CN113933304A - Vision-based needle mushroom maturity state detection method - Google Patents
Vision-based needle mushroom maturity state detection method Download PDFInfo
- Publication number
- CN113933304A CN113933304A CN202111237911.2A CN202111237911A CN113933304A CN 113933304 A CN113933304 A CN 113933304A CN 202111237911 A CN202111237911 A CN 202111237911A CN 113933304 A CN113933304 A CN 113933304A
- Authority
- CN
- China
- Prior art keywords
- mushroom
- vision
- heads
- needle mushroom
- needle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Abstract
The invention discloses a method for detecting the mature state of flammulina velutipes based on vision, and relates to the field of growth detection of flammulina velutipes. The method aims to solve the problems that the growth of mushrooms cannot be effectively detected, the quality growth difference of the mushrooms is caused, and the mushrooms are discharged from a warehouse too early or too late; the method specifically comprises the following steps; s1: system initialization, S2: acquiring images in real time, S3: filtering, S4: binarized processed image, S5: extracting the contour, S6: identifying needle mushroom heads, S7: calculating the overall size of all mushroom heads, S8: calculating the proportion of the mushroom heads meeting the requirements to all the mushroom heads in the culture dish, and S9: and (5) after the detection is finished, outputting a result. According to the method, the overall size of the mushroom head is extracted, the size of the mushroom head is used as a needle mushroom maturation judgment condition, and the maturation degree of the mushroom head in the same culture dish is comprehensively judged as a ex-warehouse condition. The ex-warehouse condition of the flammulina velutipes can be accurately judged, and the growth quality of the flammulina velutipes is improved.
Description
Technical Field
Relates to a method for detecting the mature state of flammulina velutipes based on vision, and belongs to the technical field of growth detection of flammulina velutipes.
Background
The edible mushroom industry is a sunrise industry which is started under the background of accurate poverty relief in recent years. The edible fungus industry mainly comprises the links of strain cultivation, transfer, cultivation and the like. The flammulina velutipes is one of the strains widely planted in the edible fungi, and the strains are sterilized at high temperature of about 120 ℃ after being cultivated and then enter a culture room for culture. In the process of culturing in a sterile room, the growth condition of needle mushrooms can only be estimated by judging and combining with time through human eyes, so that the growth quality of the needle mushrooms is uneven, the sizes of mushroom heads are different, even a certain amount of needle mushrooms are lost due to time errors, and the subsequent packaging and weighing are influenced.
At present, automation develops vigorously in the edible mushroom industry, how to realize intellectualization, and mushroom cultivation, planting and ex-warehouse are automatically completed to become popular contents of current research. The ex-warehouse of the flammulina velutipes generally requires that the flammulina velutipes are not completely mature so as to keep the corresponding freshness, but cannot be too fresh, thus influencing the yield of the flammulina velutipes. According to the traditional method, the method for discharging the flammulina velutipes out of the mushroom warehouse within 28 days is not strict, and the growth conditions of the flammulina velutipes can be influenced by the planting time, illumination and humidity of the flammulina velutipes.
Disclosure of Invention
The invention aims to provide a method for detecting the mature state of flammulina velutipes based on vision so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the method for detecting the mature state of the flammulina velutipes based on vision comprises the following steps:
the method comprises the following steps: initializing a system;
step two: collecting images in real time;
step three: filtering;
step four: carrying out binarization processing on the image;
step five: extracting a contour;
step six: identifying needle mushroom heads;
step seven: calculating the overall sizes of all mushroom heads;
step eight: calculating the proportion of the mushroom heads meeting the requirements to all the mushroom heads in the culture dish;
step nine: and (5) after the detection is finished, outputting a result.
As a preferred technical solution of the present invention, after initialization in S1, a mature needle mushroom model is selected, contour information of all mushroom heads is extracted, and an average size of the mushroom heads is calculated as a reference.
As a preferable technical scheme of the present invention, in S2, the needle mushroom on the petri dish is subjected to real-time image acquisition, an adopted camera is a CCD camera, and a resolution of the CCD camera is 1920X 1280.
In a preferred embodiment of the present invention, in S3, noise processing is performed on noise generated by the whole apparatus by using 5X5 median filtering.
In a preferred embodiment of the present invention, the S5 extracts continuous contours, extracts contours that continuously satisfy more than 150 pixels, and identifies mushroom heads from the extracted contours in S6.
As a preferable technical scheme of the invention, whether the flammulina velutipes can be delivered is determined according to the outline size of the head identified in the step S6 and by comparing the area of the outline in the step S7.
As a preferred technical solution of the present invention, after the comparison in S7 is completed, the needle mushroom recognition result is fed back, when the matching pair is greater than or equal to the set matching degree threshold, the detection result is to be delivered, and when the matching pair is less than the set matching degree threshold, the detection result is immature, and after the detection is mature, the upper system feeds back a request for delivery to the database: the method for detecting the growth state of the flammulina velutipes based on the vision comprises the following application steps on specific equipment:
a1: powering up the system;
a2: initializing;
a3: collecting a culture dish image;
a4: detecting the growth state of mushroom;
a5: returning to continue executing the task;
a6: finishing;
after the initialization in the A2 is completed, automatically displaying that the self-checking is successful on an equipment display interface;
and the sample in the A5 is needle mushroom on a culture dish, photographing is carried out, whether the identification result is mature or not is checked, if the identification result is immature, the step of returning to A3 is carried out, if the identification result is mature, an upper system is called to carry out the warehouse-out, and the step of returning to A3 is carried out
Compared with the prior art, the invention has the beneficial effects that: according to the method for detecting the mature state of the flammulina velutipes based on the vision, the flammulina velutipes heads are identified based on the local characteristics and the global spatial structure information, the accuracy is high, the outlines of the flammulina velutipes heads are extracted, and the area size is calculated to compare and judge the growth condition of the flammulina velutipes.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting the growth state of flammulina velutipes based on vision provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. 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.
Referring to fig. 1, the invention provides a method for detecting the mature state of flammulina velutipes based on vision, which comprises the following steps:
the method comprises the following steps: initializing a system;
step two: collecting images in real time;
step three: filtering;
step four: carrying out binarization processing on the image;
step five: extracting a contour;
step six: identifying needle mushroom heads;
step seven: calculating the overall sizes of all mushroom heads;
step eight: calculating the proportion of the mushroom heads meeting the requirements to all the mushroom heads in the culture dish;
step nine: and (5) after the detection is finished, outputting a result.
After initialization in the step S1, selecting a mature needle mushroom model, extracting contour information of all mushroom heads, and calculating the average size of the mushroom heads as a reference.
Preferably, in S2, the needle mushroom on the culture dish is subjected to real-time image acquisition, the adopted camera is a CCD camera, and the resolution of the CCD camera is 1920X 1280.
Further, in S3, noise processing is performed on noise generated by the whole device by using 5X5 median filtering.
Further, the continuous contour is extracted in S5, the contour that continuously satisfies more than 150 pixels is extracted, and the mushroom head is identified from the extracted contour in S6.
And in the step S7, according to the mushroom head contour size identified in the step S6, comparing the contour areas, and determining whether the needle mushrooms can be delivered from the warehouse or not.
And S7, feeding back the needle mushroom identification result after the comparison is finished, wherein when the matching pair is greater than or equal to the set matching degree threshold, the detection result is required to be delivered, when the matching pair is less than the set matching degree threshold, the detection result is immature, and after the detection is mature, the upper system feeds back a request to be delivered to the warehouse: the method for detecting the growth state of the flammulina velutipes based on the vision comprises the following application steps on specific equipment:
a1: powering up the system;
a2: initializing;
a3: collecting a culture dish image;
a4: detecting the growth state of mushroom;
a5: returning to continue executing the task;
a6: finishing;
after the initialization in the A2 is completed, automatically displaying that the self-checking is successful on an equipment display interface;
and the sample in the A5 is needle mushroom on a culture dish, photographing is carried out, whether the identification result is mature or not is checked, if not, the identification result is returned to A3, and if the identification result is mature, the identification result is called to an upper system to be carried out of the warehouse, and the identification result is returned to A3.
After the system is operated, the initialization is firstly carried out, and the average size of the outline of the head of the needle mushroom is calculated as a standard according to the training of standard needle mushroom ex-warehouse samples. The system continuously collects mushroom images on the culture dish, filtering binarization processing is carried out, corresponding mushroom head contours are extracted, the contour area of the extracted mushroom head contours is calculated and compared with the standard contour area, after the contours meet the ex-warehouse condition, culture dish ex-warehouse signals are fed back to the superior system, and after the contours are ex-warehouse, the growth states of golden mushrooms are continuously collected and detected after new culture dishes are supplemented.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. The method for detecting the mature state of the flammulina velutipes based on vision is characterized by comprising the following steps of:
the method comprises the following steps: initializing a system;
step two: collecting images in real time;
step three: filtering;
step four: carrying out binarization processing on the image;
step five: extracting a contour;
step six: identifying needle mushroom heads;
step seven: calculating the overall sizes of all mushroom heads;
step eight: calculating the proportion of the mushroom heads meeting the requirements to all the mushroom heads in the culture dish;
step nine: and (5) after the detection is finished, outputting a result.
2. The vision-based needle mushroom maturation state detection method of claim 1, wherein: and after initialization in the step S1, selecting a mature needle mushroom model, extracting contour information of all mushroom heads, and calculating the average size of the mushroom heads as a reference.
3. The vision-based needle mushroom maturation state detection method of claim 1, wherein: and S2, acquiring images of the needle mushrooms on the culture dish in real time, wherein the adopted camera is a CCD camera, and the resolution of the CCD camera is 1920X 1280.
4. The vision-based needle mushroom maturation state detection method of claim 1, wherein: in S3, noise processing is performed on noise generated by the whole device by using 5X5 median filtering.
5. The vision-based needle mushroom maturation state detection method of claim 1, wherein: in the step S5, continuous contours are extracted, contours continuously satisfying more than 150 pixels are extracted and retained, and mushroom heads are identified from the extracted contours in the step S6.
6. The vision-based needle mushroom maturation state detection method of claim 5, wherein: and in the step S7, according to the mushroom head contour size identified in the step S6, comparing the contour areas, and determining whether the needle mushrooms can be delivered from the warehouse or not.
7. The vision-based needle mushroom maturation state detection method of claim 6, wherein: and feeding back the needle mushroom identification result after the comparison in the step S7, wherein when the matching pair is greater than or equal to the set matching degree threshold, the detection result is to be delivered, and when the matching pair is less than the set matching degree threshold, the detection result is immature, and after the detection is mature, the upper system feeds back a request for delivery to the database: the method for detecting the growth state of the flammulina velutipes based on the vision comprises the following application steps on specific equipment:
a1: powering up the system;
a2: initializing;
a3: collecting a culture dish image;
a4: detecting the growth state of mushroom;
a5: returning to continue executing the task;
a6: finishing;
after the initialization in the A2 is completed, automatically displaying that the self-checking is successful on an equipment display interface;
and the sample in the A5 is needle mushroom on a culture dish, photographing is carried out, whether the identification result is mature or not is checked, if not, the identification result is returned to A3, and if the identification result is mature, the identification result is called to an upper system to be carried out of the warehouse, and the identification result is returned to A3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237911.2A CN113933304A (en) | 2021-10-25 | 2021-10-25 | Vision-based needle mushroom maturity state detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237911.2A CN113933304A (en) | 2021-10-25 | 2021-10-25 | Vision-based needle mushroom maturity state detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113933304A true CN113933304A (en) | 2022-01-14 |
Family
ID=79283911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111237911.2A Pending CN113933304A (en) | 2021-10-25 | 2021-10-25 | Vision-based needle mushroom maturity state detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113933304A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114850192A (en) * | 2022-05-07 | 2022-08-05 | 江苏科泰生态农业科技有限公司 | Multi-source organic solid waste mobile type iterative biotransformation equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013005725A (en) * | 2011-06-22 | 2013-01-10 | Nikon Corp | Growth degree detection device, plant cultivation system, plant cultivation plant, growth degree detection method, and program |
| CN109214393A (en) * | 2018-07-25 | 2019-01-15 | 南华大学 | A kind of porous culture plate plate hole flora growth situation image detecting method and system |
| CN111489356A (en) * | 2020-05-25 | 2020-08-04 | 南京航空航天大学苏州研究院 | Vision-based method for detecting existence of spring of automobile door lock |
| CN111507959A (en) * | 2020-04-15 | 2020-08-07 | 江苏科恒环境科技有限公司 | Mushroom head quantity statistical system based on image recognition |
| CN111681216A (en) * | 2020-05-29 | 2020-09-18 | 浙江省农业科学院 | Method for acquiring high-throughput table type information of needle mushrooms |
| CN112509030A (en) * | 2020-12-14 | 2021-03-16 | 华中科技大学 | Plant measuring method, system, computer device and medium for multi-target detection |
-
2021
- 2021-10-25 CN CN202111237911.2A patent/CN113933304A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013005725A (en) * | 2011-06-22 | 2013-01-10 | Nikon Corp | Growth degree detection device, plant cultivation system, plant cultivation plant, growth degree detection method, and program |
| CN109214393A (en) * | 2018-07-25 | 2019-01-15 | 南华大学 | A kind of porous culture plate plate hole flora growth situation image detecting method and system |
| CN111507959A (en) * | 2020-04-15 | 2020-08-07 | 江苏科恒环境科技有限公司 | Mushroom head quantity statistical system based on image recognition |
| CN111489356A (en) * | 2020-05-25 | 2020-08-04 | 南京航空航天大学苏州研究院 | Vision-based method for detecting existence of spring of automobile door lock |
| CN111681216A (en) * | 2020-05-29 | 2020-09-18 | 浙江省农业科学院 | Method for acquiring high-throughput table type information of needle mushrooms |
| CN112509030A (en) * | 2020-12-14 | 2021-03-16 | 华中科技大学 | Plant measuring method, system, computer device and medium for multi-target detection |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114850192A (en) * | 2022-05-07 | 2022-08-05 | 江苏科泰生态农业科技有限公司 | Multi-source organic solid waste mobile type iterative biotransformation equipment |
| CN114850192B (en) * | 2022-05-07 | 2023-10-03 | 江苏科泰生态农业科技有限公司 | Multi-source organic solid waste mobile iterative bioconversion equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308697B (en) | Leaf disease identification method based on machine learning algorithm | |
| Yin et al. | Computer vision and machine learning applied in the mushroom industry: A critical review | |
| EP3373203B1 (en) | Equipment of localization of peduncle and method of localization of peduncle | |
| Wu et al. | Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms | |
| Nguyen et al. | Apple detection algorithm for robotic harvesting using a RGB-D camera | |
| CN109380146B (en) | Automatic measurement device and method for live pigs | |
| CN107610122B (en) | Micro-CT-based single-grain cereal internal insect pest detection method | |
| CN110599507B (en) | Tomato identification and positioning method and system | |
| CN112990103A (en) | String mining secondary positioning method based on machine vision | |
| CN111929299A (en) | Agricultural product planting analysis and management system based on machine vision | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN113933304A (en) | Vision-based needle mushroom maturity state detection method | |
| CN111680587A (en) | Multi-target tracking-based chicken flock activity real-time estimation method and system | |
| CN111369497B (en) | Walking type tree fruit continuous counting method and device | |
| CN114387343A (en) | Method for detecting picking position of mushroom stem of clustered oyster mushroom | |
| CN103500458A (en) | Method for automatically detecting line number of corncobs | |
| Taujuddin et al. | Detection of plant disease on leaves using blobs detection and statistical analysis | |
| CN116912025A (en) | Livestock breeding information comprehensive management method and system based on cloud edge cooperation | |
| Wang et al. | Detection of corn plant population and row spacing using computer vision | |
| CN114088714B (en) | Method for detecting surface regularity of grain particles | |
| Wu et al. | A Dense Litchi Target Recognition Algorithm for Large Scenes | |
| CN111144379B (en) | Automatic identification method for visual dynamic response of mice based on image technology | |
| CN112365532B (en) | High-precision cherry size grading method | |
| CN110135481B (en) | Crop lesion detection method and detection device | |
| Ji et al. | Measuring the cap diameter of white button mushrooms (Agaricus bisporus) by using depth image processing |
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 |