CN106355609A - Automatic walking device and vegetation health condition recognition method thereof - Google Patents
Automatic walking device and vegetation health condition recognition method thereof Download PDFInfo
- Publication number
- CN106355609A CN106355609A CN201610554929.8A CN201610554929A CN106355609A CN 106355609 A CN106355609 A CN 106355609A CN 201610554929 A CN201610554929 A CN 201610554929A CN 106355609 A CN106355609 A CN 106355609A
- Authority
- CN
- China
- Prior art keywords
- vegetation
- value
- module
- rgb value
- health
- 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
- 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
- G06T2207/10024—Color image
-
- 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
- Image Processing (AREA)
Abstract
The invention relates to an automatic walking device and a vegetation health condition recognition method thereof. The method includes the steps: acquiring image information of vegetation; extracting a color value corresponding to the vegetation from the image information; comparing the RGB (red green blue) value of the vegetation with the color value of the vegetation in healthy growth to recognize whether the vegetation is healthy or not. The color value is the RGB value of the vegetation. A system comprises an acquisition module, an extraction module and a recognition module. The RGB value of the vegetation is extracted from the image information, the growth condition of the vegetation is judged, efficiency and judgment accuracy are improved, whether the vegetation is healthy in growth or not is timely recognized, and corresponding treatment measures can be taken when the vegetation is unhealthy.
Description
Technical field
The present invention relates to vegetation health identification field, the vegetation health status knowledge of more particularly to a kind of automatic running device
Other method and system.
Background technology
The normal growth of vegetation has material impact for environment.In the vegetation normal season of growth, need to judge in time
The upgrowth situation of vegetation, finds that the growth of vegetation is whether normal, thus corresponding treatment is carried out to vegetation, including watering, apply fertilizer or
Person adds very small quantities of particles etc..
Tradition mainly passes through the health status that naked eyes identify vegetation, and this method is substantially not accurate enough.Vegetation is normal
During growth, even if there being some bad growth phenomenons, but due to overall change simultaneously less, therefore, it is difficult in the way of naked eyes
Identify.If cannot identify at the bad initial stage of vegetation growth, with the growth of vegetation, subsequent growth problem
Treated again when serious, the healthy growth of vegetation can be significant adverse to.The upgrowth situation of artificial cognition vegetation, needs ward
There is stronger vegetation Professional knowledge, increase the difficulty of artificial cognition further.
Even if additionally, identify some vegetation health condition bad, present need exist for user and carry out maintenance manually, this
Sample just brings two drawbacks, first, maintenance work time and effort consuming, user feels trouble, second, if user non-plant expert,
Often do not know how maintenance to improve the health status of plant.
Content of the invention
Based on this it is necessary to provide a kind of gardening automatic running device and its preparation health status identification side of automatization
Method, whether identification vegetation growth is healthy in time.
A kind of vegetation health status recognition methodss of automatic running device, comprising:
Obtain the image information of vegetation；
Extract the color value of corresponding vegetation from image information, described color value is the rgb value of vegetation；
The rgb value of vegetation and color value during vegetation healthy growth are carried out contrast identification vegetation whether healthy.
The image information of vegetation wherein in an embodiment, is obtained using near infrared camera.
Wherein in an embodiment, extract the face of corresponding vegetation from image information using weber local feature algorithm
Colour.
Wherein in an embodiment, described recognition methodss also include:
The rgb value of vegetation is filtered, filters the rgb value rejecting non-vegetation color from the rgb value of vegetation.
Wherein in an embodiment, whether entered in the default interval rgb value to vegetation by the rgb value judging vegetation
Row filters.
Wherein in an embodiment, described default interval inclusion vegetation rgb value in health and non-health situation.
Wherein in an embodiment, color value during described vegetation healthy growth is the interval of corresponding r, g and b value, institute
State when the color value when rgb value of vegetation and vegetation healthy growth is contrasted, contrast respectively in the rgb value of described vegetation
Whether the value of r, g and b is in the interval of described corresponding r, g and b value.
Wherein in an embodiment, further comprising the steps of: by vegetation, whether healthy information is sent to user, and/
Or vegetation maintenance advisory information is sent to user.
Wherein in an embodiment, whether healthy information includes vegetation region to described vegetation, and this region
Vegetation health level and/or vegetation Damage Types；Described vegetation maintenance advisory information includes suggestion and applies fertilizer, waters, loosens the soil, removes
Grass, at least one spilt in medicine.
Wherein in an embodiment, further comprising the steps of: to vegetation, unsound region executes vegetation maintenance action.
Wherein in an embodiment, described vegetation maintenance action includes: applies fertilizer, waters, loosening the soil, weeding, spilling in medicine
At least one.
A kind of automatic running device, including the identifying system of vegetation health status, described vegetation health status identifying system
Including: acquisition module, for obtaining the image information of vegetation；
Extraction module, for extracting the color value of corresponding vegetation from image information, described color value is the rgb of vegetation
Value；
Identification module, for the rgb value of vegetation and color value during vegetation healthy growth are carried out contrast identification vegetation be
No health.
Wherein in an embodiment, described acquisition module is near infrared camera.
Wherein in an embodiment, described extraction module is extracted from image information using weber local feature algorithm
The color value of corresponding vegetation.
Wherein in an embodiment, described identifying system also includes:
Filtering module, for filtering to the rgb value of vegetation, filters from the rgb value of vegetation and rejects non-vegetation color
Rgb value.
Wherein in an embodiment, described filtering module passes through to judge whether the rgb value of vegetation is right in default interval
The rgb value of vegetation is filtered.
Wherein in an embodiment, described default interval inclusion vegetation rgb value in health and non-health situation.
Wherein in an embodiment, color value during described vegetation healthy growth is the interval of corresponding r, g and b value, institute
When stating identification module the color value when rgb value of vegetation and vegetation healthy growth being contrasted, contrast described vegetation respectively
Whether the value of r, g and b in rgb value is in the interval of described corresponding r, g and b value.
Wherein in an embodiment, also include vegetation healthalert module, described vegetation healthalert module is by vegetation
The information of health and/or vegetation maintenance advisory information are sent to user.
Wherein in an embodiment, described vegetation healthalert module includes communication module, described communication module and use
Family individual's smart device communication, by aforementioned vegetation, the information of health and/or vegetation maintenance advisory information are sent to user
On people's smart machine.
Wherein in an embodiment, whether healthy information includes vegetation region to described vegetation, and this region
Vegetation health level and/or vegetation Damage Types；Described vegetation maintenance advisory information includes suggestion and applies fertilizer, waters, loosens the soil, removes
Grass, at least one spilt in medicine.
Wherein in an embodiment, also include vegetation maintenance module, described vegetation maintenance module is unsound to vegetation
Region executes vegetation maintenance action.
Wherein in an embodiment, described vegetation maintenance module includes: fertilising module, module of watering, module of loosening the soil, removes
Careless module, at least one spilt in medicine module.
The recognition methodss of the above vegetation health status and system, extract the rgb value of vegetation from image information, sentence
The upgrowth situation of disconnected vegetation, improves efficiency and the accuracy rate judging；Timely whether identification vegetation growth is healthy, can plant
By unhealthy when take corresponding remedy measures.
Brief description
Fig. 1 is the flow chart of the recognition methodss of vegetation health status of an embodiment；
Fig. 2 is arranged on the schematic diagram on hay mover near infrared camera；
Fig. 3 is the flow chart of the recognition methodss of vegetation health status of another embodiment；
Fig. 4 is the structure chart of the vegetation health status identifying system of the automatic running device of an embodiment；
Fig. 5 is the structure chart of the vegetation health status identifying system of the automatic running device of another embodiment.
Fig. 6 is the module map of the automatic running device of another embodiment
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and
It is not used in the restriction present invention.
As shown in figure 1, the recognition methodss of the vegetation health status of the automatic running device of an embodiment include step s120
To step s160.
Step s120, obtains the image information of vegetation.Whether normally can determine whether to plant by the color in growth for the vegetation
The health by whether, because color is made up of tri- kinds of Color Channels of r, g, b, therefore, tri- kinds of color value of r, g, b of analysis vegetation
The health status of identification vegetation.The color of vegetation can be shot by near infrared camera and obtain.Generally in the image letter of collection vegetation
During breath, artificial operation is more time-consuming, and near infrared camera can be arranged on automatic running device, such as, Yong Huru
The upgrowth situation on fruit lawn to be observed, near infrared camera can be arranged on hay mover, as shown in Fig. 2 can be in hay mover 1
Front near infrared camera 2 is installed, near infrared camera 2 can be connected with the controller 3 being arranged in hay mover 1 shell.Mow
Machine 1, in motion, can control near infrared camera 2 to work, and obtains the image information of vegetation in whole lawn in time, thus in time
Judge whether the vegetation in lawn is healthy.Near infrared camera 1 is sensitive in the electromagnetic wave induction of 780～3000nm scope to wavelength,
The image information of vegetation can effectively be obtained, be a kind of special digital picture imaging device of vegetation.The performance of near infrared camera 2 is steady
Determine reliability and be easily installed, can be conveniently mounted on hay mover 1；Camera structure compact solid be hardly damaged, running hours
Between long, can use under poor environment, can the continuous uninterrupted image forming job of twenty four hours.This, for artificial, is
A kind of impossible task.Near infrared camera be progressive scan imaging, and export be uncorrected data, its spectral region is relatively
Width, the quality of imaging is very high, is more preferably suitable for vegetation is imaged.The above hay mover is in automatic running device
One kind, miscellaneous equipment can also take same or like way, such as, can pacify on the automobile observing woods woods upgrowth situation
Dress infrared camera etc..
Step s140, extracts the color value of corresponding vegetation from image information, and color value is the rgb value of vegetation.From near
Rgb value in image can be extracted, the algorithm of extraction has multiple, can be sift in the image information that infrared camera obtains
(scale invariant feature conversion), surf (speeded up robust features, fast robust feature), daisy
(daisy is local image characteristics description that can quickly calculate extracting towards dense characteristic), haar (rectangular characteristic), wld
(weber local feature), lbp (local binary patterns, local binary patterns), a kind of orb (binary feature description
Son), brief (a kind of Feature Descriptor), lda-hash (a kind of Feature Descriptor), mser (maximally stable
External regions, Region Feature Extraction), (histogram of oriented gradient, direction gradient is straight for hog
Side scheme), gray value, color histogram, grey level histogram, Gray Moment scheduling algorithm.Here, wld can be selected, (weber local is special
Levy) algorithm extracts the color value of corresponding vegetation from image information.Wld algorithm can effectively obtain the local message in image,
The local message obtaining is more accurate, can more effectively judge whether the specific part (as branch, leaf etc.) of vegetation grows normally.
Step s160, the rgb value of vegetation and color value during vegetation healthy growth are carried out whether contrast identification vegetation is good for
Health.Color value during vegetation healthy growth is the value of corresponding r, g and b.Color during vegetation healthy growth can be prestored
The data of value.Generally, color value during vegetation healthy growth is not necessarily fixed, and the condition such as different moisture changes
Color value can be led to change accordingly, therefore, the value of color value corresponding r, g and b during the vegetation healthy growth prestoring
It can be a reasonably interval.When the rgb value of vegetation is contrasted with color value during vegetation healthy growth, contrast respectively
Whether the value of r, g and b in the rgb value of vegetation is in the interval of corresponding r, g and b value.If in corresponding interval, illustrate to plant
By healthy growth, otherwise, illustrate that growth may be problematic, can analyze which problem vegetation growth occurs in that, find out specific
Reason, carries out comprehensive treatment, makes revegetation normal, healthy growth.As shown in Fig. 2 can controller in hay mover 1
3 setting memorizeies, color value during vegetation healthy growth are stored therein, controller 3 arranges algorithm processor, according to step
Rapid s140 extracts the color value in image information, and passes through programme-control execution step s160 further, thus the knowledge of automatization
Whether other vegetation is healthy.In automatic running device, setting memorizer is one kind of attainable mode it is also possible to individually set
Put processor image information is processed, including execution step s140 and step s160.Can also be in single processor
Setting memorizer, to store color value during vegetation healthy growth.
The recognition methodss of the above vegetation health status, extract the rgb value of vegetation from image information, judge vegetation
Upgrowth situation, improve efficiency and judge accuracy rate；Timely whether identification vegetation growth is healthy, can not be good in vegetation
Corresponding remedy measures are taken during health.
As shown in figure 3, the recognition methodss of the vegetation health status of the automatic running device of another embodiment also include step
s150.
Step s150, filters to the rgb value of vegetation, filters the rgb rejecting non-vegetation color from the rgb value of vegetation
Value., when obtaining the image information of vegetation, the image information of acquisition is multiple, potentially includes sky image near infrared camera,
Barrier, or other image etc..Therefore, the rgb value extracting from image information is also different, and is not belonging to vegetation
If rgb value directly identification is judged by step s160, operation time is longer, and tie the process performance of controller have higher
Require.Therefore, it can the rgb value of vegetation is filtered, reject the rgb value of wherein non-plant.Can by the rgb value of vegetation with
Default interval is contrasted, the rgb value judging vegetation whether in default interval, if not, the rgb of its non-vegetation is described
Value, can directly therefrom reject.Default interval should include rgb value under health and non-health situation for the vegetation, so may be used
Ensure not delete data by mistake, keep the globality of data.
The recognition methodss of the vegetation health status of the automatic running device of another embodiment also include step s170 and s180.
Step s170, by vegetation, whether healthy information is sent to user.Specifically, the information of vegetation whether health includes
Vegetation region, and the vegetation health level in this region and/or vegetation Damage Types.
In a kind of embodiment of the present embodiment, this information is sent to, with patterned form, the personal intelligence that user holds
Equipment, such as smart mobile phone, Intelligent flat computer, intelligent watch, PC etc..This image conversion information can be the garden of user
Or lawn map view, indicate vegetation health level and/or the plant of regional thereon in the form of color, word, icon
By Damage Types.As, with green, yellow, red respectively indicate vegetation health status good, in, poor；Respective regions are indicated with word or icon
Vegetation hydropenia, fertilizer deficiency, needs loosen the soil, have pest and disease damage etc.；Numerical value of each healthy indication with numerical marker plant etc..When
So, other forms of expression are also feasible.
In the another embodiment of the present embodiment, this information is sent to the intelligence of user in the form of the statement-of-health of garden
Energy equipment, can pass through the suitable method such as mail, short message.Garden statement-of-health is sub-category, the healthy feelings in garden are listed in region
Condition, the overall health of the vegetation in for example each region, pest and disease damage situation, moisture situation, nutrient situation, trace element situation etc.
Deng.
In the another embodiment of the present embodiment, the information of vegetation whether health is presented in the basis of automatic running device
On machine, for example, it is shown on the display screen of automatic running device, or report in the form of sound etc..Information particular content and
Appearance form is similar to embodiment above, specifically repeats no more.
Step s180, vegetation maintenance advisory information is sent to user.Specifically, vegetation maintenance advisory information includes suggestion
Apply fertilizer, water, loosening the soil, weeding, at least one spilling in medicine.Similar step s170, vegetation maintenance advisory information can also be to scheme
The form of shape or report is sent to the personal device of user, such as with map and one or more of extension, word, icon
In conjunction with mode point out user specific region to need execution the action etc. such as such as water, apply fertilizer, will not be described here.
In an alternate embodiment of the invention, step s170 and step s180 also can only have one of them.
The recognition methodss of the vegetation health status of the automatic running device of another embodiment also include step s190.
Step s190, to vegetation, unsound region executes vegetation maintenance action.Specifically, vegetation maintenance action includes:
Apply fertilizer, water, loosening the soil, weeding, at least one spilling in medicine.
Automatic running device, according to the specific health problem of the vegetation detecting, executes one or more maintenances accordingly
Action.For example, when automatic running device detects vegetation hydropenia, execute action of watering；When automatic running device detects plant
When being lacked nutrient, execute fertilising, loosen the soil or weeding activities；When automatic running device detects vegetation and meets with pest and disease damage, hold
Row spills medicine action.
As shown in figure 4, the identifying system of the vegetation health status of an embodiment includes acquisition module 120, extraction module 140
With identification module 160.
Acquisition module 120 is used for obtaining the image information of vegetation.By the color in growth for the vegetation whether normally
Judge whether vegetation is healthy, because color is made up of tri- kinds of Color Channels of r, g, b, therefore, tri- kinds of colors of r, g, b of analysis vegetation
Value can recognize that the health status of vegetation.The color of vegetation can be shot by near infrared camera and obtain.Generally in collection vegetation
During image information, artificial operation is more time-consuming, and near infrared camera can be arranged on automatic running device, such as,
If the upgrowth situation on user lawn to be observed, near infrared camera can be arranged on hay mover, as shown in Fig. 2 can be
Near infrared camera 2 is installed in the front of hay mover 1, and near infrared camera 2 can with the controller 3 being arranged in hay mover 1 shell even
Connect.Hay mover 1, in motion, can control near infrared camera 2 to work, and obtains the image information of vegetation in whole lawn in time,
Thus judging whether the vegetation in lawn is healthy in time.Near infrared camera 1 to wavelength 780～3000nm scope electromagnetic wave sense
Should be sensitive, can effectively obtain the image information of vegetation, be a kind of special digital picture imaging device of vegetation.Near infrared camera 2
Stable and reliable for performance and be easily installed, can be conveniently mounted on hay mover 1；Camera structure is compact solid to be hardly damaged, even
Continuous longevity of service, can use under poor environment, can the continuous uninterrupted image forming job of twenty four hours.This is for artificial
For, it is a kind of impossible task.Near infrared camera be progressive scan imaging, and export be uncorrected data, its spectrum
Wider range, the quality of imaging is very high, is more preferably suitable for vegetation is imaged.The above hay mover is that automatically walk sets
One of standby, miscellaneous equipment can also take same or like way, such as, can be in the vapour observing woods woods upgrowth situation
Infrared camera etc. is installed on car.
Extraction module 140 is used for extracting the color value of corresponding vegetation from image information, and color value is the rgb of vegetation
Value.Can extract rgb value in image from the image information that near infrared camera obtains, the algorithm of extraction have multiple, can
Be sift (scale invariant feature conversion), surf (speeded up robust features, fast robust feature),
Daisy (daisy is local image characteristics description that can quickly calculate extracting towards dense characteristic), haar (rectangle spy
Levy), wld (weber local feature), (a kind of two-value is special for lbp (local binary patterns, local binary patterns), orb
Levy description son), brief (a kind of Feature Descriptor), lda-hash (a kind of Feature Descriptor), mser (maximally
Stable external regions, Region Feature Extraction), hog (histogram of oriented gradient, direction
Histogram of gradients), gray value, color histogram, grey level histogram, Gray Moment scheduling algorithm.Here, wld (weber office can be selected
Portion's feature) algorithm extracts the color value of corresponding vegetation from image information.Wld algorithm can effectively obtain the local letter in image
Breath, the local message of acquisition is more accurate, can more effectively judge whether the specific part (as branch, leaf etc.) of vegetation just grows
Often.
Identification module 160 is used for for the rgb value of vegetation and color value during vegetation healthy growth carrying out contrast identification vegetation
Whether healthy.Color value during vegetation healthy growth is the value of corresponding r, g and b.When can prestore vegetation healthy growth
Color value data.Generally, color value during vegetation healthy growth is not necessarily fixed, the bar such as different moisture
Part change can lead to color value to change accordingly, therefore, color value corresponding r, g during the vegetation healthy growth prestoring and
The value of b can be a reasonably interval.When the rgb value of vegetation is contrasted with color value during vegetation healthy growth, point
Not Dui Bi r, g and b in the rgb value of vegetation value whether in the interval of corresponding r, g and b value.If in corresponding interval,
Vegetation growth health is described, otherwise, illustrates that growth may be problematic, can analyze which problem vegetation growth occurs in that, find out
Concrete the reason, carry out comprehensive treatment, make revegetation normal, healthy growth.As shown in Fig. 2 can be in hay mover 1
Controller 3 arranges memorizer, and color value during vegetation healthy growth is stored therein, and controller 3 arranges algorithm processor,
Color value in image information is extracted according to step s140, and passes through programme-control execution step s160 further, thus automatically
Whether the identification vegetation changing is healthy.In automatic running device setting memorizer be attainable mode one kind it is also possible to
It is separately provided processor image information is processed, including execution step s140 and step s160.Can also locate single
In reason device, memorizer is set, to store color value during vegetation healthy growth.
The identifying system of the above vegetation health status, extracts the rgb value of vegetation from image information, judges vegetation
Upgrowth situation, improve efficiency and judge accuracy rate；Timely whether identification vegetation growth is healthy, can not be good in vegetation
Corresponding remedy measures are taken during health.
As shown in figure 5, the identifying system of the vegetation health status of another embodiment also includes filtering module 150.
Filtering module 150 is used for the rgb value of vegetation is filtered, and filters and reject non-vegetation face from the rgb value of vegetation
The rgb value of color., when obtaining the image information of vegetation, the image information of acquisition is multiple, potentially includes sky near infrared camera
Null images, barrier, or other image etc..Therefore, the rgb value extracting from image information is also different, and not
If the rgb value belonging to vegetation directly judges identification by step s160, operation time is longer, and ties the process performance tool of controller
There is higher requirement.Therefore, it can the rgb value of vegetation is filtered, reject the rgb value of wherein non-plant.Can be by vegetation
Rgb value contrasted with default interval, the rgb value judging vegetation whether in default interval, if not, illustrating that it is non-
The rgb value of vegetation, can directly therefrom reject.Default interval should include rgb under health and non-health situation for the vegetation
Value, so can ensure not delete data by mistake, keep the globality of data.
As Fig. 6, the automatic running device of another embodiment also include vegetation healthalert module, vegetation healthalert mould
By vegetation, whether healthy information is sent to user to block.Specifically, the information of vegetation whether health includes vegetation region, with
And the vegetation health level in this region and/or vegetation Damage Types.
In a kind of embodiment of the present embodiment, vegetation healthalert module 170 includes communication module, communication module and
Individual subscriber smart device communication, by aforementioned vegetation, whether healthy information is sent on individual subscriber smart machine, such as intelligence
Energy mobile phone, Intelligent flat computer, intelligent watch, PC etc..
In one embodiment, the information of vegetation whether health is sent to, with patterned form, the personal intelligence that user holds
Energy equipment, this image conversion information can be garden or the lawn map view of user, thereon in the form of color, word, icon
Indicate vegetation health level and/or the vegetation Damage Types of regional.As indicated vegetation health shape respectively with green, yellow, red
State is good, in, poor；Loosen the soil, have pest and disease damage etc. with the vegetation hydropenia of word or icon sign respective regions, fertilizer deficiency, needs；With numerical value
Indicate numerical value of each healthy indication of plant etc..Certainly, other forms of expression are also feasible.
In the another embodiment of the present embodiment, this information is sent to the intelligence of user in the form of the statement-of-health of garden
Energy equipment, can pass through the suitable method such as mail, short message.Garden statement-of-health is sub-category, the healthy feelings in garden are listed in region
Condition, the overall health of the vegetation in for example each region, pest and disease damage situation, moisture situation, nutrient situation, trace element situation etc.
Deng.
In the another embodiment of the present embodiment, vegetation healthalert module 170 includes the health in the machine
Instruction device, by vegetation, whether healthy information is presented in the machine of automatic running device healthy instruction device, for example, health
Instruction device can be display screen, broadcaster etc..Information particular content and the similar embodiment above of appearance form, specifically
Repeat no more.
Vegetation maintenance advisory information is also sent to user by healthalert module.Specifically, vegetation maintenance advisory information bag
Include suggestion apply fertilizer, water, loosening the soil, weeding, at least one spilling in medicine.Similar, vegetation maintenance advisory information can also be to scheme
The form of shape or report is sent to the personal device of user, such as with map and one or more of extension, word, icon
In conjunction with mode point out user specific region to need execution the action etc. such as such as water, apply fertilizer, will not be described here.
In an alternate embodiment of the invention, healthalert module can only send vegetation the information of health and vegetation maintenance are built
One of view information.
The recognition methodss of the vegetation health status of the automatic running device of another embodiment also include vegetation maintenance module.Plant
By maintenance module, to vegetation, unsound region executes vegetation maintenance action.Specifically, vegetation maintenance action includes: applies fertilizer, pours
Water, loosen the soil, weeding, at least one spilling in medicine, accordingly, vegetation maintenance module includes: fertilising module, module of watering, loosens the soil
Module, weeding module, at least one spilt in medicine module.
Automatic running device, according to the specific health problem of the vegetation detecting, executes one or more maintenances accordingly
Action.For example, when automatic running device detects vegetation hydropenia, execute action of watering；When automatic running device detects plant
When being lacked nutrient, execute fertilising, loosen the soil or weeding activities；When automatic running device detects vegetation and meets with pest and disease damage, hold
Row spills medicine action.
One of vegetation maintenance module or multiple can be the interchangeable adnexa being arranged on automatic running device,
Automatic running device detect need to execute specific maintenance action when, if corresponding particular attachment is fitted without on fuselage,
Then this particular attachment of automatic Picking carries out maintenance action, or sends prompting message, points out user to install this for it and specifically supports
Shield adnexa.
Location equipment is provided with automatic running device, by regional geography positional information and vegetation health status information phase
Associate, as the aforesaid various information of generation, and the basis executing all kinds of actions.Location equipment can be gps equipment
(concrete such as dgps equipment), uwb hi-Fix equipment, picture position identification equipment etc..
Each technical characteristic of embodiment described above can arbitrarily be combined, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic applied in example is all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope of this specification record.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed, but simultaneously
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
Say, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (23)
1. a kind of vegetation health status recognition methodss of automatic running device are it is characterised in that include:
Obtain the image information of vegetation；
Extract the color value of corresponding vegetation from image information, described color value is the rgb value of vegetation；
The rgb value of described vegetation and color value during vegetation healthy growth are carried out contrast identification vegetation whether healthy.
2. recognition methodss according to claim 1 it is characterised in that obtain the image letter of vegetation using near infrared camera
Breath.
3. recognition methodss according to claim 1 are it is characterised in that adopt weber local feature algorithm from image information
Extract the color value of corresponding vegetation.
4. recognition methodss according to claim 1 are it is characterised in that also include:
The rgb value of vegetation is filtered, filters the rgb value rejecting non-vegetation color from the rgb value of vegetation.
5. whether recognition methodss according to claim 4 are it is characterised in that pass through to judge the rgb value of vegetation default
The interval rgb value to vegetation filters.
6. recognition methodss according to claim 5 are it is characterised in that described default interval inclusion vegetation is healthy and non-
Rgb value during health status.
7. recognition methodss according to claim 1 are it is characterised in that color value during described vegetation healthy growth is to correspond to
The interval of r, g and b value, when color value when the described rgb value by vegetation and vegetation healthy growth is contrasted, contrasts institute respectively
Whether the value stating r, g and b in the rgb value of vegetation is in the interval of described corresponding r, g and b value.
8. recognition methodss according to claim 1 are it is characterised in that further comprising the steps of:
By vegetation, whether healthy information is sent to user, and/or
Vegetation maintenance advisory information is sent to user.
9. recognition methodss according to claim 8 are it is characterised in that the information of described vegetation whether health includes vegetation institute
In region, and the vegetation health level in this region and/or vegetation Damage Types；Described vegetation maintenance advisory information includes suggestion
Apply fertilizer, water, loosening the soil, weeding, at least one spilling in medicine.
10. recognition methodss according to claim 1 are it is characterised in that further comprising the steps of:
To vegetation, unsound region executes vegetation maintenance action.
11. recognition methodss according to claim 10 are it is characterised in that described vegetation maintenance action includes: apply fertilizer, pour
Water, loosen the soil, weeding, at least one spilling in medicine.
A kind of 12. automatic running devices it is characterised in that including the identifying system of vegetation health status, described vegetation health shape
Condition identifying system includes:
Acquisition module, for obtaining the image information of vegetation；
Extraction module, for extracting the color value of corresponding vegetation from image information, described color value is the rgb value of vegetation；
Identification module, for the rgb value of described vegetation and color value during vegetation healthy growth are carried out contrast identification vegetation be
No health.
13. automatic running devices according to claim 12 are it is characterised in that described acquisition module is near infrared camera.
14. automatic running devices according to claim 12 are it is characterised in that described extraction module adopts weber local special
Levy the color value that algorithm extracts corresponding vegetation from image information.
15. automatic running devices according to claim 12 are it is characterised in that described identifying system also includes:
Filtering module, for filtering to the rgb value of vegetation, filters the rgb rejecting non-vegetation color from the rgb value of vegetation
Value.
16. automatic running devices according to claim 15 are it is characterised in that described filtering module passes through to judge vegetation
Whether rgb value filters in the default interval rgb value to vegetation.
17. automatic running devices according to claim 16 are it is characterised in that described default interval inclusion vegetation is strong
Rgb value when health and non-health situation.
18. automatic running devices according to claim 12 are it is characterised in that color value during described vegetation healthy growth
For the interval of corresponding r, g and b value, it is right that the rgb value of vegetation and color value during vegetation healthy growth are carried out by described identification module
Than when, whether the value contrasting r, g and b in the rgb value of described vegetation respectively in the interval of described corresponding r, g and b value.
19. automatic running devices according to claim 12 are it is characterised in that also include vegetation healthalert module, institute
The information of health and/or vegetation maintenance advisory information are sent to user by vegetation to state vegetation healthalert module.
20. automatic running devices according to claim 19 are it is characterised in that described vegetation healthalert module includes leading to
Letter module, described communication module and individual subscriber smart device communication, by the aforementioned vegetation whether information of health and/or vegetation
Maintenance advisory information is sent on individual subscriber smart machine.
21. automatic running devices according to claim 19 are it is characterised in that the information of described vegetation whether health includes
Vegetation region, and the vegetation health level in this region and/or vegetation Damage Types；Described vegetation maintenance advisory information bag
Include suggestion apply fertilizer, water, loosening the soil, weeding, at least one spilling in medicine.
22. automatic running devices according to claim 12 are it is characterised in that also include vegetation maintenance module, described plant
By maintenance module, to vegetation, unsound region executes vegetation maintenance action.
23. automatic running devices according to claim 22 are it is characterised in that described vegetation maintenance module includes: fertilising
Module, module of watering, module of loosening the soil, weeding module, at least one spilt in medicine module.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510424150X | 2015-07-17 | ||
| CN201510424150 | 2015-07-17 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106355609A true CN106355609A (en) | 2017-01-25 |
Family
ID=57843244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610554929.8A Pending CN106355609A (en) | 2015-07-17 | 2016-07-15 | Automatic walking device and vegetation health condition recognition method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106355609A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107192674A (en) * | 2017-05-25 | 2017-09-22 | 河南嘉禾智慧农业科技有限公司 | The collection system of Internet of things of plant growth in a kind of monitoring greenhouse |
| CN107682456A (en) * | 2017-11-07 | 2018-02-09 | 蔡璟 | A kind of intelligent gardens nursing system based on image and root detection |
| CN107766837A (en) * | 2017-11-07 | 2018-03-06 | 蔡璟 | The gardens maintenance system that a kind of distinguished point based compares |
| CN107844771A (en) * | 2017-11-03 | 2018-03-27 | 深圳春沐源控股有限公司 | Method, system, computer installation and the storage medium of crop production management |
| CN110347144A (en) * | 2018-04-03 | 2019-10-18 | 苏州宝时得电动工具有限公司 | From mobile device and its self-learning method, readable storage medium storing program for executing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101766106A (en) * | 2009-12-31 | 2010-07-07 | 上海量科电子科技有限公司 | Plant-nursing terminal with prompt function, system and system implementation method |
| US20130136312A1 (en) * | 2011-11-24 | 2013-05-30 | Shih-Mu TSENG | Method and system for recognizing plant diseases and recording medium |
| CN204325916U (en) * | 2014-11-05 | 2015-05-13 | 中铁二院工程集团有限责任公司 | Railroad bridge intelligent detection device |
| CN204515530U (en) * | 2014-12-30 | 2015-07-29 | 苏州宝时得电动工具有限公司 | Automatic running gear |
-
2016
- 2016-07-15 CN CN201610554929.8A patent/CN106355609A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101766106A (en) * | 2009-12-31 | 2010-07-07 | 上海量科电子科技有限公司 | Plant-nursing terminal with prompt function, system and system implementation method |
| US20130136312A1 (en) * | 2011-11-24 | 2013-05-30 | Shih-Mu TSENG | Method and system for recognizing plant diseases and recording medium |
| CN204325916U (en) * | 2014-11-05 | 2015-05-13 | 中铁二院工程集团有限责任公司 | Railroad bridge intelligent detection device |
| CN204515530U (en) * | 2014-12-30 | 2015-07-29 | 苏州宝时得电动工具有限公司 | Automatic running gear |
Non-Patent Citations (2)
| Title |
|---|
| 赵淑元: "水稻纹枯病的图象处理技术及生理生化反应研究", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
| 黄高鉴，王双喜: "温室植物病害数字化处理中图象分割方法的研究", 《农业技术与装备》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107192674A (en) * | 2017-05-25 | 2017-09-22 | 河南嘉禾智慧农业科技有限公司 | The collection system of Internet of things of plant growth in a kind of monitoring greenhouse |
| CN107844771A (en) * | 2017-11-03 | 2018-03-27 | 深圳春沐源控股有限公司 | Method, system, computer installation and the storage medium of crop production management |
| CN107682456A (en) * | 2017-11-07 | 2018-02-09 | 蔡璟 | A kind of intelligent gardens nursing system based on image and root detection |
| CN107766837A (en) * | 2017-11-07 | 2018-03-06 | 蔡璟 | The gardens maintenance system that a kind of distinguished point based compares |
| CN110347144A (en) * | 2018-04-03 | 2019-10-18 | 苏州宝时得电动工具有限公司 | From mobile device and its self-learning method, readable storage medium storing program for executing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106355609A (en) | Automatic walking device and vegetation health condition recognition method thereof | |
| Anand et al. | An application of image processing techniques for detection of diseases on brinjal leaves using k-means clustering method | |
| Aquino et al. | A new methodology for estimating the grapevine-berry number per cluster using image analysis | |
| EP2548147B1 (en) | Method to recognize and classify a bare-root plant | |
| CN106250874B (en) | Recognition methods and the device of a kind of dress ornament and carry-on articles | |
| Zhou et al. | Using colour features of cv.‘Gala’apple fruits in an orchard in image processing to predict yield | |
| Kurniawati et al. | Investigation on image processing techniques for diagnosing paddy diseases | |
| Fang | Rice crop area estimation of an administrative division in China using remote sensing data | |
| CN104598908A (en) | Method for recognizing diseases of crop leaves | |
| KR20150000435A (en) | Recongnition of Plant Growth Steps and Environmental Monitoring System and Method thereof | |
| CN102915446A (en) | Plant disease and pest detection method based on SVM (support vector machine) learning | |
| CN109711345A (en) | A kind of flame image recognition methods, device and its storage medium | |
| Lavania et al. | Novel method for weed classification in maize field using Otsu and PCA implementation | |
| Kurniawati et al. | Texture analysis for diagnosing paddy disease | |
| Ke et al. | Active contour and hill climbing for tree crown detection and delineation | |
| CN107403180A (en) | A kind of numeric type equipment detection recognition method and system | |
| CN113377062B (en) | Multifunctional early warning system with disease and pest damage and drought monitoring functions | |
| CN115661647A (en) | Timed inspection method for tree planting growth conditions | |
| CN105427279A (en) | Grassland drought status monitoring system based on and machine vision and Internet of things, grassland drought status monitoring method | |
| CN107064159B (en) | Device and system for detecting and judging growth trend according to yellow leaves of plants | |
| Finn et al. | Unsupervised spectral-spatial processing of drone imagery for identification of pine seedlings | |
| Lee et al. | Applying cellular automata to hyperspectral edge detection | |
| Reza et al. | Automatic counting of rice plant numbers after transplanting using low altitude uav images | |
| Sannakki et al. | SVM-DSD: SVM based diagnostic system for the detection of pomegranate leaf diseases | |
| CN113807143A (en) | Crop connected domain identification method and device and operation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170125 |
|
| RJ01 | Rejection of invention patent application after publication |