CN104949981A - Automatic detection method and system for cotton five-euphylla period - Google Patents
Automatic detection method and system for cotton five-euphylla period Download PDFInfo
- Publication number
- CN104949981A CN104949981A CN201410111412.2A CN201410111412A CN104949981A CN 104949981 A CN104949981 A CN 104949981A CN 201410111412 A CN201410111412 A CN 201410111412A CN 104949981 A CN104949981 A CN 104949981A
- Authority
- CN
- China
- Prior art keywords
- cotton
- stem
- plant
- image
- subimage
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an automatic detection method for a cotton five-euphylla period. The automatic detection method comprises the following steps: (1) collecting a single-row plant image of a cotton field after final singling and splitting the image into subimages of a cotton single plant; carrying out color division and crop image division to obtain cotton plant subimages after final singling; (2) detecting edges and a skeleton of the plant according all the cotton plant subimages to obtain plant main stems; (3) detecting plant primary side stems on the two sides of the positions of the main stems, taking the primary side stems which form an acute angle on the upper sides of the main stems in the images of the two sides as side stems; and (4) by taking the crossed points of the side stems and the main stems as nodes, determining that a cotton field enters the five-euphylla period when detecting that the quantity of the subimages of two or more than two nodes accounts for more than 50% of the quantity of the cotton plant subimages after final singling. The invention further provides a system for realizing the method. The automatic detection method has an accurate detection result and strong instantaneity; and the automatic observation is realized and the manpower is saved.
Description
Technical field
The invention belongs to Digital Image Processing and agrometeorological observation crossing domain, more specifically, relate to one and to grow cotton five leaf period automatic testing method and systems.
Background technology
Cotton is one of main industrial crops of China, and the output of cotton of China is also in rank first.Five leaf periods of cotton are important steps of cotton growth, are important contents of agrometeorological observation.
For a long time, the main mode of artificial observation record that adopts carries out record to cotton development stage relevant information, and observed result, owing to can be subject to the impact of observation person's subjective factor, causes application condition large; Meanwhile, because the growth cycle of cotton is longer, the scope of cotton planting is comparatively wide, solely utilizes the method manually carrying out observing to take time and effort.
Summary of the invention
For above defect or the Improvement requirement of prior art, the invention provides one to grow cotton five leaf period automatic testing method and systems, its object is to analyze cotton field photo by image processing method, thus judge whether cotton enters five leaf periods, solve current artificial judgment cotton five leaf period thus and take time and effort and inaccurate technical matters.
For achieving the above object, according to one aspect of the present invention, provide one and to grow cotton five leaf period automatic testing methods, it is characterized in that, comprise the following steps:
(1) cotton plants subimage after acquisition final singling: the positive elevational views of the single plant in cotton field after collection final singling; With the search box of applicable cotton plants individual plant image size with certain fractionation step-length, described image is split into subimage; Color segmentation and crop Iamge Segmentation are carried out to described subimage, on the region segmentation result figure of crop dividing method, the region occupied by pixel detected in retaining color segmentation result figure, cotton plants subimage after acquisition final singling;
(2) cotton plants stem is detected: for all cotton plants subimages obtained in step (1), edge detection algorithm is adopted to detect plant just edge, skeleton detection algorithm is adopted to extract plant just skeleton, to plant just edge and plant just skeleton carry out Chain Code Detection and straight-line detection obtains the vertical plant edge of cotton plants and plant skeleton, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem;
(3) cotton plants side stem is detected: by the cotton plants subimage comprising plant stem obtained in step (2), according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side; Both sides image is carried out respectively the first side stem that color segmentation and straight-line detection obtain in the image of both sides, will wherein with stem on the upside of acutangulate just side stem as side stem;
(4) cotton five leaf period is judged: for the cotton plants subimage comprising plant stem obtained in step (2), using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, judge that cotton field enters five leaf periods, otherwise carry out the detection of next day.
Preferably, described cotton five leaf period automatic testing method, step described in it (1) final seedling time judges according to following steps: every day gathers view image under cotton field under the same conditions, utilize dividing method to carry out green segmentation to described image, add up described image Green pixel proportion and be green image coverage; View green image coverage under every day cotton field is compared with view green image coverage under the previous day cotton field, is final seedling time when green image coverage reduces.
Preferably, described cotton five leaf period automatic testing method, carry out the dividing method that green segmentation uses described in it, environment self-adaption dividing method, super green operator dividing method, the crop image partition method based on Mean shift, Fisher linear discriminant method can be adopted.
Preferably, described cotton five leaf period automatic testing method, described in it, the positive elevational views of single plant is through the method process of contrast stretching.
Preferably, described cotton five leaf period automatic testing method, search box described in it is equal with the height of the positive elevational views of described single plant, and the width of described search box is 1/4 to 1/2 of its height, and described fractionation step-length is 1/2 to 5/6 of described search box width.
Preferably, described cotton five leaf period automatic testing method, (2) edge detection algorithm of step described in it and skeleton detection algorithm, adoptable image detective operators has Sobel operator, Roberts operator, LoG operator and Canny operator, preferred Canny operator.
Preferably, described cotton five leaf period automatic testing method, step described in it (2) and step (3) cathetus detect and can adopt Hough transform.
According to another aspect of the present invention, provide one and to grow cotton five leaf period automatic checkout systems, it is characterized in that, comprise cotton plants subimage acquisition module, cotton stem detection module, cotton side stem detection module and cotton five leaf period judge module;
Described cotton plants subimage acquisition module, for gathering the positive elevational views of the single plant in cotton field after final singling, split into cotton plants individual plant subimage, and after described subimage is processed into final singling, cotton plants subimage passes to cotton stem detection module;
Described cotton stem detection module, for extract cotton plants edge and main framing, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem, and described subimage is passed to cotton side stem detection module;
Described cotton side stem detection module, for comprising the cotton plants subimage of plant stem, according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side; Obtain the first side stem in both sides images, will wherein with stem on the upside of acutangulate straight line as side stem, and testing result is passed to cotton five leaf period judge module;
Described cotton five leaf period judge module, for the distribution situation according to stem number in side in cotton plants subimage after final singling, judge whether cotton enters five leaf periods: for the cotton plants subimage comprising plant stem, using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, judge that cotton field enters five leaf periods.
In general, the above technical scheme conceived by the present invention compared with prior art, owing to adopting the methods analyst cotton field photo of image procossing, thus is judged whether cotton field enters five leaf periods, can obtain following beneficial effect:
(1) replace artificial judgment cotton five leaf period, save manpower;
(2) by the method for image procossing, cotton field state can be monitored in real time, report whether cotton field enters five leaf periods at any time, thus be conducive to agrometeorological observation;
(3) carry out analysis chart picture by accurate dividing method, judge five leaf periods by statistics, than artificial judgment, more accurately and reliably;
(4) by rational optimized image process parameter, select the image processing algorithm be applicable to, take into account cotton field image processing speed and treatment effect.
Accompanying drawing explanation
Fig. 1 is cotton five leaf period automatic testing method process flow diagram provided by the invention;
Fig. 2 is the positive elevational views in cotton field;
Fig. 3 is the positive elevational views in cotton field clearly can observing single plant growing way;
Fig. 4 is that after acquisition final singling, cotton plants subimage result figure: Fig. 4 (a) is the former figure of plant subimage, Fig. 4 (b) is contrast stretching result figure, Fig. 4 (c) is color segmentation result figure, Fig. 4 (d) be Mean shift segmentation result figure, Fig. 4 (e) is comprehensive segmentation result figure;
Fig. 5 is view under cotton field;
Fig. 6 carries out the result figure after green segmentation to Fig. 5;
Fig. 7 is view coverage changing trend diagram under cotton field;
Fig. 8 is detection cotton plants stem result figure: Fig. 8 (a) is cotton plants subimage exemplary plot, and Fig. 8 (b) is plant just edge two-value subgraph, and Fig. 8 (c) is plant just skeleton two-value subgraph, and Fig. 8 (d) is stem testing result figure;
Fig. 9 is detection cotton plants side stem result figure: Fig. 9 (a) is cotton plants subimage left hand view, and Fig. 9 (b) is cotton plants subimage right part of flg, and Fig. 9 (c) is side stem testing result figure;
Figure 10 is cotton plants subimage nodal test figure.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.In addition, if below in described each embodiment of the present invention involved technical characteristic do not form conflict each other and just can mutually combine.
Cotton five leaf period automatic testing method provided by the invention, comprises the following steps:
(1) cotton plants subimage after acquisition final singling.
The positive elevational views in cotton field after collection final singling, adopt overhead high 0.35 meter, lens focus is 14 millimeters, and eastwards, with local horizon angle 0 degree, camera resolution is not less than 4,000,000 pixels to horizontal shooting direction.To be a detection period every day, to take w respectively in two each detection periods of camera and open Cotton Images (w=13).Every day is a detection-phase, is conducive to the Chief growth period identifying cotton.Object due to our image procossing is individual plant cotton plants, therefore first will cut by positive elevational views the cotton field after final singling, to obtain the positive elevational views in cotton field clearly can observing single plant growth condition.Due in cotton field forward forward sight sequence chart after the final singling that obtains at us, single plant is distributed in bottom 1/3 scope of whole figure, and therefore the size that cuts of image is preferably " the positive elevational views in cotton field wide " × (1/3 × " height of positive elevational views picture ").After cutting, the positive elevational views of the single plant in cotton field after acquisition final singling.
With the search box of applicable cotton plants individual plant image size with certain fractionation step-length, described image is split into subimage.Preferably, described search box is equal with the height of the positive elevational views of described single plant, and the width of described search box is 1/4 to 1/2 of its height, and described fractionation step-length is 1/2 to 5/6 of described search box width.Rear discovery is observed to the image of individual plant plant, the length breadth ratio of plant is generally 3:1, size due to subimage has influence on integrality and the accuracy of detection, therefore to be more preferably described search box equal with the height of the positive elevational views of described single plant for the large I of subimage, and the width of described search box is 1/3 of its height.Fractionation order has influence on search utility design, and fractionation order preferably from left to right; Split step-size influences to the time that individual plant plant is searched for and precision, split the faster precision of step-length larger fractionation speed lower, the slower precision of step-length less fractionation speed is higher, fractionation step-length is preferably 1/2 to 5/6 of described search box width, in order to ensure each strain detected in single plant and avoid duplicate detection to arrive same strain plant, be more preferably 4/5 of described search box width.
In order to carry out subsequent detection more accurately, first can utilize the method for contrast stretching, highlighting plant.Image to after stretching: adopt the distinct methods such as color segmentation or crop image partition method to obtain individual plant plant segmentation result figure.Cotton plants blade and stem top are green, and stem bottom is rufous.Based on the color characteristic of individual plant cotton plants, preferably, adopting RGB(red/green/blue) relation in color space between three Color Channels carries out green segmentation to subimage and rufous is split.When carrying out green segmentation to image, adopt R, G/R, G/B value as characteristic index, if the relation in image between pixel triple channel value meets R≤200 simultaneously, G/R >=0.9 and G/B >=2.5, then can split green blade substantially; When rufous segmentation is carried out to image, adopt R, R/G, B/G value as characteristic index, if the relation in image between pixel triple channel value meets R>100 simultaneously, R/G >=2.8 and B/G >=0.1, then can substantially rufous branch be split, combining with green and rufous segmentation result, can obtain the segmentation result of individual plant plant.Adopt crop image partition method, utilize spatial information to filter the ground unrest of image in the physical environment of field, preferred crop dividing method is the crop dividing method based on Meanshift, obtains crop image segmentation result.The result of crop image segmentation result and color segmentation is combined, namely on the region segmentation result figure of the crop dividing method based on Mean shift, the region occupied by pixel detected in retaining color segmentation result figure, to obtain cotton plants subimage after final singling.
Because image background in the physical environment of field is complicated, when using the relation in RGB color space between three Color Channels to carry out color segmentation, do not use spatial information, cause in segmentation result, there will be noise and hole.Then adopt crop image partition method antithetical phrase Image Segmentation Using based on Mean shift therefore.Finally, the result of Mean shift and color segmentation is combined, namely in conjunction with space and colouring information, plant can be partitioned into more accurately, obtain cotton plants subimage comparatively clearly.
Final seedling time is determined as follows: every day gathers view image under cotton field under the same conditions, preferably, adopts the camera of overhead high 5 meters, lens focus is 14 millimeters, eastwards, downward 60 degree with local horizon angle, camera resolution is not less than 4,000,000 pixels to horizontal shooting direction.Utilize dividing method to carry out green segmentation to described image, add up described image Green pixel proportion and be green image coverage; View green image coverage under every day cotton field is compared with view green image coverage under the previous day cotton field, is final seedling time when green image coverage reduces.Described dividing method can adopt environment self-adaption dividing method, super green operator dividing method, based on the method such as crop image partition method, Fisher linear discriminant method of Mean shift (see [1] Lei F.Tian.Environmentally adaptive segmentation algorithm for outdoor image segmentation.Computers and electronics in agriculture, 1998,21:153 ~ 168); [2] D.M.Woebbecke, G.E.Meyer, K.Von Bargen, D.A.Mortensen.Color Indices for weed identification under various soil, residue, and lighting conditions.Transactions of the ASAE, 1995,38(1): 259 ~ 269); [3] Zheng L, Zhang J, Wang Q.Mean-shift-based color segmentation of images containing green vegetation.Computers and Electronics in Agriculture, 2009,65:93-98); [4] Zheng L, Shi D, Zhang J.Segmentation of green vegetation of crop canopy images based on mean shift and Fisher linear discriminant.Pattern Recognition Letters, 2010,31(9): 920 ~ 925.).
(2) cotton plants stem is detected.
For all cotton plants subimages obtained in step (1), adopt edge detection algorithm to detect plant just edge, obtain edge two-value subgraph; Adopt skeleton detection algorithm to extract plant just skeleton, obtain skeleton two-value subgraph.Described edge detection algorithm, adoptable image detective operators has Sobel operator, Roberts operator, LoG operator and Canny operator etc., and the Canny operator that preferred edge integrity is stronger carries out rim detection.Described skeleton detection algorithm, the Refinement operation in preferred configuration image processing method.
Edge two-value subgraph and skeleton two-value subgraph carry out Chain Code Detection and straight-line detection, obtain the vertical plant edge of cotton plants and plant skeleton.By edge two-value subgraph and the superposition of skeleton two-value subgraph, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem.Described straight-line detection preferably adopts Hough transform algorithm.
The stem of cotton plants has obvious linear edge, and trunk diameter growth direction is also vertical direction substantially, and the mode detecting vertical direction straight line therefore can be adopted to judge whether have stem to exist in plant edge extracting subimage.By plant operator edge extracting two-value subgraph and plant skeleton line edge extracting two-value subgraph, all distinguish and first adopt chain code to extract straight line, then Hough transform is adopted to carry out straight-line detection to the result that chain code extracts straight line, finally the detection of straight lines result of the detection of straight lines result of operator edge extracting two-value subgraph and skeleton line edge extracting two-value subgraph is merged, final stem testing result can be obtained.
(3) cotton plants side stem is detected.
By the cotton plants subimage comprising plant stem obtained in step (2), according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side.Both sides image is carried out respectively the first side stem that color segmentation and straight-line detection obtain in the image of both sides.
Principle and the step of color segmentation are as follows: when cotton plants grows into five leaf periods, the side stem color of individual plant plant can become rufous, according to the color characteristics of side stem in the image of both sides, first the relation between pixel triple channel value in image is utilized, color segmentation is carried out to the individual plant plant subimage based on stem: adopt R, R/G, B/G value as characteristic index, if the relation in image between pixel triple channel value meets R>100 simultaneously, R/G >=2.8 and B/G >=0.1, then can split rufous side stem substantially.
At both sides image, straight-line detection is carried out to the individual plant plant subimage result figure based on stem after completing color segmentation respectively, preferably, adopt the line detection method of Hough transform.
In the first side stem of both sides image, be considered to side stem with straight line acutangulate on the upside of stem.
(4) cotton five leaf period is judged.
For the cotton plants subimage comprising plant stem obtained in step (2), using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, think that cotton field enters five leaf periods, otherwise carry out the detection of next day.
For program design is convenient, nodes is adopted to represent side stem number, the intersection point of the node on individual plant plant and stem and side stem, when the stem that color segmentation and straight-line detection result judge and side stem do not have intersection point, extend side stem until it is crossing with stem, determine that intersection point is node.Micro-judgment, image generally cannot gather whole node, therefore when detecting that the number of sub-images of more than 2 or 2 nodes accounts for all number of sub-images more than 50%, judges that cotton field enters five leaf periods, otherwise judges that cotton does not enter five leaf periods.
According to described cotton five leaf period automatic testing method, provide one to grow cotton five leaf period automatic checkout systems, it is characterized in that, comprise cotton plants subimage acquisition module, cotton stem detection module, cotton side stem detection module and cotton five leaf period judge module;
Described cotton plants subimage acquisition module, for gathering the positive elevational views of the single plant in cotton field after final singling, split into cotton plants individual plant subimage, and after described subimage is processed into final singling, cotton plants subimage passes to cotton stem detection module;
Described cotton stem detection module, for extract cotton plants edge and main framing, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem, and described subimage is passed to cotton side stem detection module;
Described cotton side stem detection module, for comprising the cotton plants subimage of plant stem, according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side; Obtain the first side stem in both sides images, will wherein with stem on the upside of acutangulate straight line as side stem, and testing result is passed to cotton five leaf period judge module;
Described cotton five leaf period judge module, for the distribution situation according to stem number in side in cotton plants subimage after final singling, judge whether cotton enters five leaf periods: for the cotton plants subimage comprising plant stem, using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, judge that cotton enters five leaf periods, otherwise judge that cotton does not enter five leaf periods.
Be below embodiment:
Whether the cotton in Fig. 2 enters five leaf periods to use method provided by the invention to judge:
(1) cotton plants subimage after acquisition final singling.
The positive elevational views in cotton field after collection final singling, camera is overhead high 0.35 meter, focal length 14 millimeters, horizontal shooting direction eastwards, be 0 degree with local horizon angle, resolution 4,000,000 pixel, embodiment is to be a detection period every day, camera is taken w respectively in each detection period and is opened Cotton Images (w=13), and image size is 3648 × 2736.Be illustrated in figure 2 the positive elevational views exemplary plot in cotton field.First cut the positive elevational views in the cotton field after final singling, clearly can observe the positive elevational views of the single plant in cotton field after the final singling of single plant growth condition to obtain, image size is 3648 × 912, as shown in Figure 3.
With the search box of 912 pixel × 304 pixels with the fractionation step-length of 240 pixels, according to order from left to right, what described image is split into 912 pixel × 304 pixels only comprises individual plant plant subimage, as shown in Figure 4 (a).
For each subimage, utilize the method for contrast stretching, highlight plant, as shown in Figure 4 (b).Subimage respectively after contrast stretching carries out color segmentation and crop cutting operation.Color segmentation: adopt R, G/R, G/B value as characteristic index, if the relation in image between pixel triple channel value meets R≤200 simultaneously, G/R >=0.9 and G/B >=2.5, then can split green blade substantially; When rufous segmentation is carried out to image, adopt R, R/G, B/G value as characteristic index, if the relation in image between pixel triple channel value meets R>100 simultaneously, R/G >=2.8 and B/G >=0.1, then can substantially rufous branch be split, combining with green and rufous segmentation result, obtain color segmentation result figure, as shown in Figure 4 (c).Crop is split: adopt the crop partitioning algorithm based on Mean shift, image is carried out crop segmentation, and result is as shown in Fig. 4 (d).The result of crop image segmentation result and color segmentation is combined, namely on the region segmentation result figure of the crop dividing method based on Mean shift, the region occupied by pixel detected in retaining color segmentation result figure, to obtain cotton plants subimage after final singling, as shown in Fig. 4 (e).
Final seedling time is determined as follows: every day gathers view image under cotton field under the same conditions, camera is overhead high 5 meters, focal length 14 millimeters, horizontal shooting direction eastwards, downward 60 degree with local horizon angle, resolution 4,000,000 pixel, embodiment is to be a detection period every day, camera is taken w respectively in each detection period and is opened Cotton Images (w=13), and image size is 3648 × 2736, is illustrated in figure 5 view example figure under cotton field.Utilize Fisher linear discriminant method to carry out green segmentation to described image, be illustrated in figure 6 green segmentation result figure, add up described image Green image coverage; View green image coverage under the cotton field of every day after the leaf period of cotton field three is compared with view green image coverage under the previous day cotton field, final seedling time is when green image coverage reduces, be illustrated in figure 7 view coverage changing trend diagram under cotton field, when detecting after cotton three leaf period the 9th day, coverage reduces, this illustrates that completing cotton field final singling this day cotton grower operates, from the 10th day, namely can carry out the detection of individual plant plant growth condition to the horizontal forward sight image sequence in cotton field.
(2) cotton plants stem is detected
For all cotton plants subimages obtained in step (1), be a cotton plants subimage exemplary plot as shown in Figure 8 (a), use Canny operator to detect plant just edge, obtain plant just edge two-value subgraph, as shown in Figure 8 (b) shows; Adopt the Refinement operation in morphological images disposal route to extract plant just skeleton, obtain plant just skeleton two-value subgraph, as shown in Fig. 8 (c).
By plant just edge two-value subgraph and plant just skeleton two-value subgraph, all distinguish and first adopt chain code to extract straight line, then adopt Hough transform to carry out straight-line detection to the result that chain code extracts straight line, obtain the two-value subgraph of the vertical plant edge of cotton plants and plant skeleton.By plant edge two-value subgraph and the superposition of plant skeleton two-value subgraph, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem, as shown in Fig. 8 (d).
(3) cotton plants side stem is detected
By the cotton plants subimage comprising plant stem obtained in step (2), according to stem position, be divided into both sides: stem is on the left of image with a left side, as shown in Fig. 9 (a), stem is on the right side of image with the right side, as shown in Figure 9 (b).Both sides image is carried out color segmentation respectively: both sides image is carried out respectively the rufous side stem that color segmentation is split substantially, adopt R, R/G, B/G value as characteristic index, if the relation in image between pixel triple channel value meets R>100 simultaneously, R/G >=2.8 and B/G >=0.1, then can substantially rufous side stem be split, substantially the rufous side stem split, then the straight line that Hough straight-line detection obtains in the image of both sides is carried out to color segmentation result figure.
In the image of both sides, be considered to side stem with straight line acutangulate on the upside of stem, by both sides image processing and tracking unit, side stem testing result can be obtained, as shown in Figure 9 (c).
(4) cotton five leaf period is judged
The intersection point of the node on individual plant plant and stem and side stem, when the stem that color segmentation and straight-line detection result judge and side stem do not have intersection point, extends side stem until it is crossing with stem, determines that intersection point is node.Micro-judgment, image generally cannot gather whole node, for the cotton plants subimage comprising plant stem obtained in step (2), when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, think that cotton field enters five leaf periods.Namely detect that 2 or 2 are with the subimage during stem of upside, as shown in Figure 10.
Those skilled in the art will readily understand; the foregoing is only preferred embodiment of the present invention; not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (8)
1. one to grow cotton five leaf period detection methods, it is characterized in that, comprise the following steps:
(1) cotton plants subimage after acquisition final singling: the positive elevational views of the single plant in cotton field after collection final singling; With the search box of applicable cotton plants individual plant image size, described image is split into subimage; Color segmentation and crop Iamge Segmentation are carried out to described subimage, on the region segmentation result figure of crop dividing method, the region occupied by pixel detected in retaining color segmentation result figure, cotton plants subimage after acquisition final singling;
(2) cotton plants stem is detected: for all cotton plants subimages obtained in step (1), detect plant just edge, extract plant just skeleton, to plant just edge and plant just skeleton carry out Chain Code Detection and straight-line detection obtains the vertical plant edge of cotton plants and plant skeleton, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem;
(3) cotton plants side stem is detected: by the cotton plants subimage comprising plant stem obtained in step (2), according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side; Both sides image is carried out respectively the first side stem that color segmentation and straight-line detection obtain in the image of both sides, will wherein with stem on the upside of acutangulate just side stem as side stem;
(4) cotton five leaf period is judged: for the cotton plants subimage comprising plant stem obtained in step (2), using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, judge that cotton field enters five leaf periods, otherwise judge that cotton field does not enter five leaf periods.
2. cotton five leaf period detection method as claimed in claim 1, it is characterized in that, described step (1) final seedling time judges according to following steps: every day gathers view image under cotton field under the same conditions, utilize dividing method to carry out green segmentation to described image, add up described image Green pixel proportion and be green image coverage; View green image coverage under every day cotton field is compared with view green image coverage under the previous day cotton field, is final seedling time when green image coverage reduces.
3. cotton five leaf period detection method as claimed in claim 2, it is characterized in that, the described dividing method carrying out green segmentation and use, can adopt environment self-adaption dividing method, super green operator dividing method, the crop image partition method based on Mean shift, Fisher linear discriminant method.
4. cotton five leaf period detection method as claimed in claim 1, it is characterized in that, the positive elevational views of described single plant is through the method process of contrast stretching.
5. cotton five leaf period detection method as claimed in claim 4, it is characterized in that, described search box is equal with the height of the positive elevational views of described single plant, and the width of described search box is 1/4 to 1/2 of its height, and described fractionation step-length is 1/2 to 5/6 of described search box width.
6. cotton five leaf period detection method as claimed in claim 1, it is characterized in that, described step (2) detects plant just edge algorithms and extraction plant just skeleton, and adoptable image detective operators has Sobel operator, Roberts operator, LoG operator and Canny operator, preferred Canny operator.
7. cotton five leaf period detection method as claimed in claim 1, is characterized in that, described step (2) and step (3) cathetus detect and can adopt Hough transform.
8. one to grow cotton five leaf period detection systems, it is characterized in that, comprise cotton plants subimage acquisition module, cotton stem detection module, cotton side stem detection module and cotton five leaf period judge module;
Described cotton plants subimage acquisition module, for gathering the positive elevational views of the single plant in cotton field after final singling, split into cotton plants individual plant subimage, and after described subimage is processed into final singling, cotton plants subimage passes to cotton stem detection module;
Described cotton stem detection module, for extract cotton plants edge and main framing, using inside the vertical plant edge comprising vertical plant skeleton as cotton plants stem, obtain and comprise the cotton plants subimage of plant stem, and described subimage is passed to cotton side stem detection module;
Described cotton side stem detection module, for comprising the cotton plants subimage of plant stem, according to stem position, be divided into both sides: stem is on the left of image with a left side, stem is on the right side of image with the right side; Obtain the first side stem in both sides images, will wherein with stem on the upside of acutangulate straight line as side stem, and testing result is passed to cotton five leaf period judge module;
Described cotton five leaf period judge module, for the distribution situation according to stem number in side in cotton plants subimage after final singling, judge whether cotton enters five leaf periods: for the cotton plants subimage comprising plant stem, using the intersection point of wherein side stem and stem as node, when cotton plants number of sub-images more than 50% after the number of sub-images of more than 2 or 2 nodes accounts for all final singlings being detected, judge that cotton enters five leaf periods, otherwise judge that cotton does not enter five leaf periods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410111412.2A CN104949981A (en) | 2014-03-24 | 2014-03-24 | Automatic detection method and system for cotton five-euphylla period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410111412.2A CN104949981A (en) | 2014-03-24 | 2014-03-24 | Automatic detection method and system for cotton five-euphylla period |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104949981A true CN104949981A (en) | 2015-09-30 |
Family
ID=54164798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410111412.2A Pending CN104949981A (en) | 2014-03-24 | 2014-03-24 | Automatic detection method and system for cotton five-euphylla period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104949981A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097372A (en) * | 2016-06-23 | 2016-11-09 | 北京农业信息技术研究中心 | Crop plant water stress Phenotypic examination method based on image procossing |
| CN106770274A (en) * | 2015-11-25 | 2017-05-31 | 财团法人资讯工业策进会 | Physiological characterization detection method, portable detection device and detection system for crops |
| CN106952241A (en) * | 2017-04-27 | 2017-07-14 | 北京航空航天大学 | A kind of electromagnetic image method of partition based on morphological method and Meanshift algorithms |
| CN106996757A (en) * | 2017-04-18 | 2017-08-01 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method based on digital camera images |
| CN107024187A (en) * | 2017-04-18 | 2017-08-08 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method based on digital camera images |
| CN107144244A (en) * | 2017-05-16 | 2017-09-08 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method |
| CN107463939A (en) * | 2017-06-27 | 2017-12-12 | 浙江工业大学 | A kind of image key line detection method |
| CN107993243A (en) * | 2017-12-21 | 2018-05-04 | 北京林业大学 | A kind of wheat tillering number automatic testing method based on RGB image |
| CN108647652A (en) * | 2018-05-14 | 2018-10-12 | 北京工业大学 | A kind of cotton development stage automatic identifying method based on image classification and target detection |
| CN110064601A (en) * | 2019-05-23 | 2019-07-30 | 仲恺农业工程学院 | Seedling detection and classification system and classification method for vegetable grafting |
| CN112069953A (en) * | 2020-08-26 | 2020-12-11 | 江苏农林职业技术学院 | Automatic identification method and device for rice seedling growth period |
| CN115147423A (en) * | 2022-09-06 | 2022-10-04 | 江苏欧罗曼家纺有限公司 | Cotton top detection method based on improved chain code method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103699A (en) * | 2011-01-27 | 2011-06-22 | 华中科技大学 | Method for detecting boll opening of cotton based on image detection |
| CN102636486A (en) * | 2012-03-23 | 2012-08-15 | 华中科技大学 | Method for automatically detecting three-true-leaf period of cotton |
-
2014
- 2014-03-24 CN CN201410111412.2A patent/CN104949981A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103699A (en) * | 2011-01-27 | 2011-06-22 | 华中科技大学 | Method for detecting boll opening of cotton based on image detection |
| CN102636486A (en) * | 2012-03-23 | 2012-08-15 | 华中科技大学 | Method for automatically detecting three-true-leaf period of cotton |
Non-Patent Citations (1)
| Title |
|---|
| YANAN LI等: "An image-based approach for automatic detecting five true-leaves stage of cotton stage of cotton", 《SPIE PROCEEDINGS》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106770274A (en) * | 2015-11-25 | 2017-05-31 | 财团法人资讯工业策进会 | Physiological characterization detection method, portable detection device and detection system for crops |
| CN106097372A (en) * | 2016-06-23 | 2016-11-09 | 北京农业信息技术研究中心 | Crop plant water stress Phenotypic examination method based on image procossing |
| CN106996757A (en) * | 2017-04-18 | 2017-08-01 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method based on digital camera images |
| CN107024187A (en) * | 2017-04-18 | 2017-08-08 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method based on digital camera images |
| CN106952241B (en) * | 2017-04-27 | 2020-03-10 | 北京航空航天大学 | Electromagnetic image blocking method based on morphological method and Meanshift algorithm |
| CN106952241A (en) * | 2017-04-27 | 2017-07-14 | 北京航空航天大学 | A kind of electromagnetic image method of partition based on morphological method and Meanshift algorithms |
| CN107144244A (en) * | 2017-05-16 | 2017-09-08 | 广西壮族自治区农业科学院农业资源与环境研究所 | A kind of leaf area measurement method |
| CN107463939A (en) * | 2017-06-27 | 2017-12-12 | 浙江工业大学 | A kind of image key line detection method |
| CN107463939B (en) * | 2017-06-27 | 2020-06-09 | 浙江工业大学 | Image key straight line detection method |
| CN107993243B (en) * | 2017-12-21 | 2020-06-23 | 北京林业大学 | Wheat tillering number automatic detection method based on RGB image |
| CN107993243A (en) * | 2017-12-21 | 2018-05-04 | 北京林业大学 | A kind of wheat tillering number automatic testing method based on RGB image |
| CN108647652A (en) * | 2018-05-14 | 2018-10-12 | 北京工业大学 | A kind of cotton development stage automatic identifying method based on image classification and target detection |
| CN108647652B (en) * | 2018-05-14 | 2022-07-01 | 北京工业大学 | Cotton development period automatic identification method based on image classification and target detection |
| CN110064601A (en) * | 2019-05-23 | 2019-07-30 | 仲恺农业工程学院 | Seedling detection and classification system and classification method for vegetable grafting |
| CN112069953A (en) * | 2020-08-26 | 2020-12-11 | 江苏农林职业技术学院 | Automatic identification method and device for rice seedling growth period |
| CN115147423A (en) * | 2022-09-06 | 2022-10-04 | 江苏欧罗曼家纺有限公司 | Cotton top detection method based on improved chain code method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104949981A (en) | Automatic detection method and system for cotton five-euphylla period | |
| CN108647652B (en) | Cotton development period automatic identification method based on image classification and target detection | |
| Fu et al. | A novel image processing algorithm to separate linearly clustered kiwifruits | |
| Zhou et al. | Using colour features of cv.‘Gala’apple fruits in an orchard in image processing to predict yield | |
| CN106951836A (en) | Crop cover degree extracting method based on priori threshold optimization convolutional neural networks | |
| Yu et al. | Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-leaf stage | |
| CN111340826B (en) | Aerial image single tree crown segmentation algorithm based on super pixels and topological features | |
| Oppenheim et al. | Detecting tomato flowers in greenhouses using computer vision | |
| CN101859375B (en) | Method for recognizing inline crops and weeds of seedling stage in farmland | |
| CN102636486B (en) | Method for automatically detecting three-true-leaf period of cotton | |
| CN113657469B (en) | Automatic observation method and system for woody plant waiting period based on image recognition | |
| KR20150000435A (en) | Recongnition of Plant Growth Steps and Environmental Monitoring System and Method thereof | |
| CN105893977B (en) | A kind of rice drafting method based on adaptive features select | |
| Adhikari et al. | 3D reconstruction of apple trees for mechanical pruning | |
| CN102592118B (en) | Automatic detection method for time emergence of seedling of corns | |
| CN102103699A (en) | Method for detecting boll opening of cotton based on image detection | |
| CN103914848A (en) | Farmland image segmentation method based on wavelet transform and maximum between-cluster variance | |
| CN103090946B (en) | Method and system for measuring single fruit tree yield | |
| CN111462058A (en) | Method for quickly detecting effective ears of rice | |
| CN109523528A (en) | A kind of transmission line of electricity extracting method based on unmanned plane binocular vision SGC algorithm | |
| CN103279762A (en) | Judging method for common growth form of fruit under natural environment | |
| CN102663396A (en) | Method for automatically detecting rice milky ripe stage | |
| CN102360428A (en) | Automatic detection methods for trefoil stage and seven-leaf stage of corn | |
| CN113807132B (en) | Method, device and storage medium for identifying irrigation state of plant growth area | |
| CN103900498A (en) | Automatic cotton field seedling situation detection method and detection device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150930 |
|
| RJ01 | Rejection of invention patent application after publication |