A potato damage and surface clay adhesion monitoring system, method and harvester

Abstract

The present application provides a potato damage and surface clay adhesion monitoring system, method and harvester, comprising a monitoring device and a control unit; the monitoring device is used for taking pictures of the potatoes before entering the potato collecting box and feeding back to the control unit; the control unit identifies the potato body boundary, damage site boundary and adhesion soil boundary according to the pictures of the potatoes, and calculates the damage rate and the adhesion rate of the potatoes; the damage site includes mechanical damage site; when the control unit identifies that the total mechanical damage rate of the potatoes exceeds the preset value, the data is fed back to the operator for adjusting the digging depth of the digging device; when the control unit identifies that the adhesion rate of the potatoes exceeds the preset value, the data is fed back to the operator for adjusting the linear velocity and vibration frequency of the potato harvester conveying and separating device. The present application reduces the damage rate of the potatoes and improves the harvesting quality of the potatoes.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of monitoring damage and surface clay adhesion in the potato harvesting process, and particularly relates to a potato damage and surface clay adhesion monitoring device and a harvester. BACKGROUND

[0002] In recent years, the planting area of potatoes in China has been increasing, and potatoes have become one of the main food crops in China, with a wide planting area. However, during the harvesting process of potatoes, a certain degree of mechanical damage will occur. Although there are methods for monitoring potato damage at present, there is a lack of statistics on the damage rate, and the operator cannot real-time understand the damage rate of potatoes during the harvesting process, so as to adjust the relevant working parameters of mechanical excavation in time to reduce mechanical damage and the like.

[0003] In addition, the damage such as insect eyes and rot cannot be monitored, and the quality of potatoes cannot be understood in time, and only one side of the potato can be photographed, so the damage of the other side cannot be obtained, which will cause calculation error.

[0004] In addition, excessive clay adhesion on the surface of potatoes will increase the impurity rate of potatoes, so that the harvesting quality is considered to be not high, and the quality is not good, so that the price is not high. Excessive soil enters the potato storage box and adheres or deposits in the box, which affects the environment in the box. At present, there is no monitoring of clay adhesion on the surface of potatoes in the potato harvesting technology, and the operator cannot adjust the working parameters of the potato-soil separation device in time according to the clay adhesion rate, which further leads to low harvesting quality. SUMMARY

[0005] In view of the above technical problems, the present application provides a potato damage and surface clay adhesion monitoring system and method, which at least solves one of the above technical problems, reduces the damage rate of potatoes, and improves the harvesting quality of potatoes.

[0006] The present application also provides a harvester comprising the potato damage and surface clay adhesion monitoring system.

[0007] The present application achieves the above technical purpose by the following technical means. A potato damage and surface clay adhesion monitoring system comprises a monitoring device and a control unit.

[0008] The monitoring device is used for photographing the picture of the potato before entering the potato collecting box and feeding back to the control unit.

[0009] The control unit identifies the potato body boundary, the damage site boundary and the attached soil boundary according to the picture of the potato, calculates the damage rate and the soil attachment rate of the potato, and the damage site includes the mechanical damage site, when the control unit identifies that the total mechanical damage rate of the potato exceeds a preset value, the data is fed back to the operator to adjust the digging depth of the digging device, and when the control unit identifies that the soil attachment rate of the potato exceeds a preset value, the data is fed back to the operator to adjust the linear speed and the vibration frequency of the conveying and separating device of the potato harvester.

[0010] In the above scheme, the control unit performs boundary segmentation on the picture of the potato taken by the monitoring device through the HSV color space, colors and distinguishes the potato body, the damage site and the attached soil of the picture of the potato taken by the monitoring device according to the color threshold of the potato body, the damage site and the attached soil, and obtains the soil surrounding circle, the potato body surrounding circle and the damage site surrounding circle according to the color distribution and the boundaries of different colors after the color distinction is completed, and calculates the damage rate and the soil attachment rate of the potato.

[0011] In the above scheme, the monitoring device includes a first industrial camera and a second industrial camera, and the monitoring device further includes a turnover device, the turnover device is used to turn over the potato, the first industrial camera takes the upper surface picture of the potato and transmits the upper surface picture to the control unit, the control unit controls the turnover device to turn over the potato, the second industrial camera takes the lower surface picture of the potato and transmits the lower surface picture to the control unit, and the control unit calculates the damage rate in combination with the upper surface picture and the lower surface picture of the potato.

[0012] Further, the turnover device includes a motor, an electric cylinder and a gear shifting mechanism, the gear shifting mechanism includes a rotating shaft, a plurality of gear shifting mechanisms are arranged on the rotating shaft, the motor is connected with the end of the rotating shaft and is used to drive the rotating shaft to rotate, and the electric cylinder is used to connect with the motor and is used to drive the motor to drive the gear shifting mechanism to move up and down. Further, the damage rate of the potato is calculated by using the coordinate filling block method and the integral method respectively, and then the average value of the two is taken as the damage rate.

[0013] In the above scheme, the damage site of the potato further includes one or more combinations of the insect eye and the rot, and therefore the damage rate of the potato includes the sum of one or more of the damage rates of the mechanical damage, the insect eye and the rot; the control unit calculates the damage rates of the mechanical damage, the insect eye and the rot, and displays the damage rates through the display.

[0014] In the scheme, the control unit uses a coordinate system to divide the soil surrounding circle and the potato body surrounding circle of the potato into two parts, performs function fitting on the boundary lines of the two parts, performs integral calculation on the function to calculate the areas of the two surrounding circles, subtracts the area of the potato body surrounding circle from the area of the soil surrounding circle, and then divides the result by the area of the potato body surrounding circle to obtain the soil adhesion rate of a single potato, calculates the longest soil adhesion distance of the potato, divides the sum of the soil adhesion rates of the multiple potatoes in the picture by the total number of the potatoes in the picture to obtain the soil adhesion rate of the potato, divides the sum of the longest soil adhesion distances of the multiple potatoes in the picture by the total number of the potatoes in the picture to obtain the longest soil adhesion distance of the potato, and feeds back data to the operator when the soil adhesion rate of the potato exceeds a preset value, and combines the soil adhesion rate of the potato and the longest soil adhesion distance of the potato to adjust the linear velocity and the vibration frequency of the conveying and separating device of the potato harvester.

[0015] A harvester comprising the potato damage and surface clay adhesion monitoring system.

[0016] A control method of the potato damage and surface clay adhesion monitoring system, comprising the following steps:

[0017] The monitoring device photographs the picture of the potato before entering the potato collecting box and feeds back to the control unit;

[0018] The control unit identifies the potato body boundary, the damage site boundary and the adhesion soil boundary according to the picture of the potato, and calculates the damage rate and the soil adhesion rate of the potato;

[0019] When the control unit identifies that the mechanical damage rate of the potato exceeds a preset value,

[0020] Data is fed back to the operator to adjust the digging depth of the digging device;

[0021] When the control unit identifies that the soil adhesion rate of the potato exceeds a preset value, data is fed back to the operator, and the soil adhesion rate of the potato and the longest soil adhesion distance of the potato are combined to adjust the linear velocity and the vibration frequency of the conveying and separating device of the potato harvester.

[0022] In the scheme, the monitoring device comprises a first industrial camera and a second industrial camera; the first industrial camera photographs the upper surface picture of the potato and transmits to the control unit, the control unit controls the turnover device to turn over the potato, the second industrial camera photographs the lower surface picture of the potato and transmits to the control unit, and the control unit calculates the damage rate in combination with the upper and lower surface pictures of the potato.

[0023] Compared with the prior art, the potato damage and surface clay adhesion monitoring system has the following beneficial effects:

[0024] 1. The present application is based on machine vision technology to monitor the device to take pictures of potatoes, and transmit to the control unit, the control unit according to the picture of the potato to identify the potato body boundary, the boundary of the damaged part on the potato and the boundary of the attached soil, calculate the damaged rate and the soil attached rate of the potato, and then together with the maximum attached distance of the potato, adjust the potato-soil separation work parameters to improve the quality and efficiency of the harvest.

[0025] 2. The present application is based on HSV color space to segment the boundary, according to the preset color threshold of potato body, damaged part and attached soil, to color and distinguish the potato body, damaged part and attached soil of the picture taken by the monitoring device; after color distinction, the soil surrounding circle, the potato body surrounding circle and the damaged part surrounding circle can be obtained according to the color distribution and the boundary of different colors, and the damaged rate and the soil attached rate of the potato can be calculated; the damaged rate of the potato is calculated by the coordinate block filling method and / or integral method, and the soil attached rate of the potato is calculated by the integral method. In order to ensure the detection result of the damaged rate more accurate, the damaged rate of the potato is calculated by the coordinate block filling method and the integral method respectively, and the average value of the two is taken as the damaged rate of the potato. The damaged rate can be displayed on the display, so that the operator can know the damaged condition of the potato in real time and adjust the relevant work parameters in time to reduce the economic loss.

[0026] 3. The damaged part of the present application includes mechanical damaged part, when the control unit identifies that the total mechanical damaged rate of the potato exceeds the preset value, the data is fed back to the operator to adjust the digging depth of the digging device to reduce the mechanical damaged rate of the potato in the harvesting process.

[0027] 4. The damaged part of the potato of the present application also includes one or more combinations of insect eyes and rot, so that the damaged rate of a single potato includes the sum of one or more of the damaged rates of mechanical damage, insect eyes and rot; the control unit calculates the total damaged rate of mechanical damage, insect eyes and rot, which not only knows the mechanical damage of the potato, but also knows the damaged rate of the insect eyes and rot of the potato, so as to know the quality of the potato in time, and provide reference for the next season planting, such as whether to increase the amount of pesticide for the next year planting when the insect eye rate is too high. The detection of the overall damaged rate can also make an estimate of the subsequent use of the potato, and the potato with high total damaged rate can be used to make industrial starch, and the potato with low total damaged rate can be used to make food.

[0028] 5. The present application takes potato picture information by machine vision technology, identifies the potato boundary and the surface attached soil, and calculates the soil attachment rate according to the integral method. When the control unit identifies that the soil attachment rate of the potato exceeds the preset value, the data is fed back to the operator, and the soil attachment rate of the potato and the longest soil attachment distance of the potato are combined to adjust the linear speed and vibration frequency of the potato harvester conveying and separating device, so as to reduce the soil attached to the surface of the potato and improve the harvesting efficiency and quality.

[0029] 6. The present application turns over the potato by the electric cylinder and the motor double-drive gear mechanism of the turning device, shoots the damage position on the upper and lower surfaces, combines the picture of the upper and lower surfaces of the potato to calculate the damage rate by the control unit, improves the damage rate detection accuracy, and solves the problem of traditional single-side detection.

[0030] Note that the description of these effects does not hinder the existence of other effects. One embodiment of the present application does not necessarily have all the above-mentioned effects. Effects other than the above-mentioned effects can be clearly seen and extracted from the description, drawings, claims, etc. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is a control method flowchart of a potato damage and surface clay attachment monitoring system of an embodiment of the present application;

[0032] Figure 2 is a gear mechanism structure schematic diagram of an embodiment of the present application;

[0033] Figure 3 is an enlarged view of the gear end surface;

[0034] Figure 4 is a potato turning force schematic diagram;

[0035] Figure 5 is a potato damage rate detection flowchart of an embodiment of the present application;

[0036] Figure 6 is a potato damage site schematic diagram of an embodiment of the present application;

[0037] Figure 7 is a potato mechanical damage rate calculation schematic diagram of an embodiment of the present application;

[0038] Figure 8 is a potato soil attachment rate detection flowchart of an embodiment of the present application;

[0039] Figure 9 is a potato soil attachment rate calculation schematic diagram of an embodiment of the present application;

[0040] Figure 10This is a schematic diagram illustrating the calculation of the longest adhesion distance of potatoes to soil according to one embodiment of the present invention.

[0041] Figure 11 This is a schematic diagram of a process for adjusting the digging depth of potatoes according to the degree of mechanical damage according to one embodiment of the present invention;

[0042] Figure 12 This is a partial structural schematic diagram of a harvester according to one embodiment of the present invention.

[0043] In the diagram: 1. Excavation device, 2. Conveying and separating device, 3. Separating and lifting reversing device, 4. Monitoring device, 4.1. First industrial camera, 4.2. Second industrial camera, 5. Potato collection box, 6. Motor, 7. Electric cylinder, 8. Tooth-shifting mechanism. Detailed Implementation

[0044] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0045] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "front," "rear," "left," "right," "upper," "lower," "axial," "radial," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0046] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0047] In combination Figure 1 As shown in FIG. 1, a potato damage and surface clay adhesion monitoring system comprises a monitoring device 4 and a control unit;

[0048] The monitoring device 4 is used to take pictures of the potatoes before entering the potato collecting box 5 and feed back to the control unit;

[0049] The control unit identifies the potato body boundary, damage site boundary and adhesion clay boundary according to the pictures of the potatoes, calculates the damage rate and clay adhesion rate of the potatoes; the damage site includes mechanical damage site, when the control unit identifies that the mechanical damage rate of the potatoes exceeds the preset value, the data is fed back to the operator for adjusting the digging depth of the digging device 1; when the control unit identifies that the clay adhesion rate of the potatoes exceeds the preset value, the data is fed back to the operator for adjusting the linear speed and vibration frequency of the conveying and separating device 2 of the potato harvester.

[0050] In an embodiment of the present application, the monitoring device 4 comprises a first industrial camera 4.1 and a second industrial camera 4.2; the first industrial camera 4.1 is used to take pictures of the upper surface of the potatoes, the second industrial camera 4.2 is used to take pictures of the lower surface of the potatoes, and a turnover mechanism is further included; the turnover device is used to turn over the potatoes so that the monitoring device 4 can take pictures of the upper and lower surfaces of the potatoes, and the upper and lower surface pictures are transmitted to the control unit; the control unit combines the sum of the damage rates of the upper and lower surface pictures as the damage rate of a single potato, which improves the accuracy of damage rate detection.

[0051] In an embodiment of the present application, the turnover device comprises a motor 6, an electric cylinder 7 and a gear shifting mechanism 8; the gear shifting mechanism 8 comprises a rotating shaft, a plurality of gear shifting mechanisms are arranged on the rotating shaft, the motor 6 is connected with the rotating shaft for driving the rotating shaft to rotate, the electric cylinder 7 is connected with the motor 6 for driving the motor 6 to drive the gear shifting mechanism 8 to move up and down, and the motor 6 and the electric cylinder 7 are respectively connected with the control unit.

[0052] In combination Figure 2 , 3 After the industrial camera 4 shown in FIG. 4 takes pictures of the upper surface damage of the potatoes, the potatoes are turned over under the action of the rotating gear shifting mechanism 8; first, the motor 6 drives the gear shifting to rotate, the gear shifting mechanism 8 applies a leftward force F1 to the potatoes, at the same time, the electric cylinder 7 extends upward to drive the gear shifting mechanism 8 to move upward, at the same time, the gear shifting mechanism 8 applies an upward force F2 to the potatoes, the resultant force F3 of the two forces makes the potatoes turn over, after turning over, the lower surface damage of the potatoes is taken by the industrial camera 4, so as to calculate the total damage rate of the upper and lower surfaces of the potatoes, the end of the gear shifting mechanism 8 is made into a circular arc smooth surface to avoid damage to the potatoes during turning over, and the electric cylinder 7 is restored after extension to ensure the turning over of the next potato.

[0053] The electric cylinder 7 and the double-drive ratchet mechanism 8 driven by the motor 6 turn over the potatoes, and the monitoring device 4 shoots the damage pictures of the upper and lower surfaces of the potatoes, thereby improving the accuracy of the damage rate detection and solving the problem of the traditional single-surface detection.

[0054] In an embodiment of the present application, the damage types of the potatoes include mechanical damage, insect eyes and rot.

[0055] In an embodiment of the present application, the discrimination of the damage types of the potatoes can be determined by machine vision combined with a Bayesian classifier, and the specific method can refer to the application of the Bayesian classifier in the external quality detection of potatoes.

[0056] In an embodiment of the present application, the method based on deep learning can be used to detect the mechanical damage of the potatoes, and the specific method can refer to the application research on the deep learning-based potato mechanical damage detection method. In an embodiment of the present application, the method based on deep learning can also be used to detect the insect eyes and rot of the potatoes by training the sample images of the insect eyes and rot of the potatoes.

[0057] In an embodiment of the present application, taking the method of machine vision combined with a Bayesian classifier as an example: a Bayesian classifier prediction model for the external quality of potatoes is established, the images of three types of potato damage, i.e., insect eyes, mechanical damage and rot, are collected by machine vision technology, the feature data of the color images of the potatoes are extracted, the prediction model for different external qualities of the potatoes is established, the feature information is obtained from the color images of the potatoes, the extracted data is smoothed, and the prediction model is established combined with the Bayesian classifier to output the prediction result of the potato damage.

[0058] The process is as follows: potato sample→feature extraction→selection of training set and prediction set→establishment of prediction model (training set)→output of prediction result (prediction set). In an embodiment of the present application, the control unit discriminates the type of potato damage by the Bayesian classifier prediction model for the external quality of potatoes based on the pictures of the potatoes shot by the first industrial camera 4.1 and the second industrial camera 4.2 of the monitoring device 4, and then performs boundary segmentation by the HSV color space, colors and distinguishes the potato body, the damage site and the attached soil of the potatoes according to the color threshold of the potato body, the damage site and the attached soil of the potatoes preset in the pictures of the potatoes shot by the monitoring device 4; after the color distinction is completed, the soil surrounding circle, the potato body surrounding circle and the damage site surrounding circle can be obtained according to the color distribution and the boundaries of different colors, and the damage rate and the soil attachment rate of a single potato are calculated; the damage rate of a single potato is calculated by the coordinate block filling method and / or the integral method, and the soil attachment rate of a single potato is calculated by the integral method.

[0059] In one embodiment of the present application, preferably, the damage rate of the single potato is calculated by using the coordinate filling block method and the integral method respectively, and the average of the two is taken as the final damage rate of the single potato.

[0060] In one embodiment of the present application, preferably, the control unit identifies the average damage rate of the plurality of damaged potatoes in the picture of the potatoes taken by the monitoring device 4 as the damage rate of the plurality of potatoes in the picture.

[0061] In one embodiment of the present application, preferably, the damaged part of the potato further includes one or a combination of the following: insect eyes, rot, and the damage rate of the single potato includes one or a combination of the following: the damage rate of mechanical damage, insect eyes, and rot; the control unit calculates the total damage rate of mechanical damage, insect eyes, and rot and displays it on the display, so that the grower can not only know the mechanical damage of the potato, but also know the damage rate of the potato insect eyes and rot, so as to timely know the quality of the potato and provide a reference for the next season planting, for example, if the insect eye rate is too high, the grower can know whether to increase the amount of pesticide in the next season planting, and the detection of the overall damage rate can also make an estimate of the subsequent use of the potato, for example, the potato with a high total damage rate can be used to make industrial starch, and the potato with a low total damage rate can be used to make food.

[0062] According to the present embodiment, preferably, the control unit divides the soil surrounding circle and the potato body surrounding circle into two parts using the coordinate system, performs function fitting on the boundary lines of the two parts, calculates the areas of the two surrounding circles by integrating the function, calculates the soil adhesion rate of the single potato by subtracting the area of the potato body surrounding circle from the area of the soil surrounding circle and then dividing the result by the area of the potato body surrounding circle, calculates the longest soil adhesion distance of the potato, calculates the soil adhesion rate of the plurality of potatoes in the picture of the potatoes taken by the monitoring device 4 by dividing the sum of the soil adhesion rates of the plurality of potatoes by the total number of the potatoes in the picture, and calculates the longest soil adhesion distance of the plurality of potatoes by dividing the sum of the longest soil adhesion distances of the plurality of potatoes by the total number of the potatoes in the picture; when the soil adhesion rate of the potato exceeds a preset value, the data is fed back to the operator, and the soil adhesion rate of the potato and the longest soil adhesion distance of the potato are used to adjust the linear velocity and the vibration frequency of the conveying and separating device 2 of the potato harvester.

[0063] A control method of the potato damage and surface clay adhesion monitoring system, comprising the following steps:

[0064] The first industrial camera 4.1 takes a picture of the upper surface of the potato before entering the potato collecting box 5 and feeds back to the control unit.

[0065] The control unit identifies the potato body boundary, the damaged site boundary and the attached soil boundary according to the upper surface picture of the potato, and calculates the upper surface damage rate and the soil attachment rate of the potato;

[0066] The tooth mechanism 8 turns over the potato, the second industrial camera 4.2 shoots the lower surface picture of the potato before entering the potato collecting box 5, and feeds back to the control unit;

[0067] The control unit identifies the potato body boundary, the damaged site boundary and the attached soil boundary according to the lower surface picture of the potato, and calculates the lower surface damage rate of the potato;

[0068] The damaged site includes a mechanical damaged site, when the control unit identifies that the total mechanical damage rate of the upper and lower surfaces of the potato exceeds a preset value, the data is fed back to the operator, and the operator adjusts the digging depth of the digging device 1 according to the data;

[0069] When the control unit identifies that the total soil attachment rate of the potato exceeds a preset value, the data is fed back to the operator, and the soil attachment rate of the potato and the longest soil attachment distance of the potato are combined to adjust the linear speed and vibration frequency of the potato harvester conveying and separating device 2.

[0070] In an embodiment of the present application, preferably, the longest soil attachment distance of the potato is obtained by the following steps:

[0071] After the first industrial camera 4.1 shoots the potato and the attached soil, the boundary coordinates are identified, the longitudinal longest distance and the transverse longest distance of the potato are marked, and an auxiliary circle is drawn with the intersection point as the center and half of the longest distance in the longitudinal direction or the transverse direction as the radius r1, then the longest radius r from the center point to the boundary of the attached soil is marked, and r-r1 is recorded as the longest attachment distance of the attached soil.

[0072] In an embodiment of the present application, preferably, the longest soil attachment distance of the potato is obtained by the following steps:

[0073] When the surface soil attachment rate R f > m, and the longest attachment distance r-r1 > k, the linear speed and vibration frequency of the potato-soil separating device are simultaneously increased;

[0074] When the surface soil attachment rate R f > m, and the longest attachment distance r-r1 < k, only the vibration frequency is increased;

[0075] When the surface soil attachment rate R f < m, and the longest attachment distance r-r1 > k, only the linear speed of the potato-soil separating device is increased;

[0076] When the surface soil adhesion rate R f When the longest adhesion distance r-r1≤k, no adjustment is needed.

[0077] Wherein, m and k are preset adhesion rate and adhesion radius critical values, which are determined according to potatoes and harvesting environment.

[0078] In a specific embodiment of the present application, the monitoring device 4 takes potato picture information by machine vision technology, identifies the boundaries of potato, insect eye, mechanical damage, rotting and the like, and calculates the damage rate of the potato by using the coordinate filling block method and the integral method, takes the average value of the two as the final damage rate of the potato and displays it on the display. Secondly, the soil adhesion rate of the potato is calculated by the integral method, and then the maximum adhesion radius of the potato is combined to realize efficient harvesting by adjusting the potato-soil separation working parameters.

[0079] In a specific embodiment of the present application, the damage of the potato is divided into mechanical damage, insect eye, rotting and the like, and under machine vision, not only can the damaged potato be identified, but also the damage rate and the clay adhesion rate of the potato can be calculated by the control unit, and the results are displayed in real time, which is convenient for the operator to adjust the working parameters in time, ensures the harvesting efficiency, and understands the quality of the potato.

[0080] In combination Figure 5 As shown in the figure, in a specific embodiment of the present application, after the first industrial camera 4.1 shoots the upper surface picture of the potato, the picture is transmitted to the control unit, and after the type of potato damage is distinguished by the potato external quality Bayesian classifier prediction model, the control unit colors and distinguishes the color of the potato boundary, damage and attached soil according to the set color threshold value in the HSV space. The specific steps are as follows:

[0081] The image is segmented by using the gray threshold segmentation method. The segmentation method is actually a kind of transformation from the input image f to the output image g:

[0082] In the formula, T1 is the threshold value of the potato boundary and the damage boundary, and T2 is the threshold value of the potato boundary and the soil adhesion boundary. For the image elements of the potato, g(x, y)=1, corresponding to yellow; for the image elements of the damage boundary, g(x, y)=2, corresponding to green; for the image elements of the soil adhesion boundary, g(x, y)=0, corresponding to black. The color can be pre-set according to the actual situation.

[0083] In combination Figure 6As shown, after the image color segmentation is completed, the soil surrounding circle, the potato body surrounding circle and the damaged part surrounding circle can be obtained according to the color distribution and the boundaries of different colors. Then the total area of the potato and the area of the damaged part are calculated by the translation of the coordinate area block, so as to calculate the damage rate by the following method:

[0084] After the machine vision identifies the upper surface of the potato and the boundary of the damaged range, the control system calculates the areas of the two by the coordinate area block. Taking the mechanically damaged potato as an example, the coordinates start from the left (0, 0), then the X coordinate is increased by x1, x1 is the length of the coordinate block used to calculate the area of the potato, and the Y coordinate is translated upwards and downwards according to the boundary of the identified potato, as shown in the following formula: Figure 6 As shown in the upper end coordinates of the second coordinate area block, the upper end coordinates are changed to (x1, y1), and the lower end coordinates are changed to (x1, -y2). The coordinate block is filled in turn to the right until the potato is filled, and the upper end coordinates of the right end coordinate block are (nx1, -y 2n-1 ), and the lower end coordinates are (nx1, -y 2n ). y 2n-1 and -y 2n represent the upper and lower coordinate values of the y-axis corresponding to the n-th coordinate block when filling the potato area, so the total area of the potato domain under the machine vision is:

[0085] S MA = x1(y1+y2)+x1(y3+y4)+……+x1(y 2n-1 +y 2n )

[0086] n represents the number of filling blocks, which is generally equal to and the upper integer;

[0087] According to the same method, the area of the mechanically damaged domain is calculated. The length of the coordinate block used to calculate the area of the mechanically damaged domain is designed as x2, the coordinates start from the left (0, 0), then the X coordinate is increased by x2 to translate to the right, and the Y coordinate is translated upwards and downwards according to the boundary of the identified mechanically damaged domain. After translation, the upper end coordinates of the second coordinate area block are changed to (x2, y'1), and the lower end coordinates are changed to (x2, -y'2). The coordinate block is filled in turn to the right until the mechanically damaged domain is filled, and the upper end coordinates of the right end coordinate block are (nx2, -y' 2n-1 ), and the lower end coordinates are (nx2, -y' 2n ). Thus the area of the mechanically damaged domain is:

[0088] S jixie = x2(y'1+y'2)+x2(y'3+y'4)+……+x2(y' 2n-1 +y'2n )

[0089] wherein n represents the number of filled blocks, is related to the total length of the x direction of the mechanical damage domain, n is generally equal to and rounding up the integer; x2 is the length of the coordinate block used to calculate the area of the mechanical damage domain.

[0090] Therefore, the damage rate of the potato under mechanical damage can be calculated as:

[0091]

[0092] In one embodiment of the present application, the potato bug eye damage rate and the rot rate can also be calculated by using the above-mentioned mechanical damage rate calculation method.

[0093] In one embodiment of the present application, in combination with Figure 7 As shown in FIG. 4, to ensure that the calculated damage rate result is more accurate, the above-mentioned coordinate block area method is used together with the integral method to calculate the damage rate, and the calculation process is shown as follows:

[0094] Similarly, taking the mechanical damage type potato as an example for calculation, first, the machine vision of the monitoring device 4 takes the upper surface of the potato and the mechanical damage boundary, then the boundary coordinates are captured by the control unit, the coordinates divide the potato boundary into two parts, taking the upper part as an example for calculation, the storage module of the control module stores the potato boundary coordinates, the coordinate point of the right boundary of the potato is (a, 0), and the coordinate point of the right boundary of the mechanical damage domain is (b, 0), and the potato damage rate is calculated according to the following steps:

[0095] The storage module of the control unit stores the potato boundary coordinates;

[0096] The fitting function program is called to perform function fitting of the upper boundary of the potato→ the upper boundary function f1(x) of the potato;

[0097] The integral function is called to calculate the area of the upper boundary of the potato→

[0098] The storage module of the control unit stores the mechanical damage domain boundary coordinates;

[0099] The control unit calls the fitting function to perform function fitting of the upper boundary of the mechanical damage domain→ the upper boundary function f3(x) of the mechanical damage domain; the integral function is called to calculate the area of the upper boundary of the mechanical damage domain→

[0100] The area of the lower boundary of the mechanical damage domain is calculated by the same method as the upper boundary→

[0101] The upper surface damage rate of the potato is calculated as:

[0102] Both methods calculate the mechanical damage rate on the upper surface of the potato, i.e.

[0103] By the above method, we obtain, respectively, and

[0104] The total damage rate on the upper surface of the potato is:

[0105] wherein, is the eye damage rate on the upper surface of the potato, is the rot damage rate on the upper surface of the potato.

[0106] In one embodiment of the application, the damage rate on the lower surface of the potato is also calculated by the method for calculating the damage rate on the upper surface of the potato:

[0107] After the potato is turned over by the tooth mechanism 8, the first industrial camera 4.1 takes the lower surface of the potato with the mechanical damage boundary,

[0108] The mechanical damage rate on the lower surface of the potato is:

[0109] The total mechanical damage rate on the potato is:

[0110] The damage rate on the lower surface of the potato is:

[0111] The total damage rate on the potato is: zong = Rx zong + Rs zong

[0112] is the eye damage rate on the lower surface of the potato, is the rot damage rate on the lower surface of the potato, is the mechanical damage rate on the lower surface of the potato, Rx zong is the total damage rate on the lower surface of the potato.

[0113] In one embodiment of the application, the monitoring of the soil adhered to the surface of the potato is monitored by the following method: Figure 8 and 9

[0114] ​According to the integral method scheme for calculating the damaged rate of potatoes, the surface soil adhesion rate of potatoes is calculated, first, the potato picture is taken by the machine vision of the monitoring device 4, the potatoes with soil adhesion are automatically classified by the prediction model, after the image color segmentation, the potato boundary and the attached soil form two enclosures and are yellow and black respectively, then the boundary coordinate capture is realized by the control unit, the coordinates divide the potato boundary and the attached soil into upper and lower parts, taking the upper part as an example, the control unit stores the potato boundary coordinates, the coordinate point of the right boundary of the potato is (c, 0), the coordinate of the left boundary is (e, 0), the coordinate point of the right boundary of the soil is (d, 0), and the surface soil adhesion rate of the potato is calculated according to the following steps:

[0115] The control unit stores the potato boundary coordinates in the storage module;

[0116] The control unit calls the fitting function to perform function fitting on the upper boundary of the potato → the upper boundary function f5(x) of the potato;

[0117] The integral function is called to calculate the area of the upper boundary of the potato →

[0118] The area of the lower boundary of the potato is calculated in the same way as the upper boundary →

[0119] The control unit stores the attached soil boundary coordinates in the storage module;

[0120] The fitting function program is called to perform function fitting on the upper boundary of the attached soil → the upper boundary function f7(x) of the attached soil;

[0121] The integral function is called to calculate the area of the upper boundary of the attached soil →

[0122] The area of the lower boundary of the attached soil is calculated in the same way as the upper boundary →

[0123] The surface soil adhesion rate of the potato is calculated as:

[0124] In an embodiment of the present application, in order to better understand the surface soil adhesion of potatoes, in addition to the above-mentioned integral method for calculating the surface soil adhesion rate of potatoes, the soil adhesion radius r is also used to represent the adhesion of soil on the surface of potatoes, by adjusting the working parameters of the potato-soil separation device 2, the working effect is ensured, and the calculation of the potato soil adhesion rate only needs to be calculated by the front first industrial camera 4.1, because the soil will scatter during the turning process, which will cause inaccurate data.

[0125] In a specific embodiment of the present application,Figure 10 As shown in the following way:

[0126] When the machine vision of the monitoring device 4 takes a picture of the potato and the attached soil, the boundary coordinates are identified, the longitudinal longest distance and the transverse longest distance of the potato are marked, and an auxiliary circle is drawn with the intersection point as the center and half of the longest distance in the longitudinal or transverse direction as the radius r1. Then the longest radius r of the boundary of the attached soil to the center point is marked, and r-r1 is recorded as the longest attached distance of the attached soil. Then the potato harvester potato-soil separation device is adjusted, including the line speed, vibration frequency and other parameters of the potato-soil separation device 2. In an embodiment of the present application, the adjustment process is as shown in Table 1:

[0127] Table 1: Adjustment of potato-soil separation device parameters

[0128] Surface soil adhesion rate Longest adhesion distance Parameters adjustment of potato-soil separation device [RC f > m [r - r1 > k] Increase both linear velocity and vibration frequency of potato-soil separation device [RC f > m [r - r1 < k] Increase vibration frequency only [R f <m]] [r - r1 > k] Increase linear velocity of potato-soil separation device only [R f ≤m]] [r - r1≤ k] No adjustment

[0129] Wherein m and k are introduced attachment rate and attachment radius critical value, which are determined according to potato and harvesting environment. The potato soil attachment radius and attachment rate are calculated only on the upper surface.

[0130] In an embodiment of the present application, in combination with Figure 11 As shown, when the identified potato damage rate is too high, the data can be fed back to the operator for timely adjustment of the potato digging depth to reduce the rate of mechanical damage controllable by humans.

[0131] The total mechanical damage rate of the potato has been calculated in the above manner:

[0132]

[0133] R jixie R is the total mechanical damage rate of the upper and lower surfaces of the potato.

[0134] In an embodiment of the present application, in combination with Table 2, when R jixie ≥e, the operator can appropriately increase the digging depth to reduce the mechanical damage rate of the potato.

[0135] Table 2 Damage rate with adjustment of digging depth Adjustment of potato digging depth [R jixie ≥e]]> Properly increase digging depth [R jixie <e]]> No adjustment

[0136] Wherein e is the critical value of the total mechanical damage rate, which can be determined by the damage qualification standard of local potatoes.

[0137] In combination with Figure 12 As shown, a harvester includes the potato damage and surface clay attachment monitoring system, thus having the beneficial effects described above, which will not be repeated here.

[0138] The digging device 1 is installed at the front end of the whole machine; the conveying and separating device 2 is installed behind the digging device 1; the separating, lifting and reversing device 3 is arranged at the side of the conveying and separating device 2, and the potatoes are conveyed into the potato collecting box 5; the monitoring device 4 is installed above the separating, lifting and reversing device 3, and is used for shooting the pictures of the potatoes in the conveying process and transmitting the pictures to the control unit.

[0139] It should be understood that, although the present specification is described in terms of various embodiments, not every embodiment contains only one independent technical solution, and the description of the specification is only for the sake of clarity, and those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that those skilled in the art can understand.

[0140] The series of detailed descriptions listed above are only specific descriptions of the feasible embodiments of the present application, and are not used to limit the protection scope of the present application, and any equivalent embodiments or changes made without departing from the spirit of the present application should be included in the protection scope of the present application.

Claims

1. A monitoring system for potato damage and surface clay adhesion, characterized in that, Includes a monitoring device (4) and a control unit; The monitoring device (4) is used to take pictures of the potatoes before they enter the potato collection box (5) and send them back to the control unit; The control unit identifies the potato body boundary, damaged area boundary, and attached soil boundary based on the potato image, and calculates the potato damage rate and soil adhesion rate. The damaged area includes mechanically damaged areas. When the control unit identifies that the potato's mechanical damage rate exceeds a preset value, it feeds the data back to the operator to adjust the digging depth of the digging device (1). When the control unit identifies that the potato's soil adhesion rate exceeds a preset value, it feeds the data back to the operator to adjust the linear speed and vibration frequency of the potato harvester's conveying and separating device (2).

2. The potato damage and surface clay adhesion monitoring system according to claim 1, characterized in that, The control unit performs boundary segmentation on the potato images captured by the monitoring device (4) using the HSV color space. Based on preset color thresholds for the potato body, damaged areas, and attached soil, the control unit colors and distinguishes the potato body, damaged areas, and attached soil in the potato images captured by the monitoring device (4). After color differentiation is completed, soil enclosures, potato body enclosures, and damaged area enclosures are obtained based on color distribution and the boundaries of different colors. The damage rate and soil adhesion rate of the potato are then calculated. The potato damage rate is calculated using the coordinate filling method and / or the integration method, and the potato soil adhesion rate is calculated using the integration method.

3. The potato damage and surface clay adhesion monitoring system according to claim 1, characterized in that, It also includes a flipping device; the monitoring device (4) includes a first industrial camera (4.1) and a second industrial camera (4.2); the flipping device is used to flip the potato; the first industrial camera (4.1) takes a picture of the upper surface of the potato and transmits it to the control unit, the control unit controls the flipping device to flip the potato, the second industrial camera (4.2) takes a picture of the lower surface of the potato and transmits it to the control unit, the control unit calculates the damage rate by combining the pictures of the upper and lower surfaces of the potato.

4. The potato damage and surface clay adhesion monitoring system according to claim 3, characterized in that, The flipping device includes a motor (6), an electric cylinder (7), and a tooth-picking mechanism (8); the tooth-picking mechanism (8) includes a rotating shaft with multiple teeth on it; the motor (6) is connected to the end of the rotating shaft and is used to drive the rotating shaft to rotate; the electric cylinder (7) is connected to the motor (6) and is used to drive the motor (6) to move the tooth-picking mechanism (8) up and down.

5. The potato damage and surface clay adhesion monitoring system according to claim 2, characterized in that, The damage rate of the potatoes was calculated using both the coordinate filling block method and the integral method, and then the average of the two methods was taken as the damage rate.

6. The potato damage and surface clay adhesion monitoring system according to claim 2, characterized in that, The damaged parts of the potato also include one or more of the following: insect holes and rot. Therefore, the potato damage rate includes the sum of one or more of the following: mechanical damage, insect holes, and rot damage rates.

7. The potato damage and surface clay adhesion monitoring system according to claim 2, characterized in that, The control unit uses a coordinate system to divide the soil surrounding the potato and the potato body surrounding the potato into upper and lower parts. The boundary lines of the upper and lower parts are fitted with a function, and the area of ​​the two surrounding circles is calculated by integrating the function. The soil surrounding area minus the potato body surrounding area and then divided by the potato body surrounding area is the soil adhesion rate of a single potato. The longest soil adhesion distance of the potato is also calculated. The sum of the soil adhesion rates of multiple potatoes in the potato image captured by the monitoring device (4) is divided by the total number of potatoes in the image to obtain the soil adhesion rate of the potato. When the soil adhesion rate of the potato exceeds the preset value, the data is fed back to the operator. The soil adhesion rate and the longest soil adhesion distance of the potato are used to adjust the linear speed and vibration frequency of the potato harvester conveying and separating device (2).

8. A harvester, characterized in that, The potato damage and surface clay adhesion monitoring system includes any one of claims 1-7.

9. A control method for a potato damage and surface clay adhesion monitoring system according to any one of claims 1-7, characterized in that, Includes the following steps: The monitoring device (4) takes pictures of the potatoes before they enter the potato collection box (5) and sends them back to the control unit; The control unit identifies the potato body boundary, damaged area boundary, and attached soil boundary based on the potato image, and calculates the potato damage rate and soil adhesion rate. When the control unit detects that the mechanical damage rate of the potatoes exceeds a preset value, The data is fed back to the operator to adjust the digging depth of the excavating device (1); When the control unit detects that the soil adhesion rate of the potato exceeds the preset value, it feeds the data back to the operator and uses the soil adhesion rate of the potato and the longest soil adhesion distance of the potato to adjust the linear speed and vibration frequency of the potato harvester conveying and separating device (2).

10. The control method of the potato damage and surface clay adhesion monitoring system according to claim 9, characterized in that, The monitoring device (4) includes a first industrial camera (4.1) and a second industrial camera (4.2); the first industrial camera (4.1) takes a picture of the upper surface of the potato and transmits it to the control unit, which controls the flipping device to flip the potato; the second industrial camera (4.2) takes a picture of the lower surface of the potato and transmits it to the control unit, which calculates the damage rate by combining the pictures of the upper and lower surfaces of the potato.

Images