CN103903252A - Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method - Google Patents
Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method Download PDFInfo
- Publication number
- CN103903252A CN103903252A CN201210585918.8A CN201210585918A CN103903252A CN 103903252 A CN103903252 A CN 103903252A CN 201210585918 A CN201210585918 A CN 201210585918A CN 103903252 A CN103903252 A CN 103903252A
- Authority
- CN
- China
- Prior art keywords
- cotton
- image
- insect pest
- pest situation
- seedling
- 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
Images
Landscapes
- Catching Or Destruction (AREA)
Abstract
An automatic cotton field pest situation monitoring device and an automatic cotton field pest situation monitoring method are used for automatically monitoring pest situation of cotton seedlings of a cotton field in real time. The method comprises the following steps: cotton seedling image information of a cotton field is acquired in real time; the cotton seedling image information is processed, and leaf contour information of cotton seedlings of the cotton field and leaf characteristics in leaf contours are extracted; and pest situation of the cotton field is judged according to the leaf characteristics so as to monitor cotton seedling pest information of the cotton field in real time. The device comprises a fixing frame fixed in a cotton field according to areas, an image acquisition device installed on the fixing frame and used for acquiring image information of cotton seedlings in real time, an image transmission device installed on the fixing frame and used for transmitting the cotton seedling image information acquired by the image acquisition device in real time, and a monitoring center connected with the image transmission device and including an image receiving device and an image analysis system. The method is adopted to analyze cotton seedling image information so as to monitor cotton seedling pest information of a cotton field in real time.
Description
Technical field
The present invention relates to a kind of automatic monitoring technical of cotton field, particularly a kind of cotton field insect pest situation automated watch-keeping facility and monitoring method.
Background technology
At present, in the plantation of cotton field, the insect pest situation of cotton seedling is normally by manually cotton seedling being observed, thereby the foundation of the field management such as deinsectization spray medicine, irrigation and fertilising is carried out in conduct to cotton seedling.But manual observation is owing to being subject to the restriction of the condition such as time, weather, insect pest situation to cotton seedling etc. is analyzed grasp in real time, cannot prevent in time and control insect pest occurs, and labour intensity is large, be affected by human factors serious, convenience is poor, in the plantation of current domestic and international cotton seedling, not yet retrieves about the insect pest of cotton seedling being carried out to the research of monitoring automatically.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of cotton field insect pest situation automated watch-keeping facility and the monitoring method that can carry out to the insect pest of Cotton seedling real-time automatic monitoring.
To achieve these goals, the invention provides a kind of cotton field insect pest situation automatic monitoring method, for the insect pest situation of Cotton seedling is carried out to real-time automatic monitoring, wherein, comprise the steps:
The cotton seedling image information in S1, Real-time Collection cotton field;
S2, described cotton seedling image information is processed, extracted the leaf characteristic in blade face profile information and this blade face profile of described Cotton seedling, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, described leaf characteristic comprises: insect pest situation appears in cotton leaf change color, cotton leaf metamorphosis and cotton leaf.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, described step S2 comprises:
S21, described cotton seedling image information is carried out to image cut apart, the colouring information that utilizes Q component in YIQ color space to extract the cotton seedling in described cotton seedling image information obtains cotton seedling image information after treatment, then uses cotton seedling image information after treatment described in OTSU automatic threshold method binaryzation;
The projection location of S22, the cotton seedling of individual plant, carries out respectively vertical and horizontal projection to the cotton seedling image information after binaryzation, and sets boundary threshold to determine the particular location of the cotton seedling of multiple individual plants;
The profile of S23, the cotton seedling of individual plant extracts, and adopts Robert edge detection algorithm to extract the blade face contour edge of single cotton plant and the hole information of profile inside, described blade face;
S24, calculate hole numerical value, after described hole information is adopted to neighbours territory zone marker algorithm tag and calculate hole numerical value;
S25, judge insect pest situation information, by described hole numerical value and an experience threshold, if described hole numerical value is greater than described empirical value, insect pest has occurred; If described hole numerical value is less than described empirical value, occur without insect pest.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, described in described OTSU automatic threshold method binaryzation, the method for cotton seedling image information after treatment is: establishing gray level image gray level is L, and tonal range is [0, L-1], utilize the optimal threshold of OTSU algorithm computed image to be:
t=Max[w0(t)*(u0(t)-u)^2+w1(t)*(u1(t)-u)^2)],
Wherein, in the time that the threshold value of cutting apart is t, w0 is background ratio, and u0 is background mean value, and w1 is prospect ratio, and u1 is prospect average, and the average that u is entire image makes the t of above transition formula evaluation maximum, is the optimal threshold of cutting apart image.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, described neighbours' field mark algorithm comprises the steps:
S241, select a gauge point, judge in the neighbours territory of described gauge point the most left, go up whether there are other points most, if all there is no other points, be judged as the beginning in a new region;
If a little the most left in the neighbours territory of the described gauge point of S242, goes up not point most, the value that described in mark, gauge point is the most left point; If the most left in the neighbours territory of described gauge point do not have a little, go up most a little, described in mark, gauge point is the value that goes up point most;
If in the neighbours territory of the described gauge point of S243 the most left, go up all a little the most left described in being, the value that goes up the minimum point in two points most of gauge point described in mark, and the value that other are greater than to the point of this minimum is revised as the value of point most.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, the Roberts edge detection operator of described Robert edge detection algorithm is a kind of operator that utilizes local difference operator to find edge, its computing formula is as follows:
G(x,y)=sqrt((f(x,y)-f(x+1,y+1))*(f(x,y)-f(x+1,y+1))+(f(x+1,y)-f(x,y+1))*(f(x+1,y)-f(x,y+1)))
Wherein, f (x, y) is input picture, and g (x, y) is output image.
Above-mentioned cotton field insect pest situation automatic monitoring method, wherein, described empirical value is.
In order to realize better above-mentioned purpose, the present invention also provides a kind of cotton field insect pest situation automated watch-keeping facility, for the insect pest situation of Cotton seedling is carried out to real-time automatic monitoring, wherein, comprising:
Fixed mount, is fixed in cotton field according to region;
Image collecting device, is arranged on described fixed mount, for the image information of the cotton seedling of Real-time Collection;
Image transmission, is arranged on described fixed mount, for transmitting the cotton seedling image information of described image collecting device Real-time Collection;
Surveillance center, is connected with described image transmission, comprising:
Image received device, for receiving the cotton seedling image information of described image transmission transmission;
Image analysis system, be connected with described image received device, adopt the cotton field insect pest situation automatic monitoring method described in any one in the claims 1-7 to analyze described cotton seedling image information, obtain the leaf characteristic in described cotton field, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
Above-mentioned cotton field insect pest situation automated watch-keeping facility, wherein, described image collector is set to thermal camera, and described image transmission is cdma wireless video transmission device.
Above-mentioned cotton field insect pest situation automated watch-keeping facility, wherein, also comprise image acquisition adjusting gear, be arranged on described fixed mount and with described image collecting device and be connected, described image acquisition adjusting gear comprises position adjusting mechanism, height adjustment mechanism and angle adjusting mechanism.
Technique effect of the present invention is:
Cotton field of the present invention insect pest situation automated watch-keeping facility is fixed on field according to region, send the cotton seedling image information of camera acquisition to strange land Indoor Video computing machine by wireless launcher, utilize image analysis system to analyze cotton seedling image, thereby grasp in real time the insect pest situation information in cotton field.The present invention has the monitoring of round-the-clock 24 hours strange lands, video automatic acquisition and processing, monitoring range and area can be in harmonious proportion the functions such as automatic analysis cotton field insect pest situation.
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
Accompanying drawing explanation
Fig. 1 is the automated watch-keeping facility structural representation of one embodiment of the invention;
Fig. 2 is cotton seedling Insect infestation monitoring schematic diagram of the present invention;
Fig. 3 is the process flow diagram of the automatic monitoring method of one embodiment of the invention;
Fig. 4 is the image analysis process schematic diagram of the automatic monitoring method of one embodiment of the invention;
Fig. 5 A-5D is the image processing effect figure of the cotton seedling of insect pest of the appearance spot of one embodiment of the invention;
Fig. 6 A-6D is the image processing effect figure of the cotton seedling of the appearance of one embodiment of the invention insect pest of incising.
Wherein, Reference numeral
1 fixed mount
2 image collecting devices
3 image transmissions
4 Surveillance center
41 image received devices
42 image analysis systems
5 image acquisition adjusting gears
51 position adjusting mechanisms
52 height adjustment mechanisms
53 angle adjusting mechanisms
S1, S2 step
Embodiment
Below in conjunction with accompanying drawing, structural principle of the present invention and principle of work are described in detail:
Referring to Fig. 1 and Fig. 2, the automated watch-keeping facility structural representation that Fig. 1 is one embodiment of the invention, Fig. 2 is cotton seedling Insect infestation monitoring schematic diagram of the present invention.Cotton field of the present invention insect pest situation automated watch-keeping facility, for the insect pest situation of Cotton seedling is carried out to real-time automatic monitoring, comprising: fixed mount 1, is fixed in cotton field according to region; Image collecting device 2, is arranged on described fixed mount 1, for the image information of the cotton seedling of Real-time Collection; Image transmission 3, is arranged on described fixed mount 1, for transmitting the cotton seedling image information of described image collecting device 2 Real-time Collections; Surveillance center 4, is connected with described image transmission 3, comprising: image received device 41, the cotton seedling image information of transmitting for receiving described image transmission 3; Image analysis system 42, be connected with described image received device 41, adopt following cotton field insect pest situation automatic monitoring method to analyze described cotton seedling image information, obtain the leaf characteristic in described cotton field, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
In the present embodiment, described image collecting device 2 is preferably thermal camera to realize round-the-clock detection, described image transmission 3 is preferably cdma wireless video transmission device so that the stable instantaneous transmission of carrying out rapidly image, Surveillance center 4 is preferably made up of fixing IP server and supervisory control comuter, and its image received device 41 and image analysis system 42 can be separately positioned on wherein.In order to improve picture quality, obtain shooting effect better, the present invention also can comprise image acquisition adjusting gear 5, be arranged on described fixed mount 1 and with described image collecting device 2 and be connected, for adjusting shooting angle and the camera site of described image collecting device 2, described image acquisition adjusting gear 5 comprises position adjusting mechanism 51, height adjustment mechanism 52 and angle adjusting mechanism 53.Because the method for this distance, height and angular adjustment all can adopt more ripe prior art, as long as can reach the object that regulates the shooting angle of described image collecting device 2 and camera site to obtain best shooting effect, the concrete structure of this image acquisition adjusting gear 5 is not limited.The cotton field insect pest situation automatic monitoring method below image analysis system 42 being adopted is described in detail.Referring to Fig. 3, the process flow diagram of the automatic monitoring method that Fig. 3 is one embodiment of the invention.This monitoring method comprises the steps:
The cotton seedling image information in step S1, Real-time Collection cotton field;
Step S2, described cotton seedling image information is processed, extracted the leaf characteristic in blade face profile information and this blade face profile of described Cotton seedling, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
Wherein, monitoring device of the present invention can carry out leaf characteristic identification to following cotton seedling insect pest situation, and described leaf characteristic comprises:
1) cotton leaf change color: macula lutea, erythema, yellowish-white spot or blackspot, appear in for example chlorosis;
2) cotton leaf metamorphosis: for example become to incise shape or hole, crispatura to the back side;
3) there is insect pest situation in cotton leaf: ovum or the adult of for example insect are positioned on blade.
Wherein, described step S2 comprises:
Step S21, described cotton seedling image information is carried out to image cut apart, utilize the colouring information of the cotton seedling in the described cotton seedling image information of Q component extraction in YIQ color space, obtain cotton seedling image information after treatment, then use cotton seedling image information after treatment described in OTSU automatic threshold method binaryzation;
Wherein, described in described OTSU automatic threshold method binaryzation, the method for cotton seedling image information after treatment is: establishing gray level image gray level is L, and tonal range is [0, L-1], utilizes the optimal threshold of OTSU algorithm computed image to be:
t=Max[w0(t)*(u0(t)-u)^2+w1(t)*(u1(t)-u)^2)],
Wherein, in the time that the threshold value of cutting apart is t, w0 is background ratio, and u0 is background mean value, and w1 is prospect ratio, and u1 is prospect average, and the average that u is entire image makes the t of above transition formula evaluation maximum, is the optimal threshold of cutting apart image.
The projection location of step S22, the cotton seedling of individual plant, only comprise black picture element and white pixel through in the image of binaryzation, cotton seedling image information after binaryzation is carried out respectively to vertical and horizontal projection, and set boundary threshold to determine the particular location of the cotton seedling of multiple individual plants;
The profile of step S23, the cotton seedling of individual plant extracts, and adopts Robert edge detection algorithm to extract the blade face contour edge of single cotton plant and the hole information of profile inside, described blade face;
Wherein, the Roberts edge detection operator of described Robert edge detection algorithm is a kind of operator that utilizes local difference operator to find edge, and its computing formula is as follows:
G(x,y)=sqrt((f(x,y)-f(x+1,y+1))*(f(x,y)-f(x+1,y+1))+(f(x+1,y)-f(x,y+1))*(f(x+1,y)-f(x,y+1)))
Wherein, f (x, y) is input picture, and g (x, y) is output image.
Step S24, calculating hole numerical value T, adopt neighbours territory zone marker algorithm tag to described hole information, then adds up and can obtain hole numerical value T;
Wherein, described neighbours' field mark algorithm comprises the steps:
S241, select a gauge point, judge in the neighbours territory of described gauge point the most left, go up whether there are other points most, if all there is no other points, be judged as the beginning in a new region;
If a little the most left in the neighbours territory of the described gauge point of S242, goes up not point most, the value that described in mark, gauge point is the most left point; If the most left in the neighbours territory of described gauge point do not have a little, go up most a little, described in mark, gauge point is the value that goes up point most;
If in the neighbours territory of the described gauge point of S243 the most left, go up all a little the most left described in being, the value that goes up the minimum point in two points most of gauge point described in mark, and the value that other are greater than to smallest point is revised as the value of point most.
Step S25, judge insect pest situation information, by described hole numerical value T and an experience threshold, if described hole numerical value is greater than described empirical value, insect pest has occurred; If described hole numerical value is less than described empirical value, occur without insect pest.Described empirical value is preferably 50-200.
Referring to Fig. 4-Fig. 6 D, Fig. 4 is the image analysis process schematic diagram of the automatic monitoring method of one embodiment of the invention, Fig. 5 A-5D is the image processing effect figure of the cotton seedling of insect pest of the appearance spot of one embodiment of the invention, the image processing effect figure of the cotton seedling of insect pest that the appearance that Fig. 6 A-6D is one embodiment of the invention is incised.Describe with a specific embodiment concrete steps that cotton seedling image is analyzed in detail below:
As shown in Figure 4, the method for this cotton seedling insect pest situation image processing is specially:
First the cotton field image collecting is carried out to image and cut apart, the cotton seedling of individual plant is oriented in projection, then it is carried out to the extraction of cotton plant profile, and calculates blade face pore quantity, compares with given threshold value, judges the insect pest information in cotton field with this.
(1) green plants is cut apart, and referring to Fig. 5 A, 5B, Fig. 6 A, 6B, wherein, Fig. 5 A is the cotton seedling of insect pest that occurs erythema, and Fig. 5 B is YIQ_Q index gray level image, and the cotton seedling of the insect pest of incising appears in Fig. 6 A, and Fig. 6 B is YIQ_Q index gray level image
Utilize the Q component in YIQ color space to extract the colouring information of green plants, then adopt Otsu automatic threshold method binary image.YIQ color space belongs to NTSC system.Here Y refers to the legibility of color, i.e. brightness.Y is exactly gradation of image value in fact, and I and Q refer to finger tone, i.e. the attribute of Description Image color and saturation degree.In YIQ color space, the monochrome information of Y representation in components image, I component and Q component are carrying colouring information, and I component represents the change color from orange to cyan, and Q component represents from purple to yellowish green change color.YIQ color space has advantages of can be by the luminance component separation and Extraction in image out, and be the relation of linear transformation between YIQ color space and RGB color space, calculated amount is little, Clustering features is also relatively good, can adapt to the occasion that intensity of illumination constantly changes, therefore can be effectively for Color Image Processing.
The corresponding relation of RGB and YIQ represents with equation below:
Y=0.299R+0.587G+0.114B
I=0.596R-0.275G-0.321B
Q=0.212R-0.523G+0.311B
OTSU algorithm also claims poor method between maximum kind, is sometimes also referred to as Otsu algorithm, is considered to image and cuts apart the optimal algorithm that middle threshold value is chosen, and calculates simply, is not subject to the impact of brightness of image and contrast, therefore in Digital Image Processing, is widely used.It is the gamma characteristic by image, and image is divided into background and prospect two parts.Inter-class variance between background and prospect is larger, illustrates that the two-part difference of composing images is larger, is divided into prospect and all can causes two parts difference to diminish when part prospect mistake is divided into background or part background mistake.Therefore, make to mean cutting apart of inter-class variance maximum misclassification probability minimum.
If gray level image gray level is L, tonal range is [0, L-1], utilizes the optimal threshold of OTSU algorithm computed image to be:
t=Max[w0(t)*(u0(t)-u)^2+w1(t)*(u1(t)-u)^2)]
Variable declaration wherein: in the time that the threshold value of cutting apart is t, w0 is background ratio, and u0 is background mean value, and w1 is prospect ratio, and u1 is prospect average, the average that u is entire image.
Make the t of above transition formula evaluation maximum, be the optimal threshold of cutting apart image.
(2) the cotton seedling of projection location individual plant, referring to Fig. 5 C, Fig. 6 C, wherein, Fig. 5 C, Fig. 6 C are Otsu automatic threshold binary image,
Only comprise black picture element (background) and white pixel (target) through in the image of binaryzation, by vertical and horizontal projection, determine the particular location of cotton seedling according to the corresponding boundary threshold of setting (rule of thumb determining).
(3) cotton plant profile extracts, and referring to Fig. 5 D, Fig. 6 D, wherein, Fig. 5 D, Fig. 6 D are Robert and extract edge, image after zone marker
Adopt Robert edge detection algorithm to extract the contour edge of single cotton plant, the method has not only been extracted the profile of blade, and the insect pest information of blade interior (being hole information) is also extracted.
Roberts edge detection operator is a kind of operator that utilizes local difference operator to find edge, and its formula is as follows
G(x,y)=sqrt((f(x,y)-f(x+1,y+1))*(f(x,y)-f(x+1,y+1))+(f(x+1,y)-f(x,y+1))*(f(x+1,y)-f(x,y+1)))
Wherein f (x, y) is input picture, and g (x, y) is output image.
(4) calculate cavity, blade face quantity
After the hole information of blade interior is adopted to neighbours territory zone marker algorithm tag and calculate its quantity.
The basic step of neighbours' field mark algorithm is:
1) judge the most left in this neighbours territory, whether go up point most, if points not all represents the beginning in a new region.
2), if a little the most left in this neighbours territory gone up not point most, this point of mark is the value of left point; If the most left in this neighbours territory do not have a little, go up most a little, this point of mark is for going up most the value of point.
3) if a little the most left in this neighbours territory gone up all a little most, this point of mark is the minimum gauge point in these two, and revises and be labeled as greatly tick marks.
(5) judge insect pest situation information
The hole number calculating is compared with empirical value, if hole number is greater than empirical value, there is insect pest in explanation; If hole number is less than empirical value, explanation does not have insect pest to occur.
Cotton field of the present invention insect pest situation automated watch-keeping facility is fixed on field according to region, send the cotton seedling image information of camera acquisition to strange land Indoor Video computing machine by wireless launcher, utilize image analysis system to analyze cotton seedling image, thereby grasp in real time the insect pest situation information in cotton field.The present invention has the monitoring of round-the-clock 24 hours strange lands, video automatic acquisition and processing, monitoring range and area can be in harmonious proportion the functions such as automatic analysis cotton field insect pest situation.
Certainly; the present invention also can have other various embodiments; in the situation that not deviating from spirit of the present invention and essence thereof; those of ordinary skill in the art are when making according to the present invention various corresponding changes and distortion, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.
Claims (10)
1. a cotton field insect pest situation automatic monitoring method, for the insect pest situation of Cotton seedling is carried out to real-time automatic monitoring, is characterized in that, comprises the steps:
The cotton seedling image information in S1, Real-time Collection cotton field;
S2, described cotton seedling image information is processed, extracted the leaf characteristic in blade face profile information and this blade face profile of described Cotton seedling, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
2. cotton field as claimed in claim 1 insect pest situation automatic monitoring method, is characterized in that, described leaf characteristic comprises: insect pest situation appears in cotton leaf change color, cotton leaf metamorphosis and cotton leaf.
3. cotton field as claimed in claim 1 or 2 insect pest situation automatic monitoring method, is characterized in that, described step S2 comprises:
S21, described cotton seedling image information is carried out to image cut apart, the colouring information that utilizes Q component in YIQ color space to extract the cotton seedling in described cotton seedling image information obtains cotton seedling image information after treatment, then uses cotton seedling image information after treatment described in OTSU automatic threshold method binaryzation;
The projection location of S22, the cotton seedling of individual plant, carries out respectively vertical and horizontal projection to the cotton seedling image information after binaryzation, and sets boundary threshold to determine the particular location of the cotton seedling of multiple individual plants;
The profile of S23, the cotton seedling of individual plant extracts, and adopts Robert edge detection algorithm to extract the blade face contour edge of single cotton plant and the hole information of profile inside, described blade face;
S24, calculate hole numerical value, after described hole information is adopted to neighbours territory zone marker algorithm tag and calculate hole numerical value;
S25, judge insect pest situation information, by described hole numerical value and an experience threshold, if described hole numerical value is greater than described empirical value, insect pest has occurred; If described hole numerical value is less than described empirical value, occur without insect pest.
4. cotton field as claimed in claim 3 insect pest situation automatic monitoring method, it is characterized in that, described in described OTSU automatic threshold method binaryzation, the method for cotton seedling image information after treatment is: establishing gray level image gray level is L, tonal range is [0, L-1], utilize the optimal threshold of OTSU algorithm computed image to be:
t=Max[w0(t)*(u0(t)-u)^2+w1(t)*(u1(t)-u)^2)],
Wherein, in the time that the threshold value of cutting apart is t, w0 is background ratio, and u0 is background mean value, and w1 is prospect ratio, and u1 is prospect average, and the average that u is entire image makes the t of above transition formula evaluation maximum, is the optimal threshold of cutting apart image.
5. cotton field as claimed in claim 3 insect pest situation automatic monitoring method, is characterized in that, described neighbours' field mark algorithm comprises the steps:
S241, select a gauge point, judge in the neighbours territory of described gauge point the most left, go up whether there are other points most, if all there is no other points, be judged as the beginning in a new region;
If a little the most left in the neighbours territory of the described gauge point of S242, goes up not point most, the value that described in mark, gauge point is the most left point; If the most left in the neighbours territory of described gauge point do not have a little, go up most a little, described in mark, gauge point is the value that goes up point most;
If in the neighbours territory of the described gauge point of S243 the most left, go up all a little the most left described in being, the value that goes up the minimum point in two points most of gauge point described in mark, and the value that other are greater than to smallest point is revised as the value of point most.
6. cotton field as claimed in claim 3 insect pest situation automatic monitoring method, is characterized in that, the Roberts edge detection operator of described Robert edge detection algorithm is a kind of operator that utilizes local difference operator to find edge, and its computing formula is as follows:
G(x,y)=sqrt((f(x,y)-f(x+1,y+1))*(f(x,y)-f(x+1,y+1))+(f(x+1,y)-f(x,y+1))*(f(x+1,y)-f(x,y+1)))
Wherein, f (x, y) is input picture, and g (x, y) is output image.
7. cotton field as claimed in claim 6 insect pest situation automatic monitoring method, is characterized in that, described empirical value is.
8. a cotton field insect pest situation automated watch-keeping facility, for the insect pest situation of Cotton seedling is carried out to real-time automatic monitoring, is characterized in that, comprising:
Fixed mount, is fixed in cotton field according to region;
Image collecting device, is arranged on described fixed mount, for the image information of the cotton seedling of Real-time Collection;
Image transmission, is arranged on described fixed mount, for transmitting the cotton seedling image information of described image collecting device Real-time Collection;
Surveillance center, is connected with described image transmission, comprising:
Image received device, for receiving the cotton seedling image information of described image transmission transmission;
Image analysis system, be connected with described image received device, adopt the cotton field insect pest situation automatic monitoring method described in any one in the claims 1-7 to analyze described cotton seedling image information, obtain the leaf characteristic in described cotton field, judge the insect pest situation in described cotton field according to described leaf characteristic, with the cotton seedling insect pest information in cotton field described in Real-Time Monitoring.
9. cotton field as claimed in claim 8 insect pest situation automated watch-keeping facility, is characterized in that, described image collector is set to thermal camera, and described image transmission is cdma wireless video transmission device.
10. cotton field insect pest situation automated watch-keeping facility as claimed in claim 8 or 9, it is characterized in that, also comprise image acquisition adjusting gear, be arranged on described fixed mount and with described image collecting device and be connected, described image acquisition adjusting gear comprises position adjusting mechanism, height adjustment mechanism and angle adjusting mechanism.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210585918.8A CN103903252A (en) | 2012-12-28 | 2012-12-28 | Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210585918.8A CN103903252A (en) | 2012-12-28 | 2012-12-28 | Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103903252A true CN103903252A (en) | 2014-07-02 |
Family
ID=50994559
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210585918.8A Pending CN103903252A (en) | 2012-12-28 | 2012-12-28 | Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103903252A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104539916A (en) * | 2015-02-02 | 2015-04-22 | 广西牛博物联信息技术有限公司 | Remote early warning system for Pseudonoorda minor Munroe |
CN104778686A (en) * | 2015-03-23 | 2015-07-15 | 无锡中科智能农业发展有限责任公司 | Tissue culture prewarning method and system based on scab monitoring |
CN104776814A (en) * | 2015-04-20 | 2015-07-15 | 湖南农业大学 | Rice leaf shape acquisition device and rice leaf shape parameter extraction method |
CN104992439A (en) * | 2015-06-26 | 2015-10-21 | 广州铁路职业技术学院 | Device and method for detecting insect pests of leaves of crops |
CN105023272A (en) * | 2015-06-26 | 2015-11-04 | 广州铁路职业技术学院 | Crop leaf insect pest detection method and system |
CN105493840A (en) * | 2015-12-11 | 2016-04-20 | 卢志文 | System for monitoring growth condition of plant wall |
CN105548222A (en) * | 2015-12-31 | 2016-05-04 | 东北大学 | Cereal crop online pest and disease damage detecting device |
CN106097119A (en) * | 2016-06-14 | 2016-11-09 | 广州大气候农业科技有限公司 | Harvester, server and information gathering, push, obtain and sending method |
CN106778888A (en) * | 2016-12-27 | 2017-05-31 | 浙江大学 | A kind of orchard pest and disease damage survey system and method based on unmanned aerial vehicle remote sensing |
CN108376402A (en) * | 2018-04-27 | 2018-08-07 | 安徽农业大学 | Trialeurodes vaporariorum community growth state analysis device and method under a kind of off-line state |
CN110393176A (en) * | 2019-07-08 | 2019-11-01 | 深圳职业技术学院 | Plant maintenance intelligence control system and method based on Internet of Things |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000023508A (en) * | 1998-07-08 | 2000-01-25 | Bio Oriented Technol Res Advancement Inst | Judgement of embryo position in aligned seeding machine |
CN201869599U (en) * | 2010-11-12 | 2011-06-22 | 中国气象局气象探测中心 | Automatic observation device for development and growth of crops |
CN102339378A (en) * | 2010-07-22 | 2012-02-01 | 中国农业机械化科学研究院 | Method and device for automatically extracting cotton seeds |
-
2012
- 2012-12-28 CN CN201210585918.8A patent/CN103903252A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000023508A (en) * | 1998-07-08 | 2000-01-25 | Bio Oriented Technol Res Advancement Inst | Judgement of embryo position in aligned seeding machine |
CN102339378A (en) * | 2010-07-22 | 2012-02-01 | 中国农业机械化科学研究院 | Method and device for automatically extracting cotton seeds |
CN201869599U (en) * | 2010-11-12 | 2011-06-22 | 中国气象局气象探测中心 | Automatic observation device for development and growth of crops |
Non-Patent Citations (3)
Title |
---|
宋怀波 等: "一种新的复杂区域孔洞填充算法", 《桂林电子科技大学学报》 * |
张秀彬 等: "《汽车智能化技术原理》", 31 March 2011 * |
陈佳娟 等: "采用计算机视觉进行棉花虫害程度的自动测定", 《农业工程学报》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104539916A (en) * | 2015-02-02 | 2015-04-22 | 广西牛博物联信息技术有限公司 | Remote early warning system for Pseudonoorda minor Munroe |
CN104539916B (en) * | 2015-02-02 | 2017-12-01 | 广西牛博物联信息技术有限公司 | A kind of EW system for Pseudonoorda minor insect pest |
CN104778686A (en) * | 2015-03-23 | 2015-07-15 | 无锡中科智能农业发展有限责任公司 | Tissue culture prewarning method and system based on scab monitoring |
CN104778686B (en) * | 2015-03-23 | 2017-09-22 | 无锡中科智能农业发展有限责任公司 | A kind of tissue culture method for early warning monitored based on scab |
CN104776814A (en) * | 2015-04-20 | 2015-07-15 | 湖南农业大学 | Rice leaf shape acquisition device and rice leaf shape parameter extraction method |
CN104776814B (en) * | 2015-04-20 | 2018-05-11 | 湖南农业大学 | The leaf harvester of rice and rice Leaf pattern parameter extracting method |
CN104992439A (en) * | 2015-06-26 | 2015-10-21 | 广州铁路职业技术学院 | Device and method for detecting insect pests of leaves of crops |
CN105023272A (en) * | 2015-06-26 | 2015-11-04 | 广州铁路职业技术学院 | Crop leaf insect pest detection method and system |
CN104992439B (en) * | 2015-06-26 | 2020-02-11 | 广州铁路职业技术学院 | Crop leaf pest detection device and detection method thereof |
CN105493840A (en) * | 2015-12-11 | 2016-04-20 | 卢志文 | System for monitoring growth condition of plant wall |
CN105548222A (en) * | 2015-12-31 | 2016-05-04 | 东北大学 | Cereal crop online pest and disease damage detecting device |
CN105548222B (en) * | 2015-12-31 | 2018-09-28 | 东北大学 | A kind of online pest and disease damage detection device of cereal crops |
CN106097119A (en) * | 2016-06-14 | 2016-11-09 | 广州大气候农业科技有限公司 | Harvester, server and information gathering, push, obtain and sending method |
CN106778888A (en) * | 2016-12-27 | 2017-05-31 | 浙江大学 | A kind of orchard pest and disease damage survey system and method based on unmanned aerial vehicle remote sensing |
CN108376402A (en) * | 2018-04-27 | 2018-08-07 | 安徽农业大学 | Trialeurodes vaporariorum community growth state analysis device and method under a kind of off-line state |
CN110393176A (en) * | 2019-07-08 | 2019-11-01 | 深圳职业技术学院 | Plant maintenance intelligence control system and method based on Internet of Things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103903252A (en) | Automatic cotton field pest situation monitoring device and automatic cotton field pest situation monitoring method | |
CN104778686B (en) | A kind of tissue culture method for early warning monitored based on scab | |
CN102759528B (en) | Method for detecting diseases of crop leaves | |
US10729117B2 (en) | Pest monitoring method based on machine vision | |
CN106688705A (en) | Intelligent planting greenhouse and monitoring method used for same | |
US20160260306A1 (en) | Method and device for automated early detection of forest fires by means of optical detection of smoke clouds | |
CN103336966B (en) | A kind of weed images discrimination method being applied to agricultural intelligent machine | |
CN103778628B (en) | Method and system for acquiring disease severity of leaf under open field environment | |
KR101633710B1 (en) | System and method for smart grass management based on image processing and sensors | |
CN107121535B (en) | Effective crop growth environment monitoring system | |
CN106951836A (en) | Crop cover degree extracting method based on priori threshold optimization convolutional neural networks | |
KR101822410B1 (en) | Apparatus for diagnosing growth state of crop organ using crop organ image | |
CN109991911A (en) | A kind of orchard comprehensive monitoring system based on Internet of Things | |
CN110286092B (en) | Crop growth trend analysis system | |
CN103914848B (en) | A kind of farmland image partition method based on wavelet transformation and maximum between-cluster variance | |
CN105894003A (en) | Large-field fruit tree disease monitoring early-warning system based on machine vision | |
CN107564071A (en) | A kind of image recognition meadow method and device | |
CN112106747A (en) | Intelligent agricultural insect pest remote automatic monitoring system | |
CN107609600A (en) | A kind of greenhouse insect-sticking plate insect automatic recognition classification method and system | |
CN102542560A (en) | Method for automatically detecting density of rice after transplantation | |
CN102592118B (en) | Automatic detection method for time emergence of seedling of corns | |
CN113645302A (en) | Greening maintenance intelligent monitoring system based on Internet of things | |
CN111047458A (en) | Farmland monitoring method | |
CN103900498A (en) | Automatic cotton field seedling situation detection method and detection device thereof | |
CN106909898A (en) | Image intelligent analysing terminal and method in straw-returning monitoring |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140702 |