CN105557175B - Intelligent grass-removing and its control method - Google Patents
Intelligent grass-removing and its control method Download PDFInfo
- Publication number
- CN105557175B CN105557175B CN201410531448.6A CN201410531448A CN105557175B CN 105557175 B CN105557175 B CN 105557175B CN 201410531448 A CN201410531448 A CN 201410531448A CN 105557175 B CN105557175 B CN 105557175B
- Authority
- CN
- China
- Prior art keywords
- image information
- external environment
- intelligent grass
- image
- standard
- 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.)
- Active
Links
Abstract
A kind of intelligent grass-removing, including：Body；Image acquisition units are set on body, the image information for acquiring external environment；Standard color part is set in the ken of described image collecting unit；Image correction apparatus, the image information of the standard color part for obtaining described image collecting unit is compared with the standard color data stored, image acquisition units generated color deviation value when acquiring the image information of external environment is obtained, colour correction is carried out to the image information of the external environment according to the color deviation value obtained；Control device, the working condition for controlling the intelligent grass-removing according to the image information of the external environment after colour correction.A kind of intelligent grass-removing control method is also provided.The present invention can effectively reduce vegetation False Rate.
Description
Technical field
The present invention relates to automated machine fields, more particularly to a kind of intelligent grass-removing and its control method.
Background technology
Grass trimmer is a kind of for cutting careless quilt, vegetation etc., trimming weeds and the semi-automation for handling smooth greening lawn
Machine tool.Grass trimmer is because easy to operate, saving manpower and time, to be widely used.
Grass trimmer in the process of work, can acquire some image informations, and according to these by installing camera
Image information judges whether front vegetation is the object for cutting and trimming.However, when vegetation because influenced by environment (such as illumination,
Reflection etc.) generate aberration when, camera the image collected information can deviate the true color of original, so as to cause grass trimmer
There is the phenomenon that vegetation erroneous judgement.
Invention content
Based on this, it is necessary to provide a kind of intelligent grass-removing and its control method that can effectively reduce vegetation False Rate.
A kind of intelligent grass-removing, including：
Body；
Image acquisition units are set on body, the image information for acquiring external environment；
Standard color part is set in the ken of described image collecting unit；
Image correction apparatus, the image information of the standard color part for obtaining described image collecting unit and institute
The standard color data of storage are compared, and it is generated when acquiring the image information of external environment to obtain image acquisition units
Color deviation value carries out colour correction according to the color deviation value obtained to the image information of the external environment；
Control device, the work for controlling the intelligent grass-removing according to the image information of the external environment after colour correction
Make state.
The standard color part is the Standard colour board of white or RGB trisection in one of the embodiments,.
The control device includes judgment module and main control module in one of the embodiments,；
The judgment module is used to judge whether the object in external environment is target vegetation according to described image information；Institute
State working condition of the main control module for controlling the intelligent grass-removing according to the judging result of the judgment module.
The judgment module includes feature extraction unit, computing unit and judging unit in one of the embodiments,；
The feature extraction unit is used to extract the characteristics of image of described image information；The computing unit is for calculating institute
State the similarity between the characteristics of image of image information and the characteristics of image of standard；The judging unit is described similar for judging
Whether degree is not less than similar threshold value, if so, the object in the external environment is target vegetation；If it is not, in the external environment
Object be not target vegetation.
A kind of intelligent grass-removing control method, including：
Acquire the image information of external environment；
Obtain the color deviation value of intelligent grass-removing external environment；
Colour correction is carried out to described image information according to the color deviation value；
The working condition of the intelligent grass-removing is controlled according to the image information of the external environment after colour correction：
When object in external environment is target vegetation, controls the intelligent grass-removing and original direction is kept to continue work
Make；When object in external environment is not target vegetation, control the intelligent grass-removing be stopped or adjustment direction continue
Work.
The step of color deviation value of acquisition intelligent grass-removing external environment is in one of the embodiments,：
The Standard colour board of white or RGB trisection is provided；
Acquire the image information of the Standard colour board of the white or RGB trisection；
The image information of the Standard colour board of the white or RGB trisection and the reference colour that is stored are carried out pair
Than obtaining color deviation value.
It is specially according to the step of color deviation value progress colour correction in one of the embodiments,：
The gain of the RGB channel of described image information is adjusted according to the color deviation value.
It is mowed in one of the embodiments, according to the image information of the external environment after the colour correction control intelligence
The step of working condition of machine includes：
Extract the characteristics of image of described image information；
Calculate the similarity between the characteristics of image and the characteristics of image of standard of described image information；
Judge whether the similarity is not less than similar threshold value, if so, the object in the external environment is target vegetation,
Controlling the intelligent grass-removing keeps original direction to work on；It is planted if it is not, the object in the external environment is not target
Quilt, controls that the intelligent grass-removing is stopped or adjustment direction works on.
Above-mentioned intelligent grass-removing and its control method obtain intelligent grass-removing external environment by the way that standard color part is arranged
Color deviation value, allow image acquisition units acquire image information according to the color deviation value carry out colour correction,
The true color of original would not be deviateed when correcting the image information after color in this way, to effectively reduce vegetation False Rate.
Description of the drawings
Fig. 1 is the structure mould block diagram of intelligent grass-removing in an embodiment；
Fig. 2 is the external structure schematic diagram of intelligent grass-removing in Fig. 1；
Fig. 3 is the frame diagram of judgment module in Fig. 2；
Fig. 4 is the flow chart of intelligent grass-removing control method in an embodiment.
Specific implementation mode
It please refers to Fig.1 and Fig. 2, the structure mould block diagram of intelligent grass-removing and situ results signal in a respectively embodiment
Figure.
The intelligent grass-removing includes body 100, standard color part 200, image acquisition units 300, image correction apparatus 400
And control device 500.Wherein, standard color part 200 is located in the camera shooting ken of image acquisition units 300, image calibration formal dress
400 are set to connect with control device 500.
Intelligent grass-removing needs that the object in external environment is identified in the process of work, to avoid external rings are worked as
Also there is the phenomenon that mistake is cut when not being target vegetation in object in border.In the present embodiment, standard color part 200 is adopted set on image
In the ken for collecting unit 300, image acquisition units 300 are set on body 100, the image information for acquiring external environment.
The influence that object in external environment can be illuminated by the light, reflect, diffuse etc. generates aberration, then passing through reference colour
As soon as the color that color part 200 is imaged, which can also deviate original color, generates a deviation value, and this deviation value embodies external rings
The color of border on the whole deviates.
In the present embodiment, standard color part 200 is the Standard colour board 200 of white or RGB trisection.Reference colour
Plate 200 is located at image acquisition units 300 and images ken center position on the upper side, as shown in Figure 2.It is appreciated that in other implementations
In example, standard color part 200 may be located on the middle position that image acquisition units 300 image the ken.
The image information for the standard color part 200 that image correction apparatus 400 is used to obtain image acquisition units 300 and institute
The standard color data of storage are compared, and are obtained image acquisition units 300 and are produced when acquiring the image information of external environment
Raw color deviation value carries out colour correction according to the color deviation value to the image information of the external environment.Specifically,
The gain of the RGB channel of described image information is such as adjusted, to restore the color of image information.
Control device 500 is used to control the intelligent grass-removing according to the image information of the external environment after colour correction
Working condition：When object in external environment is target vegetation, controls the intelligent grass-removing and original direction is kept to continue
Work；When object in external environment is not target vegetation, control the intelligent grass-removing be stopped or adjustment direction after
Continuous work.
When object in external environment is not target vegetation, it is understood that there may be two kinds of possibilities：One kind may be that intelligence is cut
When being the barriers such as shrub or the stone of lawn surrounding in front of careless machine, but the mowing work on entire lawn has not been completed in grass trimmer
Make；Alternatively possible is the corner that intelligent grass-removing reaches lawn, has completed the grass cutting action on entire lawn.In this way, if
It is that former is possible, just controls the intelligent grass-removing adjustment direction and work on, just control control possible if it is latter
The intelligent grass-removing is stopped.And what the judgement of both possibilities worked with intelligent grass-removing in the particular embodiment
Time deposits certain relationship.
Specifically, control device 500 includes judgment module 510 and main control module 520.Judgment module 510 is used for according to institute
It states image information and judges whether the object in the external environment is target vegetation.Main control module 520 is used for according to the judgement
The judging result of module controls the working condition of the intelligent grass-removing.
The color rendition of image information is very important.For example, the draft on lawn to be being target vegetation, but because of sunlight
The color of irradiation, the grass of certain positions can deviate the color of its script, be easy to influence the judgement knot of judgment module 510 in this way
The grass of fruit, these positions probably is mistaken for not being target vegetation, to be cut by leakage.Similarly, if there is setting in lawn
The road spread with stone, because of the reflex of its periphery vegetation, the color of stone may very close grass color, if not into
Row color rendition, these stones may will be judged to target vegetation by knowledge.
Please refer to Fig. 3.
In the present embodiment, judgment module 510 includes feature extraction unit 512, computing unit 514 and judging unit
516。
Feature extraction unit 512 is used to extract the characteristics of image of described image information, and characteristics of image generally comprises color spy
It seeks peace textural characteristics.Computing unit 514 is connect with feature extraction unit 512, the characteristics of image for calculating described image information
Similarity between the characteristics of image of standard.When calculating similarity, generally there are commonly mahalanobis distance or Euclidean distances.
Judging unit 516 is connect with computing unit 514, for judging whether the similarity is not less than similar threshold value, if so, described outer
Object in portion's environment is target vegetation；If it is not, the object in the external environment is not target vegetation.
In other embodiments, which can also include the warning device being connect with control device 500, described
Warning device controls the intelligent grass-removing in control device 500 and is stopped or when adjustment direction works on, sends out alarm signal
Breath.In this way so that staff can learn in time, the reliability used is improved.The warning device can make a sound alarm signal
Breath, light warning information or sound-light alarm information, are conducive to staff and intuitively learn.
It is appreciated that in other embodiments, after control device 500, which controls the intelligent grass-removing, to be stopped, may be used also
Charging station is returned to control the intelligent grass-removing to charge in time, in this way there are enough power supplys when needing work
Energy supports, and improves the reliability used, and convenient for management intelligent grass-removing.
Referring to FIG. 4, for the flow chart of intelligent grass-removing control method in an embodiment.
Step S110：Acquire the image information of external environment.
Step S120：Obtain the color deviation value of intelligent grass-removing external environment.
External environment the influences such as can be illuminated by the light, reflect, diffusing and generating aberration, then the color of standard color part imaging also can
As soon as deviateing original color generates a deviation value, and this deviation value embodies the color of external environment on the whole and deviates.
In the present embodiment, step S120 is specially：
The Standard colour board of white or RGB trisection is provided；
Acquire the image information of the Standard colour board of the white or RGB trisection；
The image information of the Standard colour board of the white or RGB trisection and the reference colour that is stored are carried out pair
Than obtaining color deviation value.
Step S130：Colour correction is carried out to described image information according to the color deviation value.
In the present embodiment, which is specially that the RGB channel of described image information is adjusted according to the color deviation value
Gain.
Step S140：The work shape of the intelligent grass-removing is controlled according to the image information of the external environment after colour correction
State：
When object in external environment is target vegetation, controls the intelligent grass-removing and original direction is kept to continue work
Make；When object in external environment is not target vegetation, control the intelligent grass-removing be stopped or adjustment direction continue
Work.
When object in external environment is not target vegetation, it is understood that there may be two kinds of possibilities：One kind may be that intelligence is cut
When the barriers such as the shrub for being lawn surrounding in front of careless machine or the stone among lawn, but entire grass has not been completed in grass trimmer
The grass cutting action on level ground；Alternatively possible is the corner that intelligent grass-removing reaches lawn, has completed the grass cutting action on entire lawn.
In this way, it is possible if it is former, it just controls the intelligent grass-removing adjustment direction and works on, it is possible if it is latter,
The intelligent grass-removing is controlled with regard to control to be stopped.And the judgement of both possibilities is cut with intelligence in the particular embodiment
The time of careless machine work deposits certain relationship.
In the present embodiment, the specific following steps of step S140：
Extract the characteristics of image of described image information；
Calculate the similarity between the characteristics of image and the characteristics of image of standard of described image information；
Judge whether the similarity is not less than similar threshold value, if so, the object in the external environment is target vegetation,
Controlling the intelligent grass-removing keeps original direction to work on；It is planted if it is not, the object in the external environment is not target
Quilt, controls that the intelligent grass-removing is stopped or adjustment direction works on.
In other embodiments, when the object in judging external environment is target vegetation, the intelligent grass-removing is controlled
Be stopped or the step of adjustment direction works on after further include the steps that alert.In this way so as to staff
It can learn in time, improve the reliability used.The warning device can make a sound warning message, light warning information or sound
Light warning message is conducive to staff and intuitively learns.
It is appreciated that in other embodiments, when it is target vegetation to judge external environment not, controlling the intelligence and mowing
Machine further includes the steps that controlling intelligent grass-removing return charging station to charge in time after being stopped, in this way so as in need
There are enough power supply energy supports when work, improves the reliability used, and convenient for management intelligent grass-removing.
Above-mentioned intelligent grass-removing and its control method obtain intelligent grass-removing external environment by the way that standard color part is arranged
Color deviation value, allow image acquisition units acquire image information according to the color deviation value carry out colour correction,
The true color of original would not be deviateed when correcting the image information after color in this way, to effectively reduce vegetation False Rate.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Cannot the limitation to the scope of the claims of the present invention therefore be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (8)
1. a kind of intelligent grass-removing, which is characterized in that including：
Body；
Image acquisition units are set on body, the image information for acquiring external environment；
Standard color part is set in the ken of described image collecting unit；
Image correction apparatus, the image information of the standard color part for obtaining described image collecting unit with stored
Standard color data compared, obtain image acquisition units generated color when acquiring the image information of external environment
Deviation value carries out colour correction according to the color deviation value obtained to the image information of the external environment；
Control device, the work shape for controlling the intelligent grass-removing according to the image information of the external environment after colour correction
State.
2. intelligent grass-removing according to claim 1, which is characterized in that the standard color part is white or RGB
The Standard colour board of trisection.
3. intelligent grass-removing according to claim 1, which is characterized in that the control device includes judgment module and master control
Module；
The judgment module is used to judge whether the object in external environment is target vegetation according to described image information；The master
Control module is used to control the working condition of the intelligent grass-removing according to the judging result of the judgment module.
4. intelligent grass-removing according to claim 3, which is characterized in that the judgment module include feature extraction unit,
Computing unit and judging unit；
The feature extraction unit is used to extract the characteristics of image of described image information；The computing unit is for calculating the figure
As the similarity between the characteristics of image of information and the characteristics of image of standard；The judging unit is for judging that the similarity is
It is no to be not less than similar threshold value, if so, the object in the external environment is target vegetation；If it is not, the object in the external environment
Body is not target vegetation.
5. a kind of intelligent grass-removing control method, which is characterized in that including：
Acquire the image information of external environment；
Obtain the color deviation value of intelligent grass-removing external environment；
Colour correction is carried out to described image information according to the color deviation value；
The working condition of the intelligent grass-removing is controlled according to the image information of the external environment after colour correction：
When object in external environment is target vegetation, controls the intelligent grass-removing and original direction is kept to work on；
When object in external environment is not target vegetation, control the intelligent grass-removing be stopped or adjustment direction continue work
Make.
6. intelligent grass-removing control method according to claim 5, which is characterized in that obtain intelligent grass-removing external environment
Color deviation value the step of be：
The Standard colour board of white or RGB trisection is provided；
Acquire the image information of the Standard colour board of the white or RGB trisection；
The image information of the Standard colour board of the white or RGB trisection is compared with the reference colour stored, is obtained
Obtain color deviation value.
7. intelligent grass-removing control method according to claim 5, which is characterized in that carried out according to the color deviation value
The step of colour correction is specially：
The gain of the RGB channel of described image information is adjusted according to the color deviation value.
8. intelligent grass-removing control method according to claim 5, which is characterized in that according to the external rings after colour correction
The image information in border controls the step of working condition of the intelligent grass-removing and includes：
Extract the characteristics of image of described image information；
Calculate the similarity between the characteristics of image and the characteristics of image of standard of described image information；
Judge whether the similarity is not less than similar threshold value, if so, the object in the external environment is target vegetation, control
The direction that the intelligent grass-removing keeps original works on；If it is not, the object in the external environment is not target vegetation, control
Make the intelligent grass-removing is stopped or adjustment direction works on.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410531448.6A CN105557175B (en) | 2014-10-10 | 2014-10-10 | Intelligent grass-removing and its control method |
| JP2017534872A JP2017535279A (en) | 2014-09-23 | 2015-09-23 | Automatic mobile robot |
| PCT/CN2015/090468 WO2016045593A1 (en) | 2014-09-23 | 2015-09-23 | Self-moving robot |
| US15/513,106 US10609862B2 (en) | 2014-09-23 | 2015-09-23 | Self-moving robot |
| EP15845392.8A EP3199009B1 (en) | 2014-09-23 | 2015-09-23 | Self-moving robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410531448.6A CN105557175B (en) | 2014-10-10 | 2014-10-10 | Intelligent grass-removing and its control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105557175A CN105557175A (en) | 2016-05-11 |
| CN105557175B true CN105557175B (en) | 2018-09-21 |
Family
ID=55868309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410531448.6A Active CN105557175B (en) | 2014-09-23 | 2014-10-10 | Intelligent grass-removing and its control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105557175B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339961A (en) * | 2020-02-28 | 2020-06-26 | 苏州科瓴精密机械科技有限公司 | Automatic work system, automatic walking device, control method thereof, and computer-readable storage medium |
| CN113950934A (en) * | 2021-11-02 | 2022-01-21 | 甘肃畜牧工程职业技术学院 | Lawn mower visual system capable of being remotely controlled |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8731295B2 (en) * | 2009-07-01 | 2014-05-20 | Mtd Products Inc. | Visual segmentation of lawn grass |
| CN202059518U (en) * | 2011-04-29 | 2011-11-30 | 罗煜 | System for white balance correction by using color plate |
| CN102771246B (en) * | 2012-07-05 | 2014-12-10 | 芜湖鸿宇智能科技有限公司 | Intelligent mower system and intelligent mowing method thereof |
| DE102012221572A1 (en) * | 2012-11-26 | 2014-05-28 | Robert Bosch Gmbh | Autonomous locomotion device |
| DE102013203707B4 (en) * | 2013-03-05 | 2024-03-07 | Robert Bosch Gmbh | Vehicle device |
| CN103839069B (en) * | 2014-03-11 | 2017-04-12 | 浙江理工大学 | Lawn miss cutting recognition method based on image analysis |
| CN103905803B (en) * | 2014-03-18 | 2016-05-04 | 中国科学院国家天文台 | A kind of color calibration method of image and device |
-
2014
- 2014-10-10 CN CN201410531448.6A patent/CN105557175B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105557175A (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2764872C2 (en) | Weed detection in natural environment | |
| CN105573308B (en) | Grass trimmer based on image detection and grass trimmer control method | |
| US20180125003A1 (en) | Self-moving robot | |
| CN106060479B (en) | A kind of intelligence based on over the horizon video technique herds monitoring system | |
| CN103336966B (en) | A kind of weed images discrimination method being applied to agricultural intelligent machine | |
| US20200178511A1 (en) | Pest monitoring method based on machine vision | |
| CN107121535B (en) | Effective crop growth environment monitoring system | |
| CN107564071A (en) | A kind of image recognition meadow method and device | |
| CN103903252A (en) | Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method | |
| JP2018108040A (en) | Work machine, control device, and program for control | |
| CN109726796A (en) | A kind of farm's management method neural network based | |
| JP2018108041A (en) | Information processing device, feedwater system, information processing system and program | |
| CN105557175B (en) | Intelligent grass-removing and its control method | |
| CN110063326A (en) | Intelligent bird-repeller method based on convolutional neural networks | |
| CN105894003A (en) | Large-field fruit tree disease monitoring early-warning system based on machine vision | |
| CN104504736B (en) | A kind of method and system for recognizing field crop growing way monitoring image Green plant | |
| CN109682326A (en) | Pot seedling upright degree detection device and detection method based on depth image | |
| JP4978799B2 (en) | Straight-forward guidance system for moving vehicles | |
| CN107527367A (en) | A kind of cotton identification and localization method based on binocular camera | |
| CN103499313A (en) | Plug seedling detecting system and method | |
| CN206820844U (en) | Penetrating Fog haze type video camera based on the detection of PM2.5 sensors | |
| TWI720842B (en) | Intelligent bamboo shoot cultivation and harvesting monitoring system and method | |
| CN205910602U (en) | Device of following spot | |
| CN105261045B (en) | Digital method for rapidly evaluating loss degree of alfalfa diseases and insect pests | |
| CN113673375A (en) | Visual intelligent sensing method and device for agricultural machinery and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |