Intelligent broccoli sorting system

Abstract

The invention discloses an intelligent broccoli sorting system, and relates to the technical field of vegetable sorting, the intelligent broccoli sorting system comprises a sorting transportation line, a feature detection module, a sorting management terminal and a sorting device; the sorting conveying line is used for conveying to-be-sorted broccoli from a feeding port to each feature detection area in a preset conveying direction under the control of the sorting management terminal, and adjusting the conveying speed according to a driving control signal of the sorting management terminal; the feature detection module is used for acquiring image feature information of the cauliflower and detecting weight information of the cauliflower; the sorting management terminal is used for identifying and classifying the cauliflower according to the obtained feature information and classification parameters, sending a control signal to the sorting device and storing detection and sorting data, and the sorting device is used for controlling the sorting equipment to sort the cauliflower according to the control signal. And the sorting quality is higher, and sorting optimization can be carried out according to user requirements to meet specific sorting requirements.

Description

Technical Field

[0001] The present application relates to the technical field of vegetable sorting, and in particular to an intelligent sorting system for cauliflower. Background Art

[0002] Cauliflower, also known as cauliflower, cauliflower or broccoli, is a cruciferous vegetable. Cauliflower sorting can help farmers accurately classify and grade harvested cauliflower, thereby improving the market value and competitiveness of the product. The traditional sorting method uses manual sorting, which results in low sorting efficiency and is prone to errors and waste. Cauliflowers of different varieties and specifications have different sorting requirements. Although the existing cauliflower sorting system has introduced a semi-automatic auxiliary screening device, it cannot optimize sorting according to user needs to meet specific sorting requirements and lacks traceability. Summary of the invention

[0003] In view of this, the present application provides an intelligent sorting system for cauliflower, which solves the problem that the traditional sorting method uses manual classification, resulting in low sorting efficiency, and easily causing errors and waste. In addition, although the existing cauliflower sorting system introduces a semi-automatic auxiliary screening device, it cannot optimize the sorting according to user needs to meet specific sorting requirements and lacks traceability.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent cauliflower sorting system comprises: a sorting transport line, a feature detection module, a sorting management terminal and a sorting device; The sorting transport line is used to transport the cauliflower to be sorted from the loading port along the preset conveying direction to each characteristic detection area under the control of the sorting management terminal, and adjust the transport speed according to the driving control signal of the sorting management terminal; The feature detection module is arranged in the feature detection area, and the feature detection module includes an image detection unit and a plurality of weight detection units, the image detection unit is used to obtain image feature information of the cauliflower, the weight detection unit is used to detect weight information of the cauliflower, and the weight detection unit includes a weight sensor, and the weight sensor is arranged under the conveyor belt in front of the secondary sorting port; The sorting management terminal is connected to the feature detection module. The sorting management terminal is used to identify and classify cauliflower according to the acquired feature information and the classification parameters preset by the user, and to send a control signal to the sorting device. It is also used to store the detection and sorting data. The sorting device is used to control the sorting equipment to sort the cauliflower according to the control signal.

[0005] Furthermore, the sorting and transporting line includes a conveying belt, a driving motor, a driving wheel and a motor driving device. The conveying belt is connected to the driving wheel, the driving wheel is connected to the motor shaft of the driving motor through a coupling, the control end of the driving motor is electrically connected to the motor driving device, and the motor driving device controls the rotation of the driving motor according to the driving control signal sent by the sorting management terminal.

[0006] The other end of the conveyor belt is connected to the driven wheel, and an encoder is installed on the driven wheel. The encoder is used to detect the transportation speed. The driven wheel is set at the feeding end, and the cauliflower enters the feeding end in turn at a certain distance. A detection box is set at a distance from the driven wheel. In order to achieve a higher sorting accuracy, a row of cauliflowers can be set on the conveyor belt. If the camera collects an image every 1s for processing, the speed of the seed conveyor belt can be adjusted by adjusting the speed of the three-phase asynchronous motor through the inverter of the motor drive device, so as to ensure that the camera will not lose the cauliflower image after each image acquisition, and avoid missed inspection. The sorting and transportation line is mainly used for the transportation of cauliflower. The main parts are the conveyor belt, the three-phase asynchronous motor and the motor drive device. The motor drive device includes a Siemens inverter. The speed of the three-phase asynchronous motor is adjusted by the Siemens inverter, so as to achieve the purpose of changing the conveyor belt speed and realize the adjustability of the conveying speed. Baffles are set on both sides of the conveyor belt to prevent cauliflower from falling.

[0007] Furthermore, an image detection unit is arranged in the detection box, and the image detection unit includes a dimming module and an industrial camera; the dimming module includes a light sensor, an LED lighting lamp, a stepless dimming circuit and a sub-controller, the light sensor is used to send the light information detected in the detection box to the sub-controller, the sub-controller compares the currently detected light value with the preset light threshold, and sends a control signal to the stepless dimming circuit according to the comparison difference, and adjusts the LED lighting lamp to the corresponding brightness range through the stepless dimming circuit; the industrial camera is connected to the system controller via a data cable.

[0008] The light source is an important component of the machine vision recognition part. The appropriate light source will affect the quality of the collected image and thus affect the processing accuracy and efficiency of the entire system. The LED lighting and industrial camera are installed on the top of the detection box. The LED lighting is a ring light source, which is set on the lens of the industrial camera CCD to ensure that the light source is vertically irradiated. During automatic control, the camera automatically takes a picture every 1s, which can also be adjusted according to actual needs.

[0009] Furthermore, the sorting management terminal includes a user interaction module, an image recognition module, a data storage module and a system controller; the user interaction module is used to obtain user identity authentication information, and obtain the cauliflower sorting size parameters, color parameters, compactness parameters and weight parameters input by the user, and visualize the operation status information and abnormal warning information of the current intelligent sorting line; the image recognition module is connected to the user interaction module, and the image recognition module includes an image preprocessing module and a pest and disease recognition module. The image preprocessing module is used to filter, reduce noise and enhance the collected image, and transmit the obtained feature data to the pest and disease recognition module. The pest and disease recognition module is used to extract features, and classify and identify cauliflower pests and diseases by using a machine learning algorithm to extract the extracted features; the data storage module includes a sorting database, and the sorting database is used to store detection and sorting data; the system controller is electrically connected to the user interaction module, the image recognition module and the data storage module, and the system controller is used to verify the user identity according to the verification information input by the user, and send a control signal to the sorting device according to the image recognition result and the size judgment result, and control the sorting device to classify and sort the cauliflower.

[0010] Furthermore, the pest and disease identification module includes a feature extraction module and a classification identification module. The feature extraction module is used to convert the collected RGB image into an HSV color space, and use the K-means algorithm to cluster the pixels in the HSV image into multiple color approximate areas. Based on the results of K-means clustering, a saliency map is calculated. The classification identification module is used to use a convolutional neural network model to identify and classify pests and diseases based on saliency image features.

[0011] Image preprocessing requires filtering and noise reduction, and the filtering adopts an adaptive filtering algorithm. After preprocessing the image data, its target features need to be extracted and then classified and identified. The convolutional neural network model adopts the VGG model.

[0012] Furthermore, the image recognition module also includes a feature classification module, which is connected to the preprocessing module. The feature classification module is used to perform target segmentation on the preprocessed image, obtain size information and hole information of the currently detected cauliflower according to the segmentation result, and compare the size information and hole information with the size threshold parameters and the number of holes and area thresholds uploaded by the user, and classify and sort the cauliflower according to the comparison result.

[0013] Furthermore, the sorting device includes multiple groups of primary sorting ports and multiple groups of secondary sorting ports, each primary sorting port is provided with a first sorting baffle, each group of secondary sorting ports is provided with a second sorting baffle and a falling material collection bucket, and the front ends of the primary sorting ports and the secondary sorting ports are provided with opposing photoelectric switches, the sorting baffles are controlled by baffle driving mechanisms, and the opposing photoelectric switches and the baffle driving mechanisms are electrically connected to the system controller.

[0014] Furthermore, the baffle driving mechanism includes a rotating shaft, a gear, a toothed plate and a cylinder. The rotating shaft is fixedly connected to the sorting baffle, the end of the rotating shaft is fixedly connected to a gear, the gear is meshed with the toothed plate, one end of the toothed plate is fixedly connected to the piston rod of the cylinder, and the control end of the cylinder is electrically connected to the system controller.

[0015] A sorting baffle is installed at each sorting port. The sorting baffle can be controlled by the cylinder to rotate a certain angle, and then the cauliflower is picked. The cylinder is provided with a pressure regulating valve, which can adjust the force and speed of the sorting baffle opening and closing. When the sorting baffle is opened, it will block and pick the cauliflower on the conveyor belt. When it is closed, the cauliflower will be directly sent to the secondary sorting port or the falling material collection bucket. And when the sorting baffle is closed, it is flush with the baffle plate to avoid affecting other cauliflowers on the conveyor belt. When the cauliflower passes through the photoelectric switch or weight sensor in turn, the photoelectric switch or weight sensor will capture the passing signal and weight signal of the cauliflower and send it to the system controller. The system controller records and calculates the weight and position information of the cauliflower to determine which sorting port each cauliflower should be sent to. When the cauliflower is transported to the sorting port, the sorting baffle will open in advance to accept the cauliflower, and drive the sorting baffle to close the sorting port after entering the sorting port. In this way, accurate grading of product quality and weight can be achieved quickly.

[0016] Furthermore, the sorting device also includes a sorting robot arm, which is provided with a teaching pendant. The bottom end of the sorting robot arm is fixedly mounted on a rotating drive platform. The rotating drive platform adjusts the rotation angle according to the control signal sent by the teaching pendant. The rotating drive platform includes a turntable, on which a first rotating arm is arranged. The end of the first rotating arm is connected to the front end of the second rotating arm through a rotating joint. A pneumatic clamp is fixedly mounted on the end of the second rotating arm. The rotating platform and the rotating joint are equipped with a driving motor for driving the rotating platform to rotate horizontally and the rotating joint to rotate longitudinally, so that cauliflower with pests and diseases can be grasped according to different needs.

[0017] The collected images are processed to screen out unqualified cauliflowers with pests and diseases. Then the teaching pendant receives the control signal of the system controller, and then controls the servo motor to send a pulse signal to control the movement of the robotic arm. The grasping end of the robotic arm reaches the position of the unqualified cauliflower to remove it.

[0018] It can be seen from the above technical solution that the advantages of the present invention are: In this application, the system can quickly process a large amount of cauliflower through the intelligent sorting system, greatly improving the sorting efficiency. Compared with the traditional manual sorting method, the intelligent sorting system can significantly reduce the sorting time and reduce labor intensity. Through advanced sensors and computer vision technology, the intelligent sorting system can accurately identify the types and characteristics of cauliflower and achieve precise sorting. This helps to reduce errors and waste in the sorting process and improve product quality. The intelligent sorting system has strong adaptability and flexibility, and can adapt to the sorting needs of cauliflower of different varieties and specifications. At the same time, the system can also be customized and optimized according to the actual needs of the user to meet specific sorting requirements. The intelligent sorting system can record the sorting process and results of each cauliflower to achieve traceability. It helps users understand the source and quality of the product and improve the safety and reliability of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0020] Figure 1 This is a schematic diagram of the composition structure of this application.

[0021] Figure 2 This is a schematic diagram of the structure of this application.

[0022] Figure 3 This is a schematic diagram of the structure of the baffle driving mechanism of the present application.

[0023] Figure 4 This is a schematic diagram of the composition structure of the sorting management terminal of this application.

[0024] Reference numerals: Sorting management terminal-1, detection box-2, first sorting baffle-3, second sorting baffle-4, rotating shaft-5, gear-6, tooth plate-7, sorting mechanical arm-8. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0026] refer to Figures 1 to 4The present embodiment provides an intelligent sorting system for cauliflower, which reduces sorting time and labor intensity through digital means to achieve efficient production. The system specifically includes: a sorting transport line, a feature detection module, a sorting management terminal 1 and a sorting device. The sorting transport line is used to transport the cauliflower to be sorted from the loading port along the preset transmission direction to each feature detection area under the control of the sorting management terminal 1, and adjust the transportation speed according to the driving control signal of the sorting management terminal 1. The feature detection module is arranged in the feature detection area, and the feature detection module includes an image detection unit and a plurality of weight detection units. The image detection unit is used to obtain the image feature information of the cauliflower, and the weight detection unit is used to detect the weight information of the cauliflower. The weight detection unit includes a weight sensor, which is arranged in front of the secondary sorting port. The sorting management terminal 1 is connected to the feature detection module. The sorting management terminal 1 is used to identify and classify the cauliflower according to the acquired feature information and the classification parameters preset by the user, and send a control signal to the sorting device. It is also used to store the detection and sorting data. The sorting device is used to control the sorting device to sort the cauliflower according to the control signal.

[0027] Specifically, the sorting and transporting line includes a conveying belt, a driving motor, a driving wheel and a motor driving device. The conveying belt is connected to the driving wheel, and the driving wheel is connected to the motor shaft of the driving motor through a coupling. The control end of the driving motor is electrically connected to the motor driving device, and the motor driving device controls the rotation of the driving motor according to the driving control signal sent by the sorting management terminal 1. The other end of the conveying belt is connected to the driven wheel, and an encoder is installed on the driven wheel. The encoder is used to detect the transportation speed. The driven wheel is set at the feeding end, and the cauliflower enters the feeding end in turn at a certain distance. A detection box 2 is set at a distance from the driven wheel. In order to achieve a higher sorting accuracy, a row of cauliflower positions can be set on the conveyor belt. If the camera collects an image every 1s for processing, the speed of the seed conveyor belt can be adjusted by adjusting the speed of the three-phase asynchronous motor through the inverter of the motor driving device, so as to ensure that the camera will not lose the cauliflower image after each image collection, and avoid missed detection.

[0028] The sorting and transporting line is mainly used for the transportation of cauliflower. The main parts are the conveying belt, three-phase asynchronous motor and motor drive device. The motor drive device includes a Siemens inverter. The speed of the three-phase asynchronous motor is adjusted by the Siemens inverter to achieve the purpose of changing the speed of the conveying belt and realize the adjustability of the transmission speed. The conveying belt is equipped with baffles on both sides to prevent the cauliflower from falling.

[0029] like Figure 2As shown, the image detection unit is arranged in the detection box 2, and strip-shaped leather curtains are installed in front and behind the detection box 2 to avoid interference of light at different angles on image acquisition. The image detection unit includes a dimming module and an industrial camera; the dimming module includes a light sensor, an LED lighting lamp, a stepless dimming circuit and a sub-controller, the light sensor is used to send the light information detected in the detection box 2 to the sub-controller, the sub-controller compares the currently detected light value with the preset light threshold, and sends a control signal to the stepless dimming circuit according to the comparison difference, and adjusts the LED lighting lamp to the corresponding brightness range through the stepless dimming circuit, wherein the stepless dimming circuit is composed of an LED driver chip and a peripheral circuit, the LED driver chip adopts the model LTC3454, the enable terminal Enx can be connected to a high level, the sub-controller outputs a PWM signal, and dims through the PWM signal to achieve the purpose of accurate stepless dimming. The industrial camera is connected to the system controller through a data line.

[0030] The light source is an important component of the machine vision recognition part. A suitable light source will affect the quality of the collected image and thus affect the processing accuracy and efficiency of the entire system. The LED lighting and industrial camera are installed on the top of the detection box 2. The LED lighting is a ring light source. The ring light source is set to the lens of the industrial camera CCD to ensure that the light source is vertically irradiated. The lens of the industrial camera is facing the cauliflower on the conveyor belt. During automatic control, the camera automatically takes a picture every 1s, which can also be adjusted according to actual needs.

[0031] The sorting management terminal 1 includes a user interaction module, an image recognition module, a data storage module and a system controller. The user interaction module is used to obtain user identity authentication information, and obtain the cauliflower sorting size parameters, color parameters, compactness parameters and weight parameters input by the user, and visually display the operation status information and abnormal warning information of the current intelligent sorting line. The user interaction module includes a liquid crystal display, a server, an input keyboard and a fingerprint recording device. The liquid crystal display is connected to the server, and the operation status information and abnormal warning information of the intelligent sorting line can be visually displayed according to the calculation and processing information of the server. The server and the system controller are connected through a connecting line, and relevant data logic processing can be realized. The user can input the corresponding parameter information through the input keyboard. The fingerprint recording device is used to record the user's fingerprint identity information, which is convenient for subsequent identity information verification.

[0032] The image recognition module is connected to the user interaction module. The image recognition module includes an image preprocessing module and a pest and disease recognition module. The image preprocessing module is used to filter, reduce noise and enhance the collected image, and transmit the obtained feature data to the pest and disease recognition module. The pest and disease recognition module is used to extract features and classify and identify cauliflower pests and diseases using a machine learning algorithm. The data storage module includes a sorting database, which is used to store detection and sorting data. The system controller is electrically connected to the user interaction module, the image recognition module and the data storage module. The system controller is used to verify the user's identity according to the verification information input by the user, and send a control signal to the sorting device according to the image recognition result and the size judgment result, and control the sorting device to classify and sort the cauliflower. The pest and disease information sorted can also be used to count the pest rate of cauliflower, which is convenient for subsequent planting optimization. The pest and disease identification module includes a feature extraction module and a classification identification module. The feature extraction module is used to convert the collected RGB image into the HSV color space, and the pixels in the HSV image are clustered into multiple color approximate regions using the K-means algorithm. Based on the results of the K-means clustering, the saliency map is calculated. The classification identification module is used to identify and classify pests and diseases based on the saliency image features using the convolutional neural network model. Specifically, based on the results of the K-means clustering, the color contrast between each pixel and the surrounding pixels is calculated according to the distance in the HSV color space, the calculated contrast value is normalized to the range of 0-1 to obtain the saliency value, the saliency value is used as the new pixel value to obtain the saliency map, and the saliency image features are input into the convolutional neural network model for identification.

[0033] Image preprocessing requires filtering and noise reduction, and the filtering adopts an adaptive filtering algorithm. After preprocessing the image data, its target features need to be extracted and then classified and identified. The convolutional neural network model adopts the VGG model.

[0034] In this embodiment, the image recognition module also includes a feature classification module, which is connected to the preprocessing module. The feature classification module is used to perform target segmentation on the preprocessed image, obtain the size information and hole information of the currently detected cauliflower according to the segmentation result, and compare the size information and hole information with the size threshold parameters and the number and area threshold of the holes uploaded by the user, and classify and sort the cauliflower according to the comparison result. The size information and hole information refer to the outer contour circumference of the cauliflower and the number of closed holes and the pixel area of ​​the holes, respectively. For example, if the outer contour circumference is greater than the preset threshold N and the number of closed holes and the pixel area of ​​the holes are less than the preset threshold M, the cauliflower is judged to be qualified in terms of compactness (greater than the preset threshold).

[0035] When performing target segmentation on the preprocessed image, the threshold processing technology is used to convert the image into a binary image, and then the morphological operation and region growing algorithm are used to connect the hole target area of ​​the cauliflower as the initial area. The GrabCut algorithm is used for iterative segmentation, and the size and number of the segmented image area are used to judge the compactness of the cauliflower.

[0036] like Figure 2 As shown, the sorting device includes multiple groups of primary sorting ports and multiple groups of secondary sorting ports, each of which is provided with a first sorting baffle 3, each of which is provided with a second sorting baffle 4 and a falling material collection bucket, and the front end of the primary sorting port and the front end of the secondary sorting port are both provided with a beam-type photoelectric switch, and the sorting baffle is controlled by a baffle driving mechanism, and the beam-type photoelectric switch and the baffle driving mechanism are both electrically connected to the system controller. Among them, the baffle driving mechanism includes a rotating shaft 5, a gear 6, a tooth plate 7 and a cylinder, the rotating shaft 5 is fixedly connected to the sorting baffle, the end of the rotating shaft 5 is fixedly connected to a gear 6, the gear 6 is meshed with the tooth plate 7, one end of the tooth plate 7 is fixedly connected to the piston rod of the cylinder, and the control end of the cylinder is electrically connected to the system controller. The cylinder drives the piston rod to move, driving the tooth plate 7 to move forward and backward, thereby driving the gear 6 meshed with the tooth plate 7 to rotate, and the rotation of the gear 6 drives the rotating shaft 5 to rotate, thereby causing the sorting baffle to rotate a certain angle.

[0037] A sorting baffle is installed at each sorting port. The sorting baffle can be controlled by the cylinder to rotate a certain angle, and then the cauliflower is picked. The cylinder is provided with a pressure regulating valve, which can adjust the force and speed of the sorting baffle opening and closing. When the sorting baffle is opened, it will block and pick the cauliflower on the conveyor belt. When it is closed, the cauliflower will be directly sent to the secondary sorting port or the falling material collection bucket. And when the sorting baffle is closed, it is flush with the baffle plate to avoid affecting other cauliflowers on the conveyor belt. When the cauliflower passes through the photoelectric switch or weight sensor in turn, the photoelectric switch or weight sensor will capture the passing signal and weight signal of the cauliflower and send it to the system controller. The system controller records and calculates the weight and position information of the cauliflower to determine which sorting port each cauliflower should be sent to. When the cauliflower is transported to the sorting port, the sorting baffle will open in advance to accept the cauliflower, and drive the sorting baffle to close the sorting port after entering the sorting port. In this way, accurate grading of product quality and weight can be achieved quickly.

[0038] The sorting device also includes a sorting mechanical arm 8, on which a teaching pendant is provided, and the bottom end of the sorting mechanical arm 8 is fixedly mounted on a rotating drive platform, and the rotating drive platform adjusts the rotation angle according to the control signal sent by the teaching pendant, and the rotating drive platform includes a turntable, on which a first rotating arm is provided, and the end of the first rotating arm is connected to the front end of the second rotating arm through a rotating joint, and a pneumatic clamp is fixedly installed at the end of the second rotating arm, and the turntable and the rotating joint are built with a driving motor for driving the turntable to rotate horizontally and the rotating joint to rotate longitudinally, so that cauliflower with pests and diseases can be grasped according to different needs. The collected image is processed to screen out unqualified cauliflower with pests and diseases, and then the teaching pendant receives the control signal of the system controller, and then controls the servo motor to send a pulse signal, controls the movement of the mechanical arm, and the grasping end of the mechanical arm reaches the position of the unqualified cauliflower to realize the operation of removing it.

[0039] The sorting robot arm 8 is arranged upstream of the sorting port, and each secondary sorting port is pre-set with a weight range for receiving cauliflowers. The cauliflowers entering the range will be sorted into the material collection bucket by the corresponding sorting baffle. The number of sorting ports determines the number of cauliflower grades. In this embodiment, three secondary sorting ports are arranged. When the cauliflowers are sorted, the disease and insect pest information of the cauliflowers is first obtained through the image recognition module, and the disease and insect pest cauliflowers are removed by the sorting robot arm 8. For the remaining cauliflowers, the primary sorting port performs initial sorting according to the compactness parameter and color parameter of the cauliflowers recognized by the image recognition module. In this embodiment, there are two primary sorting ports. When the compactness and color are both greater than the preset threshold, they are sorted into the primary sorting port A, when the compactness is greater than the preset threshold and the color is less than the preset threshold, they are sorted into the primary sorting port B, when the compactness is less than the preset threshold and the color is greater than the preset threshold or when the compactness and color are both less than the preset threshold, they are sorted into the secondary sorting port arranged at the end for weight screening.

[0040] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent sorting system for cauliflower, characterized in that: include: Sorting transport line, feature detection module, sorting management terminal (1) and sorting device; The sorting transport line is used to transport the cauliflower to be sorted from a loading port along a preset transport direction to each characteristic detection area under the control of the sorting management terminal (1), and to adjust the transport speed according to the drive control signal of the sorting management terminal (1); The feature detection module is arranged in the feature detection area, and the feature detection module comprises an image detection unit and a plurality of weight detection units, the image detection unit is used to obtain image feature information of the cauliflower, and the weight detection unit is used to detect weight information of the cauliflower; The sorting management terminal (1) is connected to the feature detection module, and is used to identify and classify cauliflower according to the acquired feature information and classification parameters preset by the user, and to send a control signal to the sorting device, and is also used to store the detection and sorting data, and the sorting device is used to control the sorting equipment to sort the cauliflower according to the control signal.

2. The intelligent cauliflower sorting system according to claim 1, characterized in that: The sorting transport line comprises a conveying belt, a driving motor, a driving wheel and a motor driving device, wherein the conveying belt is connected to the driving wheel, the driving wheel is connected to the motor shaft of the driving motor via a coupling, the control end of the driving motor is electrically connected to the motor driving device, and the motor driving device controls the rotation of the driving motor according to a driving control signal sent by the sorting management terminal (1).

3. The intelligent cauliflower sorting system according to claim 1, characterized in that: The image detection unit is arranged in the detection box (2), and the image detection unit comprises a dimming module and an industrial camera; the dimming module comprises a light sensor, an LED lighting lamp, a stepless dimming circuit and a sub-controller, the light sensor is used to send the light information detected in the detection box (2) to the sub-controller, the sub-controller compares the currently detected light value with a preset light threshold, and sends a control signal to the stepless dimming circuit according to the comparison difference, and the LED lighting lamp is adjusted to a corresponding brightness range through the stepless dimming circuit; the industrial camera is connected to the system controller via a data line.

4. The intelligent cauliflower sorting system according to claim 3, characterized in that: The sorting management terminal (1) comprises a user interaction module, an image recognition module, a data storage module and a system controller; the user interaction module is used to obtain user identity authentication information, and obtain cauliflower sorting size parameters, color parameters, compactness parameters and weight parameters input by the user, and visually display the operation status information and abnormal warning information of the current intelligent sorting line; the image recognition module is connected to the user interaction module, and the image recognition module comprises an image preprocessing module and a pest and disease recognition module, and the image preprocessing module is used to filter, reduce noise and enhance the collected image, and transmit the obtained feature data to the system controller; The data is input to the pest and disease identification module, which is used for feature extraction and classifying the extracted features to identify the pests and diseases of cauliflower using a machine learning algorithm; the data storage module includes a sorting database, which is used to store the detection and sorting data; the system controller is electrically connected to the user interaction module, the image recognition module and the data storage module, and the system controller is used to verify the user identity according to the verification information input by the user, and send a control signal to the sorting device according to the image recognition result and the size judgment result, so as to control the sorting device to classify and sort the cauliflower.

5. The intelligent cauliflower sorting system according to claim 4, characterized in that: The pest and disease identification module includes a feature extraction module and a classification identification module. The feature extraction module is used to convert the collected RGB image into the HSV color space, cluster the pixels in the HSV image into multiple color approximate areas using the K-means algorithm, and calculate the significance map based on the result of the K-means clustering. The classification identification module is used to use a convolutional neural network model to identify and classify pests and diseases based on significant image features.

6. The intelligent cauliflower sorting system according to claim 4, characterized in that: The image recognition module also includes a feature classification module, which is connected to the preprocessing module. The feature classification module is used to perform target segmentation on the preprocessed image, obtain size information and hole information of the currently detected cauliflower according to the segmentation result, and compare the size information and hole information with the size threshold parameters and the number of holes and area thresholds uploaded by the user, and classify and sort the cauliflower according to the comparison result.

7. The intelligent cauliflower sorting system according to claim 4, characterized in that: The sorting device comprises a plurality of groups of primary sorting ports and a plurality of groups of secondary sorting ports, each of the primary sorting ports is provided with a first sorting baffle (3), each of the secondary sorting ports is provided with a second sorting baffle (4) and a falling material collection bucket, the front ends of the primary sorting ports and the secondary sorting ports are both provided with a beam-type photoelectric switch, the sorting baffle is controlled by a baffle driving mechanism, and the beam-type photoelectric switch and the baffle driving mechanism are both electrically connected to the system controller.

8. The intelligent cauliflower sorting system according to claim 7, characterized in that: The baffle driving mechanism comprises a rotating shaft (5), a gear (6), a toothed plate (7) and a cylinder, wherein the rotating shaft (5) is fixedly connected to the sorting baffle, the end of the rotating shaft (5) is fixedly connected to the gear (6), the gear (6) is meshed with the toothed plate (7), one end of the toothed plate (7) is fixedly connected to the piston rod of the cylinder, and the control end of the cylinder is electrically connected to the system controller.

9. The intelligent cauliflower sorting system according to claim 7, characterized in that: The sorting device further comprises a sorting mechanical arm (8), the sorting mechanical arm (8) being provided with a teaching pendant, the bottom end of the sorting mechanical arm (8) being fixedly mounted on a rotating drive platform, the rotating drive platform adjusting the rotation angle according to a control signal sent by the teaching pendant, the rotating drive platform comprising a turntable, a first rotating arm being arranged on the turntable, the end of the first rotating arm being connected to the front end of a second rotating arm via a rotating joint, a pneumatic gripper being fixedly mounted on the end of the second rotating arm, the turntable and the rotating joint being provided with a built-in driving motor for driving the turntable to rotate horizontally and the rotating joint to rotate longitudinally, so that cauliflower with pests and diseases can be grasped according to different requirements.

Images