CN112016418A - Secant identification method and device, electronic equipment and storage medium - Google Patents
Secant identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112016418A CN112016418A CN202010833848.8A CN202010833848A CN112016418A CN 112016418 A CN112016418 A CN 112016418A CN 202010833848 A CN202010833848 A CN 202010833848A CN 112016418 A CN112016418 A CN 112016418A
- Authority
- CN
- China
- Prior art keywords
- image
- secant
- real
- time
- historical
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000010079 rubber tapping Methods 0.000 claims description 61
- 238000005520 cutting process Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000003306 harvesting Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 5
- 244000043261 Hevea brasiliensis Species 0.000 description 40
- 229920001971 elastomer Polymers 0.000 description 34
- 239000003292 glue Substances 0.000 description 11
- 230000009466 transformation Effects 0.000 description 8
- 239000004816 latex Substances 0.000 description 7
- 229920000126 latex Polymers 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 229920003052 natural elastomer Polymers 0.000 description 5
- 229920001194 natural rubber Polymers 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a secant identification method, a secant identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image; performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area; identifying the secant area to obtain the secant; according to the embodiment of the invention, the complete secant area is accurately identified and obtained by utilizing the difference of the secant area in the images at different moments, so that the complete secant is accurately identified and obtained, the interference of the characteristics of other areas of the trunk can be effectively removed, the difficulty of an image processing algorithm is greatly reduced, and the reliability and the integrity of secant detection can be improved.
Description
Technical Field
The invention relates to the technical field of modern agriculture, in particular to a secant identification method and device, electronic equipment and a storage medium.
Background
The automatic tapping is based on automatic acquisition of operation information, wherein the acquisition of the cutting line information is most critical and relatively difficult.
The existing secant detection depends on effective identification of the rubber tapping surface, but the rubber tapping surface can be continuously changed along with the rubber tapping operation, the positions, colors and forms of the rubber tapping surfaces of rubber trees in different time and places are different, a plurality of interferences exist in the rubber trees growing in the unstructured environment, and the accuracy of secant identification is further reduced.
Therefore, how to provide a method for quickly, accurately and completely obtaining a cutting line becomes a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a secant line identification method and device, electronic equipment and a storage medium, which are used for solving the defect of inaccurate secant line identification in the prior art and realizing the purpose of quickly, accurately and completely obtaining the position of a secant line.
In a first aspect, an embodiment of the present invention provides a secant identification method, including:
acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area;
and identifying the secant area to obtain the secant.
According to the secant identification method, the shooting time of the historical image is after the last tapping of the trunk and before the last glue collecting of the trunk.
According to the secant recognition method of one embodiment of the present invention, the capturing conditions of the history image are the same as the capturing conditions of the real-time image, including:
and the shooting position, the shooting angle and the lighting condition of the shooting device are the same when the historical image and the real-time image are shot.
According to the secant identification method of one embodiment of the present invention, the obtaining a secant region by performing image registration on the real-time image and the historical image and then performing subtraction includes:
preprocessing the real-time image and the historical image;
performing image segmentation on the preprocessed real-time image and the preprocessed historical image to obtain a real-time trunk image of the trunk in the real-time image and a historical trunk image of the trunk in the historical image;
taking the real-time trunk image as a reference image, carrying out image registration on the historical trunk image, and acquiring the historical trunk image after the image registration;
and subtracting the real-time trunk image from the history trunk image after the image registration to obtain the secant area.
According to the secant identification method of one embodiment of the present invention, the preprocessing the real-time image and the historical image includes:
carrying out graying operation on the real-time image and the historical image;
and performing median filtering operation on the real-time image and the historical image subjected to the graying operation. According to a secant identification method of an embodiment of the present invention, the image segmentation of the real-time image and the historical image includes:
performing fixed threshold segmentation on the real-time image and the historical image to obtain the real-time image and the historical image of the trunk only left in the image foreground;
and automatically performing threshold segmentation on the real-time image and the historical image of the trunk only left in the image foreground to obtain the real-time trunk image and the historical trunk image.
According to the secant line identification method of one embodiment of the present invention, identifying the secant line region to obtain the secant line specifically includes:
and identifying and obtaining a lower edge in the cutting line area as the cutting line.
In a second aspect, an embodiment of the present invention provides a secant identification apparatus, including:
the acquisition module is used for acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before that of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
the registration module is used for performing image registration on the real-time image and the historical image and then performing image difference to obtain a secant area;
and the identification module is used for identifying the secant area to obtain the secant.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the secant identification method according to the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the secant identification method as provided in the first aspect.
According to the secant identification method, the secant identification device, the electronic equipment and the storage medium, the secant area is obtained by obtaining the real-time image and the historical image of the trunk needing to identify the secant under the same shooting condition, and performing image registration on the real-time image and the historical image and then performing image difference; identifying the secant area to obtain the secant; the complete secant area is accurately identified and obtained by utilizing the difference of the secant area in images at different moments, so that the complete secant is accurately identified and obtained, the interference of other area characteristics of the trunk can be effectively removed, the difficulty of an image processing algorithm is greatly reduced, and the reliability and the integrity of secant detection can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating a secant identification method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a glue bowl identification method according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a trunk identification method according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating a secant identification method according to another embodiment of the present invention
Fig. 5 is a schematic structural diagram of a secant identification device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Rubber tapping is an important link in the production of natural rubber, is generally manually finished in the morning by a rubber worker, each worker taps 300-500 rubber every day, the labor cost accounts for more than 70% of the production cost of the natural rubber, and the rubber tapping can not be automated all the time due to the complex environment of a rubber tree plantation, strict requirements on rubber tapping technology and the like. In recent years, the problems of continuous decline of the natural rubber price, loss of gum workers and aging are increasingly serious, an automatic rubber tapping technology is explored, the rubber tapping effect is optimized through reasonable system design, the yield of the natural rubber is improved, the technical dependence on the gum workers is reduced, and the method has important significance for the development of the natural rubber industry.
The tapping line detection depends on the form of the tapping surface, but the tapping surface can be continuously changed along with the tapping operation, and the positions, colors and forms of the tapping surface of rubber trees in different time and places are different, so that the detection method is required to have higher adaptability and robustness; for the problem, the first difficulty is that the glue outlet surface is too narrow, and the occupied pixels in the visual image are rare; secondly, the identification of the glue surface is established on the basis of the color image, and a plurality of interferences exist on the trunk of the rubber tree growing in the unstructured environment, so that not only shell-shaped lichens which are close to the color of the glue surface and grow randomly, animals or plants which appear irregularly, but also regenerated barks which are similar to the texture of the glue surface exist, and the glue surface is difficult to extract by the conventional means; finally, the shape of the glue outlet surface changes along with the difference of time and view point, and is greatly influenced by insufficient illumination of night environment.
In view of the above problems, the main idea of the embodiments of the present invention is that: the color and form difference of the residual latex on the rubber surface before the previous rubber recovery and the rubber tapping is utilized to realize the rapid, accurate and complete extraction of the rubber surface, and then the lower edge of the extracted rubber surface is detected to obtain the final rubber tapping line.
The following is described in detail by way of a number of examples:
fig. 1 is a schematic flow chart of a secant identification method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
specifically, due to the change of time, other parts on the trunk of the rubber tree cannot change, and only the cut line region, namely the residual latex on the rubber surface, has the difference in color and form, so that the cut line region can be obtained by subtracting the two previous and subsequent pictures.
Specifically, to the trunk that needs discernment secant at present, can utilize image acquisition equipment, respectively before this tapping, for example after the last tapping, before receiving glue, and when this tapping, shoot the rubber tree trunk that includes the secant, shoot the angle for the dead ahead of secant, shoot apart from view image acquisition equipment's ability and decide, use the clear prerequisite of secant formation of image, obtain the real-time image and the historical image of this trunk.
It can be understood that, before the rubber tapping, for example, after the rubber tapping, before the rubber tapping, and during the rubber tapping, the same image acquisition device can be used to shoot the trunk of the rubber tree at the same position and under the same illumination condition, so as to reduce the difference between the registration image and the reference image, and reduce the workload of the subsequent image registration. In order to ensure that the registration image and the reference image are the same rubber tree, the automatic tapping device can have a function of matching with the image acquisition device to identify the rubber tree. Meanwhile, it can be understood that the image acquisition device may have a larger storage space to store the images of the plurality of rubber tree trunks.
specifically, the real-time image and the historical image obtained in step 100 may be subjected to image registration and then differencing, and it can be understood that the secant region can be accurately obtained by taking the real-time image of the trunk region of the tapping at this time as a reference image, and taking the historical image of the trunk region before the tapping at this time, such as after the last tapping and before the tapping, as a registration image, and then differencing after the registration.
And 120, identifying the secant area to obtain the secant.
Specifically, it can be understood that for the cutting line on the rubber tree, each rubber tapping is performed on the basis of the original cutting line, and therefore, the cutting line position can be obtained after the cutting line area is identified.
According to the secant identification method provided by the embodiment of the invention, a secant area is obtained by obtaining a real-time image and a historical image of a trunk needing to identify the secant under the same shooting condition, and performing image registration and image subtraction on the real-time image and the historical image; identifying the secant area to obtain the secant; through the difference of the image of the secant area at different moments, the complete secant area is accurately identified and obtained, then the complete secant is accurately identified and obtained, the interference of other area characteristics of the trunk can be effectively removed, the difficulty of an image processing algorithm is greatly reduced, and the reliability and the integrity of secant detection can be improved.
Optionally, on the basis of the foregoing embodiments, the shooting time of the history image is after the last tapping of the tree trunk and before the last glue collecting of the tree trunk.
Specifically, each tapping is performed, a layer of bark is cut off on the basis of the original tapping line, then latex flows out of the rubber tree, and the residual latex on the rubber-out surface can be identified within a period of time, so that in order to ensure accurate identification of the tapping line position, the shooting time of the historical image can be after the last tapping of the trunk and before rubber collection; in order to have better effect comparison and reduce the workload of the image acquisition equipment, the optimal shooting time of the historical image can be the time after the last rubber tapping and before the rubber collecting of the trunk, after the rubber tapping equipment cuts the rubber, the image acquisition equipment on the rubber tapping equipment finishes the shooting of the historical image, and stores the historical image according to the serial number of the rubber tree, and simultaneously positions and stores the position and the direction of the equipment at the moment when the rubber tree is shot.
Optionally, on the basis of the foregoing embodiments, the capturing conditions of the history image are the same as the capturing conditions of the real-time image, and the capturing conditions of the history image and the capturing conditions of the real-time image include:
and the shooting position, the shooting angle and the lighting condition of the shooting device are the same when the historical image and the real-time image are shot.
It can be understood that, in order to make the gray values of other parts of the historical image and the real-time image closer, it can be ensured that the shooting position, the shooting angle and the lighting condition of the shooting device when shooting the historical image and the real-time image are the same, and the obtained secant area is more accurate when performing subtraction after image registration.
It is understood that, in the present embodiment, in order to ensure the same realizability of the lighting conditions and to ensure easier picture segmentation, the shooting may be selected at night.
For example, after the previous tapping and before the rubber tapping, the automatic tapping equipment stops near the trunk of the rubber tree, the stop position at the time is recorded, the image acquisition equipment on the tapping equipment is used for shooting the image of the trunk of the rubber tree acquired by the tapping line, and the image is named and stored by the current rubber tree number; when the rubber tapping is performed, namely a real-time image is acquired, the automatic rubber tapping equipment stops near the trunk of the rubber tree according to the parking position after the rubber tapping and before the rubber tapping, the image acquisition equipment is used for acquiring the rubber tree by directly facing the secant, and the same shooting condition as the previous shooting is kept.
Optionally, on the basis of the foregoing embodiments, the performing image registration on the real-time image and the historical image and then performing difference to obtain a secant region includes:
preprocessing the real-time image and the historical image;
performing image segmentation on the preprocessed real-time image and the preprocessed historical image to obtain a real-time trunk image of the trunk in the real-time image and a historical trunk image of the trunk in the historical image;
taking the real-time trunk image as a reference image, carrying out image registration on the historical trunk image, and acquiring the historical trunk image after the image registration;
specifically, the method may first respectively pre-process the historical images, such as the image after the previous rubber tapping, the image before the rubber tapping, and the image of the trunk of the rubber tree after the current rubber tapping, and segment the trunk of the rubber tree through the image, so as to respectively obtain a real-time trunk image of the trunk in the real-time image and a historical trunk image of the trunk in the historical image;
specifically, after obtaining a real-time trunk image of the trunk in the real-time image and a historical trunk image in the historical image, obtaining a registration image, namely the historical trunk image, required by glue surface identification and a reference image, namely the real-time trunk image; during registration, the embodiment may preferentially select a mutual information-based medical image registration method, and register the historical trunk image, such as the trunk image after tapping and before tapping, with the real-time trunk image, that is, the tapping trunk image, wherein the registration optimization step size may not be greater than 0.01pixel, and the number of iterations may not be less than 100 times, so that the registered image is registered with the real-time image through affine transformation integrating translation transformation, rotation transformation, scale transformation, image editing, and the like.
And subtracting the real-time trunk image from the history trunk image after the image registration to obtain the secant area.
Specifically, after the images are registered, since the gray value of the residual latex in the registered image, i.e., the historical trunk image after the images are registered, is greater than that of the reference image, i.e., the real-time trunk image, the registered image can be preferentially subtracted from the reference image to obtain a gray difference image, then a gray threshold 50 can be preferentially selected for performing fixed threshold segmentation on the gray difference image, a contour area threshold 100pixel is preferentially selected for identifying a dividing line area, i.e., a rubber surface, and then the lower edge of the rubber surface can be extracted to be a dividing line.
Optionally, on the basis of the foregoing embodiments, the preprocessing the real-time image and the historical image includes:
carrying out graying operation on the real-time image and the historical image;
and performing median filtering operation on the real-time image and the historical image subjected to the graying operation.
Specifically, when the real-time image and the historical image are preprocessed, since the image stored by the image acquisition device is generally a color image, and is usually represented and stored in an RGB color space, the image may be grayed first, that is, the r (red), g (green), and b (blue) three components of the color image are weighted and averaged with different weights. Since the human eye has the highest sensitivity to green and the lowest sensitivity to blue, the present embodiment can preferentially adopt the psychology gray formula:
Gray＝0.114B+0.587G+0.299R。
it can be understood that the trunk image of the rubber tree is collected in the night environment, a large amount of random noise exists on the ground with insufficient illumination, and the outer edge of the rubber surface is a finally required secant and can be protected. The median filtering is a common nonlinear filter, the basic idea is to replace the gray value of the pixel with the median of the gray value of the neighborhood of the pixel, and the main function is to change the pixel with larger gray value difference in the neighborhood pixel into the gray value close to the neighborhood pixel, thereby eliminating the isolated noise point. In order to eliminate the noise of the ground background while preserving the edges of the rubber surface, the embodiment may preferably use a median filter with a template size of 3 × 3 to perform noise reduction on the trunk image of the rubber tree.
Optionally, on the basis of the foregoing embodiments, the performing image segmentation on the real-time image and the historical image includes:
performing fixed threshold segmentation on the real-time image and the historical image to obtain the real-time image and the historical image of the trunk only left in the image foreground;
specifically, when the real-time image and the historical image are subjected to image segmentation, fixed threshold segmentation can be performed firstly, and it can be understood that in this embodiment, because the planting distance of the rubber tree is longer and the shooting device is closer to the trunk, only the current trunk and the rubber bowls on the trunk have gray values in the image and the other parts are all covered by the black background during each shooting; therefore, the fixed threshold segmentation is to segment off the rubber bowls in the image.
It can be understood that the rubber bowl is used for storing and receiving latex, generally, a low-cost durable white ceramic bowl is adopted, for a secant and a trunk, the rubber bowl is useless information and needs to be removed in advance, fig. 2 is a flow schematic diagram of the rubber bowl identification method provided by the embodiment of the invention, as shown in fig. 2, the rubber bowl identification is performed after image preprocessing, a gray threshold 115 can be preferentially selected to perform fixed threshold segmentation on a preprocessed image, then the rubber bowl is identified by preferentially utilizing a rectangle degree threshold of 0.65-0.80, and the rubber bowl removal is completed by utilizing the preprocessed image to remove an identified rubber bowl area.
Wherein, the rectangular degree RsThe calculation formula of (2) is as follows: rs＝A/Ara/(L × W). Wherein A is the area of the secant region; a. therThe area of the minimum external rectangle of the rubber bowl area is shown; l, W are the length and width, respectively, of the smallest circumscribed rectangle.
And automatically performing threshold segmentation on the real-time image and the historical image of the trunk only left in the image foreground to obtain the real-time trunk image and the historical trunk image.
Specifically, in this embodiment, after the fixed threshold segmentation is performed, only the trunk portion remains in the foreground of the real-time image and the historical image, so that automatic threshold segmentation can be performed to obtain the real-time trunk image and the historical trunk image.
Specifically, in the rubber tree trunk image, more than half of the information is a black background, and the effective information is in the rubber tree trunk area. The tree trunk is identified and extracted, so that effective information can be reserved, the size of an image subjected to image registration can be reduced, and the algorithm efficiency is greatly improved, fig. 3 is a flow schematic diagram of the tree trunk identification method provided by the embodiment of the invention, as shown in fig. 3, after the tree trunk is identified and rubber bowls are removed, the embodiment of the invention preferentially selects a maximum inter-class variance method to perform automatic threshold segmentation on the image subjected to rubber bowl removal, then sums the number of foreground pixels according to image columns, and positions the left and right boundaries of the tree trunk by 1/10 which preferentially sets the foreground pixels and the threshold as the number of image lines, and the region between the left and right boundaries is extracted to be the tree trunk region.
Optionally, on the basis of the foregoing embodiments, the identifying the secant area to obtain the secant specifically includes:
and identifying and obtaining a lower edge in the cutting line area as the cutting line.
In particular, it can be understood that for the cutting line on the rubber tree, the rubber cutting is performed below the original cutting line each time the rubber is picked, and therefore, the lower edge of the cutting line area can be identified to obtain the cutting line position.
According to the secant identification method provided by the embodiment of the invention, a secant area is obtained by obtaining a real-time image and a historical image of a trunk needing to identify the secant under the same shooting condition, and performing image registration and image subtraction on the real-time image and the historical image; identifying the secant area to obtain the secant; through the difference of the image of the secant area at different moments, the complete secant area is accurately identified and obtained, then the complete secant is accurately identified and obtained, the interference of other area characteristics of the trunk can be effectively removed, the difficulty of an image processing algorithm is greatly reduced, and the reliability and the integrity of secant detection can be improved.
Fig. 4 is a schematic flow chart of a secant identification method according to another embodiment of the present invention, as shown in fig. 4, the method includes the following steps:
after the rubber is cut for the previous time and before the rubber is collected, the automatic rubber cutting equipment stops near the trunk of the rubber tree, the stop position at the time is recorded, image acquisition equipment on the rubber cutting equipment is used for shooting an image of the trunk of the rubber tree which is acquired by a cutting line to obtain a historical image, and the image is named and stored by the current rubber tree number;
when tapping is performed at this time, the central control system of the automatic tapping equipment calls the trunk image of the rubber tree, which is acquired during the previous tapping and has the same serial number as the current rubber tree, as a real-time image.
specifically, in this embodiment, after the real-time image and the historical image are obtained, image preprocessing may be performed on the historical image obtained after the previous rubber tapping and before the rubber tapping and the real-time image of the trunk of the rubber tree obtained by the current rubber tapping; and acquiring a real-time image and a historical image after preprocessing.
Specifically, in this embodiment, the preprocessing the real-time image and the historical image includes performing graying operation on the real-time image and the historical image; a psychology gray formula can be used in the graying operation: gray ═ 0.114B +0.587G + 0.299R;
after the graying operation is performed, a median filtering operation may be performed on the real-time image and the historical image after the graying operation is performed, and specifically, a median filtering with a template size of 3 × 3 may be preferably used to perform noise reduction on the real-time image and the historical image of the trunk of the rubber tree.
specifically, in this embodiment, a fixed threshold segmentation may be performed on the real-time image and the historical image, that is, the rubber bowls in the image are segmented, so as to obtain an image in which only the trunk region is left in the foreground; automatic threshold segmentation may then be performed to obtain real-time trunk images and historical trunk images.
specifically, in this embodiment, after obtaining the real-time trunk image of the trunk in the real-time image and the historical trunk image in the historical image, image registration may be performed; during registration, the historical trunk image can be used as a registration image, the real-time trunk image is used as a reference image, the optimization step length of the registration can be not more than 0.01pixel, and the iteration time can be not less than 100 times, so that the registration image is registered with the real-time image through affine transformation integrating translation transformation, rotation transformation, scale transformation, image editing and the like.
specifically, after the images are registered, since the gray value of the residual latex in the registered image, i.e., the historical trunk image after the images are registered, is greater than that of the reference image, i.e., the real-time trunk image, the registered image can be used to subtract the reference image to obtain a gray difference image, a gray threshold 50 can be selected to perform fixed threshold segmentation on the gray difference image, i.e., a secant area, and a contour area threshold 100pixel is preferably selected to identify the secant area, i.e., a rubber surface.
specifically, after the dividing line region is obtained, the dividing line region, that is, the lower edge of the rubber-out surface, may be extracted as the dividing line.
Fig. 5 is a schematic structural diagram of a secant identification apparatus according to an embodiment of the present invention, and as shown in fig. 5, the apparatus includes: an acquisition module 510, a registration module 520, and an identification module 530.
Wherein;
the obtaining module 510 is configured to obtain a real-time image and a historical image of a trunk, where a shooting time of the historical image is before a shooting time of the real-time image, and a shooting condition of the historical image is the same as a shooting condition of the real-time image;
the registration module 520 is configured to perform image registration on the real-time image and the historical image and then perform subtraction to obtain a secant region;
the identifying module 530 is used for identifying the secant area to obtain the secant.
Specifically, the secant identification device acquires a real-time image and a historical image of a trunk needing to identify the secant currently through the acquisition module 510, and then performs image registration on the real-time image and the historical image through the registration module 520 and performs subtraction to obtain a secant area; finally, the secant region is identified and the secant position is obtained by the identification module 530.
The secant line identification device provided by the embodiment of the invention obtains a secant line area by obtaining a real-time image and a historical image of a trunk needing to identify the secant line under the same shooting condition, and performing image registration and difference on the real-time image and the historical image; identifying the secant area to obtain the secant; through the difference of the image of the secant area at different moments, the complete secant area is accurately identified and obtained, then the complete secant is accurately identified and obtained, the interference of other area characteristics of the trunk can be effectively removed, the difficulty of an image processing algorithm is greatly reduced, and the reliability and the integrity of secant detection can be improved.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a cut line identification method comprising:
acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area;
and identifying the secant area to obtain the secant.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the secant identification method provided by the above-mentioned method embodiments, where the method includes: acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area;
and identifying the secant area to obtain the secant.
In still another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the secant identification method provided in the foregoing embodiments, and the method includes:
acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area;
and identifying the secant area to obtain the secant.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A secant identification method is characterized by comprising the following steps:
acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before the shooting time of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
performing image registration on the real-time image and the historical image, and then performing subtraction to obtain a secant area;
and identifying the secant area to obtain the secant.
2. The secant identification method of claim 1 wherein the historical image is captured at a time after a last tapping of the tree trunk and before a last harvest of the tree trunk.
3. The secant identification method according to claim 1, wherein the photographing condition of the history image is the same as that of the real-time image, including:
and the shooting position, the shooting angle and the lighting condition of the shooting device are the same when the historical image and the real-time image are shot.
4. The secant identification method of claim 1, wherein the obtaining the secant region by performing image registration and image subtraction on the real-time image and the historical image comprises:
preprocessing the real-time image and the historical image;
performing image segmentation on the preprocessed real-time image and the preprocessed historical image to obtain a real-time trunk image of the trunk in the real-time image and a historical trunk image of the trunk in the historical image;
taking the real-time trunk image as a reference image, carrying out image registration on the historical trunk image, and acquiring the historical trunk image after the image registration;
and subtracting the real-time trunk image from the history trunk image after the image registration to obtain the secant area.
5. The secant identification method of claim 4 wherein said pre-processing said real-time image and said historical image comprises:
carrying out graying operation on the real-time image and the historical image;
and performing median filtering operation on the real-time image and the historical image subjected to the graying operation.
6. The secant identification method of claim 4 wherein said image segmenting the real-time image and the historical image comprises:
performing fixed threshold segmentation on the real-time image and the historical image to obtain the real-time image and the historical image of the trunk only left in the image foreground;
and automatically performing threshold segmentation on the real-time image and the historical image of the trunk only left in the image foreground to obtain the real-time trunk image and the historical trunk image.
7. The secant identification method according to claim 1, wherein the identifying the secant area to obtain the secant specifically comprises:
and identifying and obtaining a lower edge in the cutting line area as the cutting line.
8. A secant identification device, comprising:
the acquisition module is used for acquiring a real-time image and a historical image of a trunk needing to identify a secant at present, wherein the shooting time of the historical image is before that of the real-time image, and the shooting condition of the historical image is the same as that of the real-time image;
the registration module is used for performing image registration on the real-time image and the historical image and then performing image difference to obtain a secant area;
and the identification module is used for identifying the secant area to obtain the secant.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the secant identification method according to any one of claims 1 to 7 are implemented when the program is executed by the processor.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the secant identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010833848.8A CN112016418B (en) | 2020-08-18 | 2020-08-18 | Secant recognition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010833848.8A CN112016418B (en) | 2020-08-18 | 2020-08-18 | Secant recognition method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112016418A true CN112016418A (en) | 2020-12-01 |
| CN112016418B CN112016418B (en) | 2023-12-22 |
Family
ID=73504972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010833848.8A Active CN112016418B (en) | 2020-08-18 | 2020-08-18 | Secant recognition method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016418B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408440A (en) * | 2021-06-24 | 2021-09-17 | 展讯通信（上海）有限公司 | Video data jam detection method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120250040A1 (en) * | 2011-03-29 | 2012-10-04 | Yoshirou Yamazaki | Recording position error measurement apparatus and method, image forming apparatus and method, and computer-readable medium |
| CN106097344A (en) * | 2016-06-15 | 2016-11-09 | 武汉理工大学 | A kind of image processing method detecting geometric form impurity in rubber for tire and system |
| CN208169934U (en) * | 2018-03-28 | 2018-11-30 | 中国热带农业科学院橡胶研究所 | A kind of rubber tree secant filming apparatus and system |
| CN110014680A (en) * | 2019-02-18 | 2019-07-16 | 4Jet科技有限公司 | Device and method for tire marker and label tire |
| CN110122256A (en) * | 2019-05-21 | 2019-08-16 | 中国农业大学 | A kind of rubber tapping robot system and method for tapping rubber |
| CN110189285A (en) * | 2019-05-28 | 2019-08-30 | 北京迈格威科技有限公司 | A kind of frames fusion method and device |
| CN110806585A (en) * | 2019-10-16 | 2020-02-18 | 北京理工华汇智能科技有限公司 | Robot positioning method and system based on trunk clustering tracking |
| CN110852990A (en) * | 2019-10-09 | 2020-02-28 | 北京理工华汇智能科技有限公司 | Rubber tree oblique cutter mark detection method based on image processing |
-
2020
- 2020-08-18 CN CN202010833848.8A patent/CN112016418B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120250040A1 (en) * | 2011-03-29 | 2012-10-04 | Yoshirou Yamazaki | Recording position error measurement apparatus and method, image forming apparatus and method, and computer-readable medium |
| CN106097344A (en) * | 2016-06-15 | 2016-11-09 | 武汉理工大学 | A kind of image processing method detecting geometric form impurity in rubber for tire and system |
| CN208169934U (en) * | 2018-03-28 | 2018-11-30 | 中国热带农业科学院橡胶研究所 | A kind of rubber tree secant filming apparatus and system |
| CN110014680A (en) * | 2019-02-18 | 2019-07-16 | 4Jet科技有限公司 | Device and method for tire marker and label tire |
| CN110122256A (en) * | 2019-05-21 | 2019-08-16 | 中国农业大学 | A kind of rubber tapping robot system and method for tapping rubber |
| CN110189285A (en) * | 2019-05-28 | 2019-08-30 | 北京迈格威科技有限公司 | A kind of frames fusion method and device |
| CN110852990A (en) * | 2019-10-09 | 2020-02-28 | 北京理工华汇智能科技有限公司 | Rubber tree oblique cutter mark detection method based on image processing |
| CN110806585A (en) * | 2019-10-16 | 2020-02-18 | 北京理工华汇智能科技有限公司 | Robot positioning method and system based on trunk clustering tracking |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408440A (en) * | 2021-06-24 | 2021-09-17 | 展讯通信（上海）有限公司 | Video data jam detection method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112016418B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dorj et al. | An yield estimation in citrus orchards via fruit detection and counting using image processing | |
| Wang et al. | Individual tree-crown delineation and treetop detection in high-spatial-resolution aerial imagery | |
| CN111666883B (en) | Grape picking robot target identification and fruit stalk clamping and cutting point positioning method | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN110599507B (en) | Tomato identification and positioning method and system | |
| CN104239886A (en) | Image analysis based lawn and background boundary extraction method | |
| CN103295018A (en) | Method for precisely recognizing fruits covered by branches and leaves | |
| EP4242964A1 (en) | Obstacle recognition method applied to automatic traveling device and automatic traveling device | |
| CN109785321A (en) | Meibomian gland method for extracting region based on deep learning and Gabor filter | |
| CN106683098B (en) | A kind of dividing method of overlapped blades image | |
| Devi et al. | Image processing system for automatic segmentation and yield prediction of fruits using open CV | |
| CN112861654A (en) | Famous tea picking point position information acquisition method based on machine vision | |
| CN112016418B (en) | Secant recognition method and device, electronic equipment and storage medium | |
| CN116109637A (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
| CN109754423B (en) | Method and equipment for extracting coverage area of leaf scab | |
| CN110796654A (en) | Guide wire detection method, device, equipment, tyre crane and medium | |
| Tang et al. | Leaf extraction from complicated background | |
| CN111369497B (en) | Walking type tree fruit continuous counting method and device | |
| CN113269690A (en) | Method and system for detecting diseased region of blade | |
| CN115994921A (en) | Mature cherry fruit image segmentation method integrating HSV model and improving Otsu algorithm | |
| JP7126316B2 (en) | House change estimation device and program | |
| CN115331166B (en) | Intelligent monitoring and early warning method and system for grid trash remover | |
| CN111079530A (en) | Mature strawberry identification method | |
| CN114240758B (en) | Mountain tea garden low-altitude image splicing method taking quadrilateral plots as reference objects | |
| CN114862889A (en) | Road edge extraction method and device based on remote sensing image |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |