CN108682033A - A kind of phase safflower filament two-dimensional image center in full bloom point extracting method - Google Patents
A kind of phase safflower filament two-dimensional image center in full bloom point extracting method Download PDFInfo
- Publication number
- CN108682033A CN108682033A CN201810527616.2A CN201810527616A CN108682033A CN 108682033 A CN108682033 A CN 108682033A CN 201810527616 A CN201810527616 A CN 201810527616A CN 108682033 A CN108682033 A CN 108682033A
- Authority
- CN
- China
- Prior art keywords
- image
- circle
- filigree
- safflower
- phase
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The present invention provides a kind of phase safflower filament two-dimensional image center in full bloom point extracting methods.By collected phase safflower filament image in full bloom, after image segmentation being carried out with chromatism method and maximum variance between clusters, with in mathematical morphology opening operation, with the mode that operation and dilation operation are combined filigree bianry image is handled, finally picture circle is recycled inside it with a kind of maximum inscribe member=circule method, until finding the maximum inscribed circle of image outline, dot and radius are acquired.It is that the three-dimensional localization of safflower picking robot and intelligence are picked and provided fundamental basis the beneficial effects of the invention are as follows can retaining the extraction of progress two-dimensional center point on the basis of filigree original information to greatest extent according to phase filigree cluster-shaped feature in full bloom, improving accuracy.
Description
Technical field
The present invention relates to agricultural harvest people fields, are suitable for safflower picking robot, the especially knowledge of safflower filament image
It is not extracted with two-dimensional center point.
Background technology
Safflower is one of the major economic crops in Xinjiang, and safflower filament has the function of medicinal, pigment extraction etc., but it is picked
Time is short, mainly based on opening 2-3 days, in addition labor shortage, causes waste serious, economic loss is huge.However at present
The Simple mechanical that the safflower harvest machine occurred in the market is mostly manually born, harvest efficiency is low, and net picking rate is low, cannot meet increasingly
The safflower industry development of growth.So to improve harvest efficiency, labour production cost is reduced, the harvesting of safflower intelligent machineization seems
It is very urgent.
The safflower filament of phase in full bloom is in cluster shape, and color is orange red, is had with background colours such as green cauline leafs more bright
Aobvious difference, though the identification that can carry out filigree according to color is extracted, the positioning to carry out two-dimensional center point still has certain
Difficulty, and have no related scholar both at home and abroad and Position Research was carried out to cluster-shaped object, so being badly in need of one kind can accurately carry
A kind of method of cluster-shaped safflower filament image is taken, realizes the essential step intelligently picked.
Invention content
For deficiency existing for existing safflower intelligence picked technology, the present invention provides a kind of phase safflower filament images in full bloom
Two-dimensional center point extracting method solves the problems, such as position inaccurate in safflower intelligence picking process.
The present invention achieves the above technical objects by the following technical means.
A kind of phase safflower filament two-dimensional image center in full bloom point extracting method, it is characterised in that comprise the steps of：
Step 1：Image Acquisition digital camera is to blooming the phase（2-3 days）Safflower carries out static shooting；
Step 2：To collected safflower image into row threshold division, and carry out binary conversion treatment；
Step 3：Morphology processing is carried out to the image after binaryzation；
Step 4：Region inside-paint circle is carried out to the image after Morphological scale-space with Maximum Inscribed Circle Method, seeks obtaining maximum inscribed circle, and
Find out the center of circle.
Step 5：Bianry image after the filigree positioning obtained to the step 6 carries out filigree original information filling, observation
Positioning accuracy.
Further, the step 1 is specially shooting when carrying out static shooting to safflower filament image using digital camera
Angle is to overlook above polarization 30 degree, shooting distance 45cm, and be aided with camera support progress camera and fix.
Further, the step 2 is specially and is split to safflower filament image using chromatism method under RGB models,
It is used in combination maximum variance between clusters to extract filigree information, then carries out binary conversion treatment.
Further, the step 3 is specially：
Step 3.1：Morphology opening operation is carried out to the step 2 treated image with radius different circular configuration element；
Step 3.2：By the step 3.1 treated image and the step 2 treated image, intersection processing is carried out；
Step 3.3：Morphological dilations operation again is carried out to the step 3.2 treated image, and is filled.
Further, the step 4 is specially to carry out edge extracting to filigree image, set point pixel value on edge as
1, other pixel values are 0；Edge image is defined with the rectangle frame less than picture size, a little for the center of circle, to be adopted in frame
Picture circle is carried out with the mode of increasing radii, when it is a little a bit on filigree edge that circle is upper, circle is drawn and stops, and record the center of circle at this time
Coordinate and radius value；Center pixel value is added 1, is repeated the above process, and when central coordinate of circle value is a bit on filigree edge,
Not picture is justified；After having traversed all pixels value in the rectangle frame, the maximum radius circle and central coordinate of circle pixel of record are obtained
Value, carries out picture circle, is just the maximum inscribed circle of filigree image at this time.
The maximum advantageous effect of the present invention is taken the lead in proposing one kind and identifies and positions on the basis of forefathers do not study
The method of phase safflower filament image in full bloom, especially the two-dimensional center point location of filigree image are current safflower intelligent machine
Harvesting provides precondition and basis.
Description of the drawings
Fig. 1 is safflower filament artwork.
Fig. 2 is safflower filament binary map.
Fig. 3 is filigree opening operation design sketch.
Fig. 4 is that filigree image is opened and operation effect figure.
Fig. 5 is filigree image reexpansion design sketch.
Fig. 6 is filigree image zooming-out maximum inscribed circle design sketch.
Fig. 7 is that filigree two-dimensional image central point extracts final effect figure.
Specific implementation mode
Below in conjunction with the accompanying drawings and specific embodiment the present invention is further illustrated, it should be emphasised that, under state
Bright to be only exemplary, protection scope of the present invention is not limited to this.
For the embodiment of the present invention using the collected single safflower of digital camera as research object, concrete scheme is as follows：
Step 1：Using digital camera to blooming the phase（2-3 days）Safflower carries out static shooting, as shown in Figure 1, filigree image is obtained,
Shooting angle is to overlook above polarization 30 degree, shooting distance 45cm, and camera support progress camera is aided with during shooting and is fixed.
Step 2：Collected safflower image is handled with MATLAB image processing softwares, under RGB models, is adopted
Safflower filament image is split with R-B chromatism methods, is used in combination maximum variance between clusters to extract filigree information, then carries out two-value
Change is handled, as shown in Figure 2.
Step 3：Morphology opening operation is carried out with circular radius structural element to the image of the step 2 processing, eliminates flower
The peripheral fine strip shape bur of silk, makes image regularization, as shown in Figure 3.
Step 4：Missing or increase through the step 3 treated image will necessarily cause filigree information, reduce it
Phenomena such as authenticity, and there are still corner angle protrusion, image is unsmooth, so the filigree image that the step 2 processing is obtained
The image obtained with the step 3 carries out taking intersection operation, can not only retain the real pixel information of filigree in this way, but also can disappear
Except increased pixel value, the nucleus of filigree image is remained.
Step 5：To the dilation operation of the step 4 treated image carries out again small circular radius structure element,
Purpose is to eliminate tiny bur and corner angle, so that image is reached a kind of closest to circular state, as shown in figure 5, in being subsequent
Heart point location provides condition.
Step 6：Edge extracting is carried out to the step 5 treated filigree image, set point pixel value on edge as
1, other pixel values are 0；Edge image is defined with the rectangle frame less than picture size, a little for the center of circle, to be adopted in frame
Picture circle is carried out with the mode of increasing radii, when it is a little a bit on filigree edge that circle is upper, circle is drawn and stops, and record the center of circle at this time
Coordinate and radius value；Center pixel value is added 1, is repeated the above process, and when central coordinate of circle value is a bit on filigree edge,
Not picture is justified；After having traversed all pixels value in the rectangle frame, the maximum radius circle and central coordinate of circle pixel of record are obtained
Value, carries out picture circle, is just the maximum inscribed circle of filigree image at this time, as shown in Figure 6.
Step 7：Bianry image after the filigree positioning obtained to the step 6 carries out filigree original information filling, observation
Positioning accuracy.
Above-described embodiment is only the preferable example of the present invention, is not the restriction to embodiment of the present invention, all
All any modification, equivalent and improvement made by within the spirit and principles in the present invention etc. should be included in the power of the present invention
Within the scope of profit is claimed.
Claims (5)
1. a kind of phase safflower filament two-dimensional image center in full bloom point extracting method, which is characterized in that comprise the steps of：
Step 1：Image Acquisition selects digital camera to blooming the phase（2-3 days）Safflower carries out static shooting；
Step 2：To collected safflower image into row threshold division, and carry out binary conversion treatment；
Step 3：Morphology processing is carried out to the image after binaryzation；
Step 4：Region inside-paint circle is carried out to the image after Morphological scale-space with Maximum Inscribed Circle Method, seeks obtaining maximum inscribed circle, and
Find out the center of circle;
Step 5：Bianry image after the filigree positioning obtained to the step 6 carries out filigree original information filling, observation positioning
Precision.
2. a kind of phase safflower filament two-dimensional image center in full bloom point extracting method as described in claim 1, the spy of the step 1
Sign is：
Single static shooting is carried out to safflower filament image using digital camera, and shooting angle is that 30 degree are overlooked above polarization, is clapped
Photographic range is 45cm, and when shooting, which is aided with camera support and carries out camera, to be fixed.
3. a kind of phase safflower filament two-dimensional image center in full bloom point extracting method as described in claim 1, the spy of the step 2
Sign is：
Collected safflower image is handled with MATLAB image processing softwares, under RGB models, using R-B aberration
Method is split safflower filament image, is used in combination maximum variance between clusters to extract filigree information, then carries out binary conversion treatment.
4. a kind of phase safflower filament two-dimensional image center in full bloom point extracting method as described in claim 1, the spy of the step 3
Sign is to comprise the steps of：
Step 3.1：Morphology opening operation is carried out to the step 2 treated image with radius different circular configuration element；
Step 3.2：By the step 3.1 treated image and the step 2 treated image, intersection processing is carried out；
Step 3.3：Morphological dilations operation again is carried out to the step 3.2 treated image, and is filled.
5. a kind of phase safflower filament two-dimensional image center in full bloom point extracting method as described in claim 1, the spy of the step 4
Sign is：
Edge extracting is carried out to the step 5 treated filigree image, sets point pixel value on edge as 1, other pixels
Value is 0；Edge image is defined with the rectangle frame less than picture size, with any is the center of circle in frame, using increasing radii
Mode carry out picture circle, when it is a little a bit on filigree edge that circle is upper, draws circle and stop, and record central coordinate of circle and radius at this time
Value；Center pixel value is added 1, is repeated the above process, and when central coordinate of circle value is a bit on filigree edge, not picture is justified；
After having traversed all pixels value in the rectangle frame, obtains the maximum radius circle and central coordinate of circle pixel value of record, carry out picture
Circle is just the maximum inscribed circle of filigree image at this time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810527616.2A CN108682033A (en) | 2018-05-29 | 2018-05-29 | A kind of phase safflower filament two-dimensional image center in full bloom point extracting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810527616.2A CN108682033A (en) | 2018-05-29 | 2018-05-29 | A kind of phase safflower filament two-dimensional image center in full bloom point extracting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108682033A true CN108682033A (en) | 2018-10-19 |
Family
ID=63808491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810527616.2A Pending CN108682033A (en) | 2018-05-29 | 2018-05-29 | A kind of phase safflower filament two-dimensional image center in full bloom point extracting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108682033A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176020A (en) * | 2019-04-09 | 2019-08-27 | 广东工业大学 | A kind of bird's nest impurity method for sorting merging 2D and 3D rendering |
| CN114454266A (en) * | 2022-02-14 | 2022-05-10 | 三菱电机自动化(中国)有限公司 | Log cutting device, method and computer readable medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657617A (en) * | 2017-09-29 | 2018-02-02 | 石河子大学 | A kind of safflower filament recognition methods |
-
2018
- 2018-05-29 CN CN201810527616.2A patent/CN108682033A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657617A (en) * | 2017-09-29 | 2018-02-02 | 石河子大学 | A kind of safflower filament recognition methods |
Non-Patent Citations (1)
| Title |
|---|
| BING C. LI: "《Shape distance transform for morphological filtering and landing site selection》", 《SPIE 9476, AUTOMATIC TARGET RECOGNITION XXV, 94760B》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176020A (en) * | 2019-04-09 | 2019-08-27 | 广东工业大学 | A kind of bird's nest impurity method for sorting merging 2D and 3D rendering |
| CN114454266A (en) * | 2022-02-14 | 2022-05-10 | 三菱电机自动化(中国)有限公司 | Log cutting device, method and computer readable medium |
| CN114454266B (en) * | 2022-02-14 | 2023-09-08 | 三菱电机自动化(中国)有限公司 | Log cutting device, method and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
| CN106296653B (en) | Brain CT image hemorrhagic areas dividing method and system based on semi-supervised learning | |
| CN107292298A (en) | Ox face recognition method based on convolutional neural networks and sorter model | |
| CN110120042B (en) | Crop image pest and disease damage area extraction method based on SLIC super-pixel and automatic threshold segmentation | |
| CN104392233B (en) | A kind of image saliency map extracting method based on region | |
| CN106682639B (en) | A kind of crop leaf portion abnormal image extracting method based on video surveillance | |
| CN109117703B (en) | Hybrid cell type identification method based on fine-grained identification | |
| CN103679173A (en) | Method for detecting image salient region | |
| CN107527054B (en) | Automatic foreground extraction method based on multi-view fusion | |
| CN111798470A (en) | Crop image entity segmentation method and system applied to intelligent agriculture | |
| CN108090485A (en) | Display foreground extraction method based on various visual angles fusion | |
| CN109344820A (en) | Digital electric meter Recognition of Reading method based on computer vision and deep learning | |
| CN106683098B (en) | A kind of dividing method of overlapped blades image | |
| CN108682033A (en) | A kind of phase safflower filament two-dimensional image center in full bloom point extracting method | |
| CN104992448B (en) | The automatic positioning method of robot antisitic defect grape-picking | |
| CN112528947A (en) | False hypha detection method and device by increasing direction dimension and storage medium | |
| CN114708208A (en) | Famous tea tender shoot identification and picking point positioning method based on machine vision | |
| CN113191334B (en) | Plant canopy dense leaf counting method based on improved CenterNet | |
| CN107886493A (en) | A kind of wire share split defect inspection method of transmission line of electricity | |
| CN116403004B (en) | Cow face fusion feature extraction method based on cow face correction | |
| CN103778428B (en) | Disease area-of-interest exacting method and system based on block labelling | |
| Wang et al. | A color-texture segmentation method to extract tree image in complex scene | |
| Sabri et al. | K-means vs. fuzzy C-means for segmentation of orchid flowers | |
| CN109117767A (en) | A kind of speed(-)limit sign classification method based on region growing | |
| CN107657617A (en) | A kind of safflower filament recognition methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181019 |
|
| WD01 | Invention patent application deemed withdrawn after publication |