000001855 Portulaca oleracea Nutrition 0.000 description 1
- 235000010086 Setaria viridis var. viridis Nutrition 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 235000014134 echinacea Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 244000230342 green foxtail Species 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M21/00—Apparatus for the destruction of unwanted vegetation, e.g. weeds
- A01M21/02—Apparatus for mechanical destruction
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Insects & Arthropods (AREA)
- Environmental Sciences (AREA)
- Quality & Reliability (AREA)
- Zoology (AREA)
- Wood Science & Technology (AREA)
- Pest Control & Pesticides (AREA)
- Mechanical Engineering (AREA)
- Soil Working Implements (AREA)
Abstract
The invention discloses a mechanical weeding identification method and device for a corn seedling stage based on machine vision, and belongs to the field of agricultural engineering. The image is collected through the identification camera and transmitted to the processor, the corn plant area is identified through a mechanical weeding identification method in the corn seedling stage based on machine vision, the corn root position information is measured and calculated, then the action of the actuating mechanism is controlled, the rotary weeding knife with the notch rotates around the corn root, weeds around the corn plant are removed, and the path navigation of the weeding device is realized through the navigation camera. The invention provides a high-precision and high-speed mechanical weeding identification algorithm, realizes autonomous and efficient operation of a weeding device, and has strong practical value.
Description
Technical Field
The invention relates to a mechanical weeding identification method and device, belongs to the field of agricultural engineering, and particularly relates to a mechanical weeding identification method and device for corn seedling stage based on machine vision.
Background
Weeds have great harm to the growth of crops, compete for fertilizer, light, moisture and space with the crops, and are easy to breed diseases and insect pests, so that the yield and the quality of the crops are reduced. The existing weeding methods at present comprise artificial weeding, mechanical weeding, chemical weeding, biological weeding, flame weeding, electric weeding, radiation weeding and the like. The mechanical weeding can effectively resist the use of pesticides and fertilizers, meet the requirements of organic production systems and the public on food safety and environmental protection, increase the air permeability and water permeability of soil and contribute to the growth of crops. The key technology of mechanical weeding is accurate identification of weeds, and the intellectualization and refinement of mechanical weeding can be guaranteed only by realizing accurate identification of weeds.
Corn is the first large grain crop in China, and common weeds in corn fields comprise annual gramineous weeds including large crabgrass, goosegrass, green bristlegrass and the like, annual broadleaf weeds including amaranthus retroflexus, quinoa, purslane and the like, and perennial weeds including cyperus rotundus, bindweed, echinacea and the like. The corn in the seedling stage is most seriously damaged by weeds, and the corns in the middle and later stages form a high and large closed group, so that the generation and growth of the weeds are inhibited, and the influence on the yield is not too great. Thus, the corn seedling stage is a critical stage for weed control.
The invention discloses a high-precision and high-speed corn seedling stage mechanical weeding recognition algorithm and an autonomous and efficient operation mechanical weeding device, and has high practical value.
Disclosure of Invention
The invention discloses a high-precision and high-speed corn seedling stage mechanical weeding identification algorithm and an autonomous and efficient mechanical weeding device, aiming at the problems that the variety of weeds in the corn seedling stage is various, the accuracy and the real-time performance of weed identification in the prior art are insufficient, and the like.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a mechanical weeding identification method for corn seedlings based on machine vision is characterized in that weed identification is equivalent to identification of non-corn plant parts in green plants, and identification of corn plants enables an identification algorithm to be more efficient.
A mechanical weeding identification method for corn seedling stage based on machine vision, which is operated according to the following steps,
a. carrying out binarization processing on the collected RGB image according to color characteristics to obtain a binarization image with a green plant as a foreground region, removing noise, and then carrying out connected domain marking on the foreground region;
b. calculating an HSV model to respectively obtain a saturation image and a chrominance image;
c. establishing a saturation energy model, performing mask processing on the saturation image by using a binary image, and calculating the saturation energy value in each connected domain, wherein the connected domain with the maximum saturation energy value is a corn plant region;
d. and measuring and calculating the root position information of the corn plants according to the chrominance images.
The utility model provides a maize seedling stage machinery weeding device based on machine vision, comprises treater I, discernment camera II, navigation camera III, arm IV, end effector V, characterized by: the processor I is an embedded controller of the system; the identification camera II and the navigation camera III are visual sensors of the system and are connected with the processor I through a bus; the mechanical arm IV is controlled by the processor I through a motor; the end effector V is a weeding knife of the weeding device and is connected with the mechanical arm IV; the image acquired by the identification camera II is an RGB image for mechanical weeding identification; the processor I calculates and calculates the root position information of the corn plants according to a mechanical weeding identification method, and further controls the mechanical arm IV to act; the end effector V is a rotary weeding knife with a notch.
The invention discloses a mechanical weeding identification method and device for corn seedling stage based on machine vision, which is characterized in that:
(1) compared with weed identification, the method is simpler and more accurate;
(2) the feature extraction dimensionality of the identification method is increased by introducing the HSV model, and the identification method is simplified;
(3) the rotary weeding knife with the opening is controlled to operate according to the root position information of the corn plants, so that the effects of fixed-point weeding and rotary seedling avoidance can be achieved.
Drawings
FIG. 1 is a flow chart of a mechanical weeding identification method for corn in seedling stage based on machine vision
FIG. 2 is a schematic structural view of a mechanical weeding device for corn in seedling stage
FIG. 3 is a schematic view of a rotary weeding knife with a notch
The legend symbols in the drawings each have the following meanings:
i-processor, II-discernment camera, III-navigation camera, IV-arm, V-end effector, 1-the cutting edge of weeding sword.
Detailed Description
Specific embodiments are given below with reference to the accompanying drawings.
As shown in figure 1, a mechanical weeding identification method for corn seedling stage based on machine vision is operated according to the following steps,
a. carrying out binarization processing on the collected RGB image according to color characteristics, taking the region with the green component larger than the red component and the blue component as a foreground region, namely a green plant region, and taking the other regions as background regions, then carrying out denoising processing on the binarization image, and carrying out connected domain marking on the foreground region in the image with the noise removed;
b. converting the RGB model into an HSV model to respectively obtain a saturation image and a chrominance image;
c. establishing a saturation energy model, defining the saturation energy of a region as the dispersion square sum of the saturation of all points in the region and the mean value of the saturation, performing masking treatment on the saturation image by using a binary image, and calculating the saturation energy value in each connected domain, wherein the connected domain with the maximum saturation energy value is the corn plant region;
d. in the corn plant area, the root colorimetric value is the largest, so that the root position information of the corn plant can be measured and calculated according to the colorimetric image.
The concrete example is as follows:
firstly, binarization processing-convenient post processing;
secondly, denoising treatment, namely removing noise interference;
thirdly, connected domain marking, which is convenient for processing each connected domain, and the diagram shown in FIG. 1 has 7 connected domains;
fourthly, acquiring a saturation image, which is convenient for extracting saturation characteristics;
fifthly, mask processing, namely facilitating analysis of the saturation characteristics of each connected domain;
sixthly, determining a corn plant by calculating saturation energy, wherein the region with the maximum saturation energy in each connected domain is a corn plant region, in the diagram shown in fig. 1, the connected domain with the label of 1 has the maximum saturation energy and is the corn plant region, the region is marked as 1 again, and other regions are weed regions and are marked as 2 again;
acquiring a chrominance image, which is convenient for extracting saturation characteristics;
and eighthly, measuring and calculating the information of the root position, namely facilitating the removal of weeds around the corn plant by using a rotary weeding cutter with a notch, analyzing a connected domain marked as 1 again in the graph shown in the figure 1, and marking the pixel point with the maximum chroma as the root position by using a white circle.
As shown in fig. 2, an embodiment of a mechanical weeding device based on machine vision for corn seedling stage is that an identification camera ii and a navigation camera iii are used as visual sensors of a system, respectively collect images to identify corn plants and plan the path of the weeding device, and the collected images are sent to a processor I through a bus to be processed; the processor I controls the mechanical weeding device to operate according to the rows through a leading line detection algorithm; the processor I identifies corn plants by a mechanical weeding identification method in a corn seedling stage, measures and calculates root position information, and further controls the mechanical arm IV to generate corresponding actions; and the mechanical arm IV drives the end effector V to move to the root of the corn plant for fixed-point weeding.
In the weeding device, the end effector V is a rotary weeding knife with a notch, the top view of the rotary weeding knife is shown in figure 3, when the mechanical arm IV drives the rotary weeding knife to move to the root position of a corn plant, the notch is opposite to the corn plant and rotates clockwise around a central axis, and the blade 1 of the weeding knife cuts and eradicates weeds around the corn plant. Can change weeds clearance range through changing the weeding sword diameter, through changing weeding sword opening angle, can change crop protection zone size, consequently can design the weeding sword of different diameters and different opening angle to the row spacing selects for use different weeding sword according to maize plant.
The invention has been described in detail with respect to the general description and specific embodiments thereof, but it is not intended to be limited thereto, and modifications and improvements can be made within the spirit of the invention.
Claims (5)
1. A mechanical weeding identification method for corn seedling stage based on machine vision is characterized in that: the operation is carried out according to the following steps,
carrying out binarization processing on the collected RGB image according to color characteristics to obtain a binarization image with a green plant as a foreground region, removing noise, and then carrying out connected domain marking on the foreground region;
calculating an HSV model to respectively obtain a saturation image and a chrominance image;
establishing a saturation energy model, performing mask processing on the saturation image by using a binary image, and calculating the saturation energy value in each connected domain, wherein the connected domain with the maximum saturation energy value is a corn plant region;
and measuring and calculating the root position information of the corn plants according to the chrominance images.
2. The utility model provides a maize seedling stage machinery weeding device based on machine vision, by treater [ I ], discernment camera [ II ], navigation camera [ III ], arm [ IV ], end effector [ V ] constitute characterized by: the processor [ I ] is an embedded controller of the system; the identification camera [ II ] and the navigation camera [ III ] are visual sensors of the system and are connected with the processor [ I ] through a bus; the mechanical arm [ IV ] is controlled by the processor [ I ] through a motor; the end effector [ V ] is a weeding knife of the weeding device and is connected with the mechanical arm [ IV ].
3. The mechanical weeding device for corn seedlings based on machine vision as claimed in claim 2, wherein: and the image acquired by the identification camera [ II ] is an RGB image for mechanical weeding identification.
4. The mechanical weeding device for corn seedlings based on machine vision as claimed in claim 2, wherein: the processor [ I ] measures and calculates the root position information of the corn plants according to a mechanical weeding identification method, and then controls the mechanical arm [ IV ] to act.
5. The mechanical weeding device for corn seedlings based on machine vision as claimed in claim 2, wherein: the end effector [ V ] is a rotary weeding knife with a notch.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010019478.4A CN111028233A (en) | 2020-01-08 | 2020-01-08 | Corn seedling stage mechanical weeding identification method and device based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010019478.4A CN111028233A (en) | 2020-01-08 | 2020-01-08 | Corn seedling stage mechanical weeding identification method and device based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111028233A true CN111028233A (en) | 2020-04-17 |
Family
ID=70202466
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010019478.4A Pending CN111028233A (en) | 2020-01-08 | 2020-01-08 | Corn seedling stage mechanical weeding identification method and device based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111028233A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115581135A (en) * | 2022-09-30 | 2023-01-10 | 扬州大学 | Intelligent unmanned sowing and fertilizing device and method based on machine vision |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102172233A (en) * | 2011-03-04 | 2011-09-07 | 江苏大学 | Method for carrying out real-time identification and targeted spraying on cotton field weeds |
CN203105068U (en) * | 2013-03-22 | 2013-08-07 | 中国农业大学 | Multi-tooth hoe blade of hoeing robot |
CN104396428A (en) * | 2014-11-28 | 2015-03-11 | 重庆速腾机械制造有限公司 | Swing type lawn mower |
CN109511361A (en) * | 2019-01-08 | 2019-03-26 | 安徽农业大学 | A kind of farmland Special weeder device people and its control method |
-
2020
- 2020-01-08 CN CN202010019478.4A patent/CN111028233A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102172233A (en) * | 2011-03-04 | 2011-09-07 | 江苏大学 | Method for carrying out real-time identification and targeted spraying on cotton field weeds |
CN203105068U (en) * | 2013-03-22 | 2013-08-07 | 中国农业大学 | Multi-tooth hoe blade of hoeing robot |
CN104396428A (en) * | 2014-11-28 | 2015-03-11 | 重庆速腾机械制造有限公司 | Swing type lawn mower |
CN109511361A (en) * | 2019-01-08 | 2019-03-26 | 安徽农业大学 | A kind of farmland Special weeder device people and its control method |
Non-Patent Citations (1)
Title |
---|
XINYU HU等: "Study on Classification Corn Seedling and Weed Based on RGB Model and HSV Model", 《AGRICULTURE, FORESTRY AND FISHERIES》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115581135A (en) * | 2022-09-30 | 2023-01-10 | 扬州大学 | Intelligent unmanned sowing and fertilizing device and method based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kumar et al. | Diseases detection of various plant leaf using image processing techniques: A review | |
CN100416590C (en) | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic | |
CN106688705A (en) | Intelligent planting greenhouse and monitoring method used for same | |
CN111914914A (en) | Method, device, equipment and storage medium for identifying plant diseases and insect pests | |
Narvekar et al. | Grape leaf diseases detection & analysis using SGDM matrix method | |
CN109543552B (en) | Rice growth area mapping method and system based on multi-feature extraction in growth period | |
CN104915660A (en) | Winter wheat automatic recognition method based on GF-1/WFV NDVI time sequence | |
Vikram | Agricultural Robot–A pesticide spraying device | |
CN115456960A (en) | Citrus huanglongbing disease and pest monitoring and early warning system and method | |
Gining et al. | Harumanis mango leaf disease recognition system using image processing technique | |
CN103392482B (en) | Efficient simple mulching cultivation method for sweet potatoes | |
Wang et al. | Recognition of weeds at asparagus fields using multi-feature fusion and backpropagation neural network | |
Xu et al. | Research and application on corn crop identification and positioning method based on Machine vision | |
He et al. | Visual detection of rice rows based on Bayesian decision theory and robust regression least squares method | |
Gupta et al. | Smart irrigation system and plant disease detection | |
CN111028233A (en) | Corn seedling stage mechanical weeding identification method and device based on machine vision | |
Tian et al. | Research on plant diseases and insect pests identification based on CNN | |
Jiang et al. | A conceptual evaluation of a weed control method with post-damage application of herbicides: A composite intelligent intra-row weeding robot | |
CN113331160A (en) | Special accurate medicine system that spouts of tobacco | |
Sahoo et al. | Automatic Dead zone detection in 2-D leaf image using clustering and segmentation technique | |
CN117115769A (en) | Plant detection and positioning method based on semantic segmentation network | |
Narvekar et al. | Novel algorithm for grape leaf diseases detection | |
CN117058607A (en) | Plant growth state monitoring system based on image visual analysis | |
Concepcion et al. | Arabidopsis Tracker: A Centroid-Based Vegetation Localization Model for Automatic Leaf Canopy Phenotyping in Multiple-Pot Cultivation System | |
CN112712534B (en) | Corn rhizome navigation datum line extraction method based on navigation trend line |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200417 |
|
WD01 | Invention patent application deemed withdrawn after publication |