CN109685174B - Automatic analysis device and method for cucumber high yield - Google Patents

Automatic analysis device and method for cucumber high yield Download PDF

Info

Publication number
CN109685174B
CN109685174B CN201811600972.9A CN201811600972A CN109685174B CN 109685174 B CN109685174 B CN 109685174B CN 201811600972 A CN201811600972 A CN 201811600972A CN 109685174 B CN109685174 B CN 109685174B
Authority
CN
China
Prior art keywords
cucumber
data
cucumbers
image
handheld recorder
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.)
Active
Application number
CN201811600972.9A
Other languages
Chinese (zh)
Other versions
CN109685174A (en
Inventor
李凤菊
王浩
王建春
孙海波
钱春阳
张雪飞
杜彦芳
徐义鑫
吕雄杰
宋斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Information Research Institute Of Tianjin Academy Of Agricultural Sciences
Original Assignee
Information Research Institute Of Tianjin Academy Of Agricultural Sciences
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Information Research Institute Of Tianjin Academy Of Agricultural Sciences filed Critical Information Research Institute Of Tianjin Academy Of Agricultural Sciences
Priority to CN201811600972.9A priority Critical patent/CN109685174B/en
Publication of CN109685174A publication Critical patent/CN109685174A/en
Application granted granted Critical
Publication of CN109685174B publication Critical patent/CN109685174B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01G—WEIGHING
    • G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
    • G01G19/52—Weighing apparatus combined with other objects, e.g. furniture
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/40—Scaling the whole image or part thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • 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
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • 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
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/68—Food, e.g. fruit or vegetables

Abstract

The invention relates to a cucumber high yield automatic analysis device and a method, wherein the device comprises a measuring host and a handheld recorder; the handheld recorder includes: the handheld recorder comprises a handheld recorder shell (1), a rechargeable battery (2), a first antenna (3), a touch screen (4), a processing chip (5), a data storage module (6) and a data communication module (7); the measurement host computer include: the device comprises a stainless steel table top (8), universal wheels (9), a long-side horizontal ruler (10), a wide-side horizontal ruler (11), a bearing plate (12), a fixing plate (13), a gasket (14), a balance beam single-point type weighing sensor (15), a digital camera (16), an intelligent data processing module (17), a second antenna (18), a sensor lead interface (19) and a support rod piece (20); the invention can automatically record the variety number and the cucumber yield in real time in the process of cultivating the cucumber variety, and is convenient for scientific research personnel to carry out field operation.

Description

Automatic analysis device and method for cucumber high yield
Technical Field
The invention relates to the technical field of measurement, in particular to an automatic cucumber yield analysis device and method.
Background
In the breeding process of crop varieties such as cucumbers and the like, the weight of each picking in the whole growth period needs to be recorded in the screening process of each breeding material (strain) so as to analyze the difference of the weight of each melon, the early-stage yield, the later-stage yield and the total yield among the materials. The high yield is taken as the yield level of the crop variety under the actual production condition, which is the basic content for measuring the economic performance of the crop variety and is the main basis for determining the application range of the variety in the production practice. In the traditional cucumber variety breeding process, an agricultural expert needs to plant a plurality of cucumber varieties simultaneously, the expert sets different code numbers for the different varieties, the numbers are counted in the fruit harvest period, in the actual operation, an operator needs to continuously weigh, read and record data, carry the cucumber varieties to be measured and move the electronic scale, huge workload is brought to the breeding expert, meanwhile, certain human errors can be generated when data are copied from the electronic scale, and the level of the electronic scale can be influenced when the electronic scale is frequently carried to a proper position, so that system errors are caused. Therefore, the wireless acquisition device for automatically measuring the cucumber high yield can be manufactured, the functions of storing and uploading data can be completed, and the wireless acquisition device is particularly important in the aspects of saving time and labor force.
Disclosure of Invention
The embodiment of the invention provides a cucumber high yield automatic analysis device and method, and aims to solve the technical problems of the existing measuring device and method.
According to a specific implementation manner of the present invention, in a first aspect, an automatic cucumber yield analysis apparatus provided by an embodiment of the present invention includes a measurement host and a handheld recorder;
the handheld recorder includes: the handheld recorder comprises a handheld recorder shell 1, a rechargeable battery 2, a first antenna 3, a touch screen 4, a processing chip 5, a data storage module 6 and a data communication module 7; the handheld recorder shell 1 is made of waterproof plastic materials, and the antenna 3 is connected with the handheld recorder shell 1 through punching; a circuit board is arranged in the handheld recorder shell 1, and connectors of the processing chip 5, the battery 2 mounting seat, the touch screen 4 and the antenna 3 are welded on the circuit board;
the measurement host computer include: the device comprises a stainless steel table top 8, a universal wheel 9, a long-side horizontal ruler 10, a wide-side horizontal ruler 11, a bearing plate 12, a fixing plate 13, a gasket 14, a balance beam single-point type weighing sensor 15, a digital camera 16, an intelligent data processing module 17, a second antenna 18, a sensor lead interface 19 and a support rod 20; the processing chip 5 is composed of an STM32F103RBT6 control chip and peripheral circuits thereof.
The universal wheel 9 is arranged on the bottom surface of the fixed plate 13 and is used for the measurement host to move freely; the long-side horizontal ruler 10 and the wide-side horizontal ruler 11 are respectively positioned on the long side and the wide-side edge of the stainless steel table top 8 and used for leveling the stainless steel table top 8; the bearing plate 12 is tightly attached to the lower side of the top surface of the stainless steel table top 8, and the weighing sensor 15 is arranged between the bearing plate 12 and the fixing plate 13 through the gasket 14; the digital camera 16 is installed at one end of the supporting rod 20 and is used for acquiring image data of the cucumber and transmitting the image data to the intelligent data processing module 17, and the intelligent data processing module 17 detects phenotype data of the cucumber and transmits the phenotype data to the handheld recorder through the antenna 18 transmission module.
Optionally, the touch screen is a 4.3 inch true color resistive touch screen with a resolution of 480 x 272.
According to a specific embodiment of the present invention, in a second aspect, a method for automatically analyzing cucumber fertility by using the device as described above comprises the following steps:
the stainless steel table top 8 is leveled through the long-side horizontal rule 10 and the wide-side horizontal rule 11;
starting the handheld recorder, and inputting cucumber strain number codes through the touch screen 4;
acquiring weight data of the cucumbers through the weighing sensor 15;
acquiring image data of the cucumber through the digital camera 16;
and after processing the weight data and the image data, returning to the cucumber grading.
Optionally, after processing the weight data and the image data, returning to cucumber grading, including:
cutting and compressing the image data;
detecting the image by adopting an SSD target detection algorithm, and carrying out image segmentation on the image;
preprocessing each segmentation image to obtain the cucumber outline image;
acquiring the numerical value of a G channel in an original RGB image, and dividing cucumber colors into three levels according to a color distribution histogram of the G channel;
fixing the height of the digital camera 16, and calculating the length, width and radian of the cucumber according to the centroid coordinate, the coordinates of two end points of the cucumber profile and the coordinate of the circumscribed circle;
calculating the area of each contour in the contour image, and counting the thorny density by setting a relevant threshold;
dividing the cucumbers into four stages by adopting an SVM algorithm according to the weight, color, length, width, arc and density of the cucumbers;
and returning to cucumber grading.
Optionally, the SSD destination detection algorithm includes:
Figure BDA0001922490910000031
wherein m denotes a special featureNumber of figure, skRepresents the size ratio, s, of the kth feature map to the originalminAnd smaxIndicating the minimum and maximum values of the ratio.
Optionally, according to the weight, color, length, width, arc and density of cucumber, adopt SVM algorithm to divide the cucumber into four grades, including:
defining the data of melon weight, melon color, melon length, melon radian, melon thickness and cucumber density as 6 dimensions of cucumber fertility evaluation;
the quality of the cucumbers is classified by adopting an SVM algorithm model, and the model is as follows:
Figure BDA0001922490910000032
wherein the content of the first and second substances,
Figure BDA0001922490910000042
is a Lagrange multiplier, rtOutput quantity, x, of a 6-dimensional vector of classification of known samplestIs the input quantity, K (x), of a 6-dimensional vector of known samplestAnd x) is the kernel function of the SVM algorithm, expressed as follows:
Figure BDA0001922490910000041
wherein δ represents the training sample standard deviation;
the detected cucumbers are divided into special cucumbers, first-class cucumbers, second-class cucumbers and third-class cucumbers.
Compared with the prior art, the scheme of the embodiment of the invention at least has the following beneficial effects:
the automatic analysis device and method for the cucumber high yield, provided by the invention, are applied to the cucumber breeding process, can automatically record the variety number and the cucumber yield in real time in the cucumber variety cultivation process, automatically identify and classify the cucumber varieties according to the training model, are simple and convenient to operate, and are convenient for scientific research personnel to carry out field operation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a diagram of a host structure of an automatic analyzer according to an embodiment of the present invention.
Fig. 2 is a structural diagram of a hand-held recorder of the automatic analyzer according to the embodiment of the present invention.
Fig. 3 is a flow chart of an automatic analysis method according to an embodiment of the present invention.
FIG. 4 is a flow chart of model training of the automatic analysis method according to the embodiment of the present invention.
Fig. 5 is a melon color analysis flowchart of the automatic analysis method according to the embodiment of the present invention.
Fig. 6 is a flow chart of melon growth analysis of the automatic analysis method according to the embodiment of the present invention.
Fig. 7 is a schematic view of the overall structure of the automatic analyzer according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the 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.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe … … in the embodiments of the present application, these … … should not be limited to these terms. These terms are used only to distinguish … …. For example, the first … … can also be referred to as the second … …, and similarly the second … … can also be referred to as the first … … without departing from the scope of embodiments herein.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1 and fig. 2, according to an embodiment of the present invention, in a first aspect, an automatic cucumber fertility analyzing device provided by an embodiment of the present invention includes a measuring host and a handheld recorder;
the handheld recorder includes: the handheld recorder comprises a handheld recorder shell 1, a rechargeable battery 2, a first antenna 3, a touch screen 4, a processing chip 5, a data storage module 6 and a data communication module 7; the handheld recorder shell 1 is made of waterproof plastic materials, and the antenna 3 is connected with the handheld recorder shell 1 through punching; a circuit board is arranged in the handheld recorder shell 1, and connectors of the processing chip 5, the battery 2 mounting seat, the touch screen 4 and the antenna 3 are welded on the circuit board;
the measurement host computer include: the device comprises a stainless steel table top 8, a universal wheel 9, a long-side horizontal ruler 10, a wide-side horizontal ruler 11, a bearing plate 12, a fixing plate 13, a gasket 14, a balance beam single-point type weighing sensor 15, a digital camera 16, an intelligent data processing module 17, a second antenna 18, a sensor lead interface 19 and a support rod 20; the processing chip 5 is composed of an STM32F103RBT6 control chip and peripheral circuits thereof.
The universal wheel 9 is arranged on the bottom surface of the fixed plate 13 and is used for the measurement host to move freely; the long-side horizontal ruler 10 and the wide-side horizontal ruler 11 are respectively positioned on the long side and the wide-side edge of the stainless steel table top 8 and used for leveling the stainless steel table top 8; the bearing plate 12 is tightly attached to the lower side of the top surface of the stainless steel table top 8, and the weighing sensor 15 is arranged between the bearing plate 12 and the fixing plate 13 through the gasket 14; the digital camera 16 is installed at one end of the supporting rod 20 and is used for acquiring image data of the cucumber and transmitting the image data to the intelligent data processing module 17, and the intelligent data processing module 17 detects phenotype data of the cucumber and transmits the phenotype data to the handheld recorder through the antenna 18 transmission module.
Optionally, the touch screen is a 4.3 inch true color resistive touch screen with a resolution of 480 x 272.
Wherein, the first antenna 3 and the second antenna 18 of the hand-held recorder realize wireless communication.
Optionally, the balance beam single-point weighing sensor has a measuring range of 60kg, a comprehensive error of +/-0.017% f.s., a sensitivity of 2.0 +/-0.2 mV/V, and a protection grade of IP 65.
Optionally, the chip unit 5 is composed of an STM32F103RBT6 control chip and its peripheral circuits. Or a 32-bit ARM low-power-consumption microprocessor STM32F103RCT6 with 25Kbyte Flash and 48Kbyte RAM is adopted, the working frequency can reach 72MHz, and the requirements of data acquisition, processing, storage, display and transmission in the early stage of facility cucumber variety breeding can be met.
The touch screen unit comprises a touch screen, an external FLASH and an SD card. The touch screen adopts a true color resistance touch screen with the resolution of 480 x 272 and 4.3 inches, and is used for man-machine interaction in the whole data acquisition process; the FLASH is used for storing relevant parameters set through the touch screen; the SD card is used for storing the touch screen program for batch downloading. Optionally, the touch screen adopts a 7-inch true color resistance touch screen with a resolution of 800 × 480.
The external storage unit comprises an SD/TF card and an external circuit, wherein the external TF card is used for storing cucumber variety number codes and yield data, an FATFS file system is adopted to support a FAT12/FAT16/FAT32 file system compatible with Windows, the erasing period of the FATFS file system is up to 10W times, the support voltage is 2.7-3.6V, and standard SPI communication is supported.
The communication unit comprises a short-distance wireless communication module and a long-distance wireless transmission module. Wherein the short-distance wireless communication module adopts 433MHz frequency transmission, and the transmission distance is 400-700 m; the long-distance wireless transmission module GPRS adopts a SIM900A chip and an industrial standard interface, the working frequency is GSM/GPRS 850/900/1800/1900MHz, and the transmission of voice, SMS, data and fax information can be realized with low power consumption.
The power management unit in the handheld recorder comprises a lithium iron phosphate rechargeable battery for supplying power to the system; the power management unit in the measurement host comprises a 220VAC power interface meeting the international standard and a lithium iron phosphate rechargeable battery.
As shown in fig. 3, according to a second aspect of the present invention, a method for automatically analyzing cucumber fertility by using the device as described above comprises the following steps:
the stainless steel table top 8 is leveled through the long-side horizontal rule 10 and the wide-side horizontal rule 11;
starting the handheld recorder, and inputting cucumber strain number codes through the touch screen 4;
acquiring weight data of the cucumbers through the weighing sensor 15;
acquiring image data of the cucumber through the digital camera 16;
and after processing the weight data and the image data, returning to the cucumber grading.
Optionally, after processing the weight data and the image data, returning to cucumber grading, including:
cutting and compressing the image data;
detecting the image by adopting an SSD target detection algorithm, and carrying out image segmentation on the image;
preprocessing each segmentation image to obtain the cucumber outline image;
acquiring the numerical value of a G channel in an original RGB image, and dividing cucumber colors into three levels according to a color distribution histogram of the G channel;
fixing the height of the digital camera 16, and calculating the length, width and radian of the cucumber according to the centroid coordinate, the coordinates of two end points of the cucumber profile and the coordinate of the circumscribed circle;
calculating the area of each contour in the contour image, and counting the thorny density by setting a relevant threshold;
dividing the cucumbers into four stages by adopting an SVM algorithm according to the weight, color, length, width, arc and density of the cucumbers;
and returning to cucumber grading.
Optionally, the SSD model target detection algorithm includes:
Figure BDA0001922490910000081
wherein m denotes the number of characteristic diagrams, skIndicating the k-th feature map relative to the originalScale of the figure, sminAnd smaxIndicating the minimum and maximum values of the ratio.
An SSD algorithm model used for cucumber sample detection has a 16-layer network structure and 4366 training parameters, wherein cucumber features are extracted on 4 layers, 6 layers, 7 layers, 8 layers, 9 layers, 10 layers and 11 layers, in order to adapt to targets with different sizes, a multi-scale feature map mode is adopted for feature extraction, known cucumber sample data is used for training the network model to obtain corresponding parameter values to form a pd file for cucumber detection, and when a new cucumber image is photographed by a digital camera, the cucumber sample in the image can be quickly calibrated by using the training model.
As shown in fig. 4, the main work in the training of cucumber detection algorithm focuses on three aspects of training data preparation, model improvement and parameter adjustment.
In terms of training data preparation: the following three aspects of improvement are mainly carried out: (1) angle expansion, namely carrying out 0-180-degree random angle expansion on the basis of the existing training data. (2) And (4) illumination processing, namely performing brightness equalization before training to remove over-bright and over-dark data. (3) Scaling and expanding: and performing scaling data expansion based on the training data in a pyramid-like mode.
In terms of model improvement and parameter adjustment: (1) the characteristic graphs of different levels in the deep learning network have different sizes of receptive fields. For the SSD framework, the default box need not correspond to the actual receptive field of each layer. The tiling (tiling) of the default boxes can be designed so that a particular feature map learns to respond to a particular object dimension. By combining the characteristic characteristics of the cucumber, the ratio of increasing the thin height and the wide and flat shape is increased in the set, the degree of cutting between the default box and the cucumber is improved, and the detection effect is improved. (2) The main adjusting parameters in the model training are as follows: the learning rate and the batch size are adjusted by setting a larger value at the beginning of the model to quickly converge the network model, and the two parameter values are gradually smaller with the increase of the number of model iterations to maximize the accuracy of the whole model.
Optionally, according to the weight, color, length, width, arc and density of cucumber, adopt SVM algorithm to divide the cucumber into four grades, including:
defining the data of melon weight, melon color, melon length, melon radian, melon thickness and cucumber density as 6 dimensions of cucumber fertility evaluation;
the quality of the cucumbers is classified by adopting an SVM algorithm model, and the model is as follows:
Figure BDA0001922490910000091
wherein the content of the first and second substances,
Figure BDA0001922490910000102
is a Lagrange multiplier, rtOutput quantity, x, of a 6-dimensional vector of classification of known samplestIs the input quantity, K (x), of a 6-dimensional vector of known samplestAnd x) is the kernel function of the SVM algorithm, expressed as follows:
Figure BDA0001922490910000101
wherein δ represents the training sample standard deviation;
the detected cucumbers are divided into special cucumbers, first-class cucumbers, second-class cucumbers and third-class cucumbers.
As shown in fig. 5, the image after cucumber detection is segmented, the segmented image only contains one cucumber, the image is reconstructed through a window with the size of 500 × 500, the RGB three channels of the image are subjected to binarization processing by using a threshold value (130,255.0), the cucumber contour is detected by using a Canny operator, and scattered noise points in the image are eliminated by using an open operation mode, so that the final contour image of one single cucumber is obtained. Then, the color, length, width, radian and density of each cucumber are studied.
And acquiring the numerical value of a G channel of the original image according to the cucumber contour image, performing normalization processing, setting related threshold values through a color distribution histogram of the G channel, and defining the color histogram into three types, namely dark green, oil green and light green corresponding to cucumber colors.
As shown in fig. 6, the centroid of the profile is calculated according to the cucumber profile, the coordinates of two end points of the profile are obtained according to grid scanning, the circumscribed circle of the cucumber profile is determined according to the centroid coordinates and the coordinates of the two end points, and the camber value of the cucumber is calculated according to the circumscribed circle.
Because the digital camera is constant in height from the image, the cucumber length of the cucumber can be inversely calculated by calculating the Euclidean distance between two end points.
The line connecting the center of the circumscribed circle and the centroid intersects the outline at two points, and the distance between the two points is calculated as the thickness of the melon.
Calculating the area of each closed contour in the cucumber contour, carrying out normalization processing, defining the area between 0 and 100 as the stabbing smoothness, and obtaining the stabbing smoothness number and the stabbing smoothness total area through traversal accumulation.
Through the calculation, the phenotype data of the cucumber, namely the color, length, smoothness, density, radian and thickness of the cucumber are obtained.
The analysis device amplifies and conditions the output signal of the high-precision balance beam single-point type weighing sensor in the cucumber yield acquisition unit; the communication unit can transmit the measurement data to external equipment, such as an external server or equipment, through the antenna, and can also package and upload the measurement data to a cloud-end data server database for storage.
This embodiment has designed the wireless automatic statistics device of cucumber commodity nature (high yield) of handheld record appearance and measurement host computer separation, and two parts are connected through 433 MHz's short distance wireless transmission technique, make things convenient for researcher handheld device to record.
The interface that connects high accuracy compensating beam single-point formula weighing sensor has been designed to this embodiment to supply the measurement host computer to gather current output data in real time, guarantee accurate record cucumber variety number and the corresponding output data.
The embodiment can store the cucumber number codes and the yield data of different lines in the nonvolatile memory in batches, can flexibly set according to the specific planting situation, realizes the automatic yield statistics of different lines of cucumbers in the whole growth period, can receive perception layer data as facility agriculture internet of things middleware equipment, packages the perception layer data and uploads the perception layer data to an upper application layer data base, and plays a crucial role in the cucumber breeding link.
The automatic analysis device and method for the cucumber high yield, provided by the invention, are applied to the cucumber breeding process, can automatically record the variety number and the cucumber yield in real time in the cucumber variety cultivation process, automatically identify and classify the cucumber varieties according to the training model, are simple and convenient to operate, and are convenient for scientific research personnel to carry out field operation.
The whole equipment of this design has characteristics such as small, light in weight, easy operation, convenient to use, save the manual work, record accuracy.
The above embodiments are only examples, and do not have specific limiting effect, and the analysis device of the present invention can realize automatic recording and statistics of yield data of the whole growth period of different varieties of cucumbers in the breeding process. As shown in fig. 7, in the using process, the device is firstly placed in a greenhouse of a facility, the screen jump is carried out on a working table through a long-side horizontal ruler and a wide-side horizontal ruler to eliminate the system error in the measuring process, then a switch of the device is turned on, the serial number code compiled in advance by a breeding expert is input after a serial number code page is displayed and input by a touch screen, the collected same serial cucumber is placed on a stainless steel table of the device, a next serial number button on the touch screen is clicked after data to be measured is stable, the device automatically increases the number to enter the next serial number code, the measured cucumber is collected and stored, the next serial cucumber is placed, and the process is repeated until the yield of all the serial cucumbers is counted, the measured statistical data is stored in an external memory to facilitate analysis and arrangement of researchers, and after the statistics of the yield of each time in the whole growth period is completed, the system can count the data of single-hanging yield, early-stage yield, later-stage yield and total yield in the whole growth period according to the serial number of the cucumber strains.
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.
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 (6)

1. An automatic cucumber yield analysis device is characterized by comprising a measuring host and a handheld recorder;
the handheld recorder includes: the handheld recorder comprises a handheld recorder shell (1), a rechargeable battery (2), a first antenna (3), a touch screen (4), a processing chip (5), a data storage module (6) and a data communication module (7); the handheld recorder shell (1) is made of waterproof plastic materials, and the antenna (3) is connected with the handheld recorder shell (1) through punching; a circuit board is arranged in the handheld recorder shell (1), and a processing chip (5), a battery (2) mounting seat, a touch screen (4) and a connecting port of an antenna (3) are welded on the circuit board;
the measurement host computer include: the device comprises a stainless steel table top (8), universal wheels (9), a long-side horizontal ruler (10), a wide-side horizontal ruler (11), a bearing plate (12), a fixing plate (13), a gasket (14), a balance beam single-point type weighing sensor (15), a digital camera (16), an intelligent data processing module (17), a second antenna (18), a sensor lead interface (19) and a support rod piece (20); the processing chip (5) consists of an STM32F103RBT6 control chip and a peripheral circuit thereof;
the universal wheel (9) is arranged on the bottom surface of the fixed plate (13) and is used for the measurement host to move freely; the long-edge horizontal ruler (10) and the wide-edge horizontal ruler (11) are respectively positioned at the long edge and the wide edge of the stainless steel table top (8) and used for leveling the stainless steel table top (8); the bearing plate (12) is tightly attached to the lower side of the top surface of the stainless steel table top (8), and the weighing sensor (15) is arranged between the bearing plate (12) and the fixing plate (13) through the gasket (14); the digital camera (16) is arranged at one end of the supporting rod piece (20) and used for acquiring image data of the cucumbers and transmitting the image data to the intelligent data processing module (17), and the intelligent data processing module (17) detects phenotype data of the cucumbers and transmits the phenotype data to the handheld recorder through the antenna (18) transmission module.
2. The device of claim 1, wherein the touch screen is a 4.3 inch true color resistive touch screen with a resolution of 480 x 272.
3. A method for automatically analyzing cucumber fertility by using the device of claim 1 or 2, wherein the method comprises the following steps: the method comprises the following steps:
the stainless steel table top (8) is leveled through the long-side horizontal ruler (10) and the wide-side horizontal ruler (11);
starting the handheld recorder, and inputting cucumber strain number codes through the touch screen (4);
acquiring weight data of the cucumber through the weighing sensor (15);
acquiring image data of the cucumber through the digital camera (16);
and after processing the weight data and the image data, returning to the cucumber grading.
4. The method of claim 3, wherein: and after the weight data and the image data are processed, returning cucumber grading, which comprises the following steps:
cutting and compressing the image data;
detecting the image by adopting an SSD target detection algorithm, and carrying out image segmentation on the image;
preprocessing each segmentation image to obtain the cucumber outline image;
acquiring the numerical value of a G channel in an original RGB image, and dividing cucumber colors into three levels according to a color distribution histogram of the G channel;
fixing the height of the digital camera (16), and calculating the length, width and radian of the cucumber in a reverse manner according to the centroid coordinate, the coordinates of two end points of the cucumber profile and the coordinate of the circumscribed circle;
calculating the area of each contour in the contour image, and counting the thorny density by setting a relevant threshold;
dividing the cucumbers into four stages by adopting an SVM algorithm according to the weight, color, length, width, arc and density of the cucumbers;
and returning to cucumber grading.
5. The method of claim 4, wherein: the SSD destination detection algorithm comprises:
Figure FDA0001922490900000021
wherein m denotes the number of characteristic diagrams, skRepresents the size ratio, s, of the kth feature map to the originalminAnd smaxIndicating the minimum and maximum values of the ratio.
6. The method of claim 4, wherein: according to the weight, color, length, width, arc and density of cucumber, the SVM algorithm is adopted to divide the cucumber into four grades, including:
defining the data of melon weight, melon color, melon length, melon radian, melon thickness and cucumber density as 6 dimensions of cucumber fertility evaluation;
the quality of the cucumbers is classified by adopting an SVM algorithm model, and the model is as follows:
Figure FDA0001922490900000031
wherein the content of the first and second substances,
Figure FDA0001922490900000032
is a Lagrange multiplier, rtOutput quantity, x, of a 6-dimensional vector of classification of known samplestIs the input quantity, K (x), of a 6-dimensional vector of known samplestAnd x) is the kernel function of the SVM algorithm, expressed as follows:
Figure FDA0001922490900000033
wherein δ represents the training sample standard deviation;
the detected cucumbers are divided into special cucumbers, first-class cucumbers, second-class cucumbers and third-class cucumbers.
CN201811600972.9A 2018-12-26 2018-12-26 Automatic analysis device and method for cucumber high yield Active CN109685174B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811600972.9A CN109685174B (en) 2018-12-26 2018-12-26 Automatic analysis device and method for cucumber high yield

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811600972.9A CN109685174B (en) 2018-12-26 2018-12-26 Automatic analysis device and method for cucumber high yield

Publications (2)

Publication Number Publication Date
CN109685174A CN109685174A (en) 2019-04-26
CN109685174B true CN109685174B (en) 2021-09-21

Family

ID=66188501

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811600972.9A Active CN109685174B (en) 2018-12-26 2018-12-26 Automatic analysis device and method for cucumber high yield

Country Status (1)

Country Link
CN (1) CN109685174B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113518182B (en) * 2021-06-30 2022-11-25 天津市农业科学院 Cucumber phenotype characteristic measuring method based on raspberry pie

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201000556Y (en) * 2006-09-01 2008-01-02 上海农业信息有限公司 Crop cultivation monitoring apparatus
CN103125457A (en) * 2013-01-29 2013-06-05 华南农业大学 Orchard bactrocera dorsalis insect damage recognition system based on digital signal processing (DSP) and internet of things
CN103503637A (en) * 2013-10-14 2014-01-15 青岛农业大学 Intelligent identification picking robot and picking method
CN104503310A (en) * 2014-12-08 2015-04-08 天津市农业科学院信息研究所 Greenhouse environment and soil information remote monitoring device and use method thereof
CN204301841U (en) * 2014-12-19 2015-04-29 中山佳维电子有限公司 A kind of novel electronics is traced to the source platform balance
CN205209623U (en) * 2015-11-27 2016-05-04 广西壮族自治区农业科学院甘蔗研究所 Movable platform scale
CN106600434A (en) * 2016-10-18 2017-04-26 河南省农业科学院农业经济与信息研究所 Remote crop growth status monitoring method based on crop model and assimilation technology
CN207019779U (en) * 2017-06-06 2018-02-16 浙江宇阳衡器有限公司 One kind can survey high degree type electronic platform scale
CN207050830U (en) * 2017-07-25 2018-02-27 包头市金峰衡器制造有限公司 A kind of dynamic road vehicle overload detects bending plate type sensor system in real time
CN107967321A (en) * 2017-11-23 2018-04-27 北京信息科技大学 A kind of crop breeding evaluation method based on hierarchical support vector machines
CN108151644A (en) * 2016-12-02 2018-06-12 财团法人资讯工业策进会 Agricultural product detection device, agricultural product management system and method thereof
CN108572174A (en) * 2018-04-25 2018-09-25 苏州农业职业技术学院 A kind of quality of agricultural product index nondestructive detection method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10866584B2 (en) * 2016-05-09 2020-12-15 Strong Force Iot Portfolio 2016, Llc Methods and systems for data processing in an industrial internet of things data collection environment with large data sets

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201000556Y (en) * 2006-09-01 2008-01-02 上海农业信息有限公司 Crop cultivation monitoring apparatus
CN103125457A (en) * 2013-01-29 2013-06-05 华南农业大学 Orchard bactrocera dorsalis insect damage recognition system based on digital signal processing (DSP) and internet of things
CN103503637A (en) * 2013-10-14 2014-01-15 青岛农业大学 Intelligent identification picking robot and picking method
CN104503310A (en) * 2014-12-08 2015-04-08 天津市农业科学院信息研究所 Greenhouse environment and soil information remote monitoring device and use method thereof
CN204301841U (en) * 2014-12-19 2015-04-29 中山佳维电子有限公司 A kind of novel electronics is traced to the source platform balance
CN205209623U (en) * 2015-11-27 2016-05-04 广西壮族自治区农业科学院甘蔗研究所 Movable platform scale
CN106600434A (en) * 2016-10-18 2017-04-26 河南省农业科学院农业经济与信息研究所 Remote crop growth status monitoring method based on crop model and assimilation technology
CN108151644A (en) * 2016-12-02 2018-06-12 财团法人资讯工业策进会 Agricultural product detection device, agricultural product management system and method thereof
CN207019779U (en) * 2017-06-06 2018-02-16 浙江宇阳衡器有限公司 One kind can survey high degree type electronic platform scale
CN207050830U (en) * 2017-07-25 2018-02-27 包头市金峰衡器制造有限公司 A kind of dynamic road vehicle overload detects bending plate type sensor system in real time
CN107967321A (en) * 2017-11-23 2018-04-27 北京信息科技大学 A kind of crop breeding evaluation method based on hierarchical support vector machines
CN108572174A (en) * 2018-04-25 2018-09-25 苏州农业职业技术学院 A kind of quality of agricultural product index nondestructive detection method

Also Published As

Publication number Publication date
CN109685174A (en) 2019-04-26

Similar Documents

Publication Publication Date Title
US20180047177A1 (en) Systems, devices, and methods for monitoring and assessing characteristics of harvested specialty crops
CN107316116B (en) Leaf vegetable yield prediction method
CN209802305U (en) system for be used for crops output aassessment
CN113468964B (en) Hyperspectrum-based agricultural disease and pest monitoring method and device
CN102524024A (en) Crop irrigation system based on computer vision
CN103778630A (en) Field disease degree image identification method based on android
Sun et al. Remote estimation of grafted apple tree trunk diameter in modern orchard with RGB and point cloud based on SOLOv2
CN106971409A (en) Maize canopy leaf color modeling and method
CN111397709A (en) Rapid measurement method for thousand-grain weight of wheat
CN109685174B (en) Automatic analysis device and method for cucumber high yield
Tian et al. The detection system for greenhouse tomato disease degree based on android platform
CN112465893A (en) Vegetation leaf area measuring method and device, terminal and storage medium
CN111289997A (en) Method for detecting field crop canopy thickness based on laser radar sensor
CN114782840A (en) Real-time wheat phenological period classification method based on unmanned aerial vehicle RGB images
CN114596509A (en) Machine vision-based rice seedling leaf age period identification method
Miao et al. Measurement method of maize morphological parameters based on point cloud image conversion
CN112434569B (en) Unmanned aerial vehicle thermal imaging system
CN110882948B (en) Grapefruit quality classification method and device
CN109960972A (en) A kind of farm-forestry crop recognition methods based on middle high-resolution timing remotely-sensed data
CN111814585A (en) Unmanned aerial vehicle near-ground-to-air crop seedling condition remote sensing monitoring method and device and storage medium
CN116258844A (en) Rapid and accurate identification method for phenotype character of cotton leaf
CN110580495A (en) automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear
CN114283344A (en) Automatic real-time monitoring method and system for forest ecological hydrological process
CN115372281A (en) Monitoring system and method for physical structure and chemical composition of soil
CN110674453B (en) Method and system for acquiring digital image of cotton leaf cluster index

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