Machine Vision-Based Wolfberry Screening and Grading Method and System

Abstract

The present invention discloses a wolfberry screening and grading method and system based on machine vision, specifically related to the field of wolfberry screening; by measuring the conveyor belt speed in real time, combining with the distribution density of wolfberries, determining the number of images to be processed and the theoretical processing speed of the image processing system, and comparing with the actual processing speed, identifying speed synchronization anomalies; further analyzing the fluctuations in classification accuracy and data processing delays, evaluating the system performance stability, and dividing it into different categories; dynamically adjusting the conveyor belt speed according to the evaluation results to ensure the efficiency and stability of the wolfberry screening and grading process, improving the overall efficiency and accuracy of the system, reducing the defective rate and production cost, and enhancing the consistency and quality of the product.

Description

Technical Field

[0001] The present invention relates to the field of wolfberry screening, and particularly to a wolfberry screening and grading method and system based on machine vision. Background Art

[0002] Wolfberry screening and grading based on machine vision refers to the process of screening and classifying wolfberries using machine vision technology. Machine vision technology captures images of wolfberries through cameras or sensors and uses image processing algorithms to analyze these images, thereby identifying features such as the size, color, and shape of wolfberries. Based on these features, the system can automatically classify wolfberries into different grades or categories for subsequent packaging and sales. The application of this technology can significantly improve the efficiency and accuracy of wolfberry screening and grading, reduce errors and labor costs in manual operations. The machine vision system can process a large number of wolfberries in a short time and perform precise classification according to preset standards, thus ensuring the consistency of product quality. In addition, this automated grading method also helps to improve the overall automation level of the production line and achieve a more efficient production process.

[0003] Deficiencies in the prior art:

[0004] In the prior art, when a high-resolution camera is used to take real-time pictures of wolfberries on a conveyor belt, due to the need for powerful computing capabilities and fast data transmission for real-time shooting and processing of a large amount of image data. However, if the data processing speed cannot keep up with the speed of the conveyor belt, it may lead to lag in image processing and classification, affecting the overall grading efficiency. At the same time, the classification lag makes real-time monitoring and quality control more difficult. It is difficult for production managers to discover and correct errors in the grading process in a timely manner, resulting in an increase in the difficulty of product quality control. Summary of the Invention

[0005] The purpose of the present invention is to provide a wolfberry screening and grading method and system based on machine vision to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A wolfberry screening and grading method based on machine vision, including the following steps:

[0007] S1: Measure the real-time speed of the conveyor belt under different operating conditions, determine the number of images to be processed within a fixed time period according to the real-time speed of the conveyor belt and the distribution density of wolfberries, and determine the theoretical processing speed of the image processing system according to the number of images;

[0008] S2: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed, and classify it into a normal speed synchronization situation and an abnormal speed synchronization situation according to the analysis result;

[0009] S3: For the speed synchronization anomaly, analyze the fluctuation range of the accuracy of wolfberry classification by the image processing system and the latency of data processing by the image processing system, and evaluate the performance stability of the image processing system when classifying wolfberries.

[0010] S4: According to the evaluation results, divide the performance stability of the image processing system when classifying wolfberries under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance.

[0011] S5: When the performance of the image processing system is of possible stability, further analyze the performance stability of the image processing system when classifying wolfberries within a subsequent fixed time period, and dynamically adjust the conveyor belt speed according to the analysis results to improve the overall efficiency of wolfberry screening and grading.

[0012] Preferably, in S2, compare and analyze the theoretical processing speed and the actual processing speed of the image processing system, and divide them into a speed synchronization normal situation and a speed synchronization anomaly situation according to the analysis results.

[0013] Select a fixed time period as the reference time period. According to the conveyor belt speed and the distribution density of wolfberries, calculate the total number of wolfberries passing on the conveyor belt within the fixed time period, determine the image acquisition frequency, calculate the number of images to be processed, and the theoretical processing speed of the image processing system = the number of images to be processed per second.

[0014] Within the fixed time period, record the time required for the image processing system to complete classification from image acquisition, use timestamps to record the start and end times of processing each frame of the image, and calculate the number of images actually processed per unit time according to the recorded actual processing time. The actual processing speed of the image processing system = the number of images actually processed within the fixed time period / the fixed time period.

[0015] Compare the theoretical processing speed and the actual processing speed of the image processing system, calculate their difference, and express the deviation of the actual processing speed from the theoretical processing speed as a percentage. The specific calculation formula is: speed deviation rate = (actual processing speed - theoretical processing speed) / theoretical processing speed.

[0016] According to the speed deviation rate, classify the speed deviation rate within ±10% as a speed synchronization normal situation, and if it exceeds ±10%, classify it as a speed synchronization anomaly situation.

[0017] Preferably, in S3, for the speed synchronization anomaly situation, generate a classification accuracy fluctuation index according to the fluctuation range of the accuracy of wolfberry classification by the image processing system. The method for obtaining the classification accuracy fluctuation index is as follows:

[0018] During a fixed time period, record the classification accuracy data A of each frame of image and establish a corresponding data set A = {a1, a2,..., aj,..., an}; where j = 1, 2,..., n, and n is a positive integer greater than 0, and determine the size W of the sliding window; calculate the local fluctuation value of the classification accuracy data within each sliding window, where KM is the local fluctuation value and AQ is the mean of the accuracy data within the sliding window; perform smoothing processing on the calculated fluctuation data to obtain the smoothed classification accuracy fluctuation index, and the specific calculation expression is: LG = λ * KM + (1 - λ)LG t-1 ; where LG is the classification accuracy fluctuation index and λ is the smoothing coefficient.

[0019] Preferably, in S3, generate an image data processing delay index according to the delay situation of data processing by the image processing system, and the acquisition method of the image data processing delay index is:

[0020] Obtain the processing delay time of each frame of image in real time to form a time series data set D = {d1, d2,..., dm}; use the ACF and PACF diagrams to determine the parameters p, d, q of the ARIMA model, and use the delay time series data to fit the ARIMA model and estimate the model parameters. The calculation expression of the ARIMA model is: where Y t is the observed value at time t, k is the constant term, φ i is the coefficient of the autoregressive part, θ j is the coefficient of the moving average part, s t is the white noise error term; use historical data to fit the ARMA model to obtain the parameters φ i and θ j , use the fitted ARMA model to predict future values to obtain the predicted value DM, calculate the error between the actual delay and the predicted delay, and calculate the image data processing delay index according to the statistical characteristics of the error. The specific calculation expression is: where HG is the image data processing delay index.

[0021] Preferably, perform normalization processing on the classification accuracy fluctuation index and the image data processing delay index, and calculate the performance stability coefficient of the image processing system for wolfberry classification through the normalized classification accuracy fluctuation index and the image data processing delay index.

[0022] Preferably, in S4, divide the performance stability of the image processing system for wolfberry classification under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, specifically:

[0023] Compare the performance stability coefficient of the image processing system obtained during wolfberry classification with the gradient thresholds. The gradient thresholds include a first threshold and a second threshold, and the first threshold is less than the second threshold. Compare the performance stability coefficient of the image processing system during wolfberry classification with the first threshold and the second threshold respectively;

[0024] If the performance stability coefficient of the image processing system during wolfberry classification is greater than the second threshold, the performance stability of the image processing system during wolfberry classification is high. Classify it into the performance stability category and maintain the current hardware configuration and algorithm;

[0025] If the performance stability coefficient of the image processing system during wolfberry classification is greater than or equal to the first threshold and less than or equal to the second threshold, classify it into the performance possible stability category and adjust the parameters of the image processing algorithm;

[0026] If the performance stability coefficient of the image processing system during wolfberry classification is less than the first threshold, classify it into the performance instability category and improve the image processing and classification algorithms.

[0027] Preferably, in S5, further analyze the performance stability of the image processing system during wolfberry classification in subsequent fixed time periods, and dynamically adjust the conveyor belt speed according to the analysis results. Specifically:

[0028] When the performance of the image processing system is of possible stability, that is, the performance stability coefficient generated within a fixed time period is greater than or equal to the first threshold and less than or equal to the second threshold, establish a corresponding data set for the performance stability coefficients greater than or equal to the first threshold and less than or equal to the second threshold generated in the subsequent fixed time period, and calculate the mean value within the data set. Compare and analyze the performance stability coefficients within the data set with the mean value of the performance stability coefficients, and dynamically adjust the conveyor belt speed according to the analysis results.

[0029] Preferably, if the performance stability coefficient within the data set is greater than or equal to the mean value of the performance stability coefficients and less than or equal to the second threshold, reduce the real-time speed of the conveyor belt to improve system stability. The specific adjustment formula is: In the formula, V new is the adjusted conveyor belt speed, V at is the current speed of the conveyor, β1 is the adjustment coefficient, representing the proportion of speed increase, WP is the performance stability coefficient, WP v is the mean value of the performance stability coefficients, WP max is the second threshold;

[0030] If the performance stability coefficient within the data set is greater than or equal to the first threshold and less than or equal to the mean value of the performance stability coefficients, increase the real-time speed of the conveyor belt to improve processing efficiency. The specific adjustment formula is: Wherein, V new is the adjusted conveyor belt speed, V at is the current conveyor belt speed, β2 is the adjustment coefficient, representing the proportion of speed reduction, WP is the performance stability coefficient, WP v is the mean value of the performance stability coefficient, WP min is the first threshold.

[0031] The present invention also provides a wolfberry screening and grading system based on machine vision, including a conveyor belt speed acquisition module, a speed comparison and analysis module, a performance stability evaluation module, a performance classification module, and a dynamic adjustment module;

[0032] Conveyor belt speed acquisition module: Measure the real-time speed of the conveyor belt under different operating conditions, determine the number of images to be processed within a fixed time period according to the real-time speed of the conveyor belt and the distribution density of wolfberries, and determine the theoretical processing speed of the image processing system according to the number of images;

[0033] Speed comparison and analysis module: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed, and classify it into a speed synchronization normal situation and a speed synchronization abnormal situation according to the analysis result;

[0034] Performance stability evaluation module: For the speed synchronization abnormal situation, analyze according to the fluctuation range of the accuracy of wolfberry classification by the image processing system and the latency of data processing by the image processing system, and evaluate the performance stability of the image processing system when classifying wolfberries;

[0035] Performance classification module: According to the evaluation result, divide the performance stability of the image processing system when classifying wolfberries under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance;

[0036] Dynamic adjustment module: When the performance of the image processing system is possibly stable, further analyze the performance stability of the image processing system when classifying wolfberries within the subsequent fixed time period, and dynamically adjust the conveyor belt speed according to the analysis result to improve the overall efficiency of wolfberry screening and grading.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention:

[0038] 1. The present invention measures the conveyor belt speed and the wolfberry distribution density in real time, combines the theory and actual processing speed of the image processing system, identifies speed synchronization anomalies, analyzes the fluctuations in classification accuracy and data processing delays, and evaluates the system performance stability. According to the performance stability coefficient, the system is divided into three categories: stable performance, possibly stable, and unstable, and corresponding measures are taken for optimization, including parameter adjustment, algorithm improvement, and hardware upgrade. In addition, by dynamically adjusting the conveyor belt speed, the efficient operation of the system under the condition of possible performance stability is ensured, further improving the overall efficiency and stability of wolfberry screening and grading.

[0039] 2. The present invention not only improves the processing speed and classification accuracy of the system, ensures the efficiency and stability of the wolfberry screening and grading process, but also effectively reduces the defective rate and production cost, and improves the consistency of product quality and market competitiveness. Through the normalized classification accuracy fluctuation index and image data processing delay index, the system performance stability evaluation is optimized, the intelligent and dynamic adjustment of the conveyor belt speed is realized, and the flexibility and adaptability of the entire system are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0041] Figure 1 It is a flowchart of the method of the present invention.

[0042] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention fall within the protection scope of the present invention.

[0044] Example 1. Please refer to Figure 1 As shown, the wolfberry screening and grading method based on machine vision in this embodiment includes the following steps:

[0045] S1: Measure the real-time speed of the conveyor belt under different operating conditions. Based on the real-time speed of the conveyor belt and the distribution density of goji berries, determine the number of images to be processed within a fixed time period. Based on the number of images, determine the theoretical processing speed of the image processing system.

[0046] S2: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed. Based on the analysis results, classify it into normal speed synchronization and abnormal speed synchronization.

[0047] S3: For abnormal speed synchronization, analyze the fluctuation range of the accuracy of goji berry classification by the image processing system and the data processing delay of the image processing system, and evaluate the performance stability of the image processing system when classifying goji berries.

[0048] S4: Based on the evaluation results, classify the performance stability of the image processing system when classifying goji berries under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance.

[0049] S5: When the performance of the image processing system is of possible stability, further analyze the performance stability of the image processing system when classifying goji berries in subsequent fixed time periods, and dynamically adjust the conveyor belt speed according to the analysis results to improve the overall efficiency of goji berry screening and grading.

[0050] Among them, in S1, measure the real-time speed of the conveyor belt under different operating conditions. Based on the real-time speed of the conveyor belt and the distribution density of goji berries, determine the number of images to be processed within a fixed time period. Based on the number of images, determine the theoretical processing speed of the image processing system. Specifically:

[0051] Install a speed sensor (such as an optoelectronic sensor or a rotary encoder) on the conveyor belt to measure the speed of the conveyor belt. Under different operating conditions, including no-load, full-load, and different load conditions, continuously record the speed data of the conveyor belt. Ensure that sufficient speed sample data is collected at different time periods and working states. Use a data acquisition system to record and store the data of the conveyor belt speed sensor for subsequent analysis.

[0052] Select a fixed time period (such as 1 second, 5 seconds, or 10 seconds) as the reference time period for calculating the number of images. Through experiments or statistical methods, determine the average number of goji berries per unit length of the conveyor belt. For example, how many goji berries are there on average per meter of the conveyor belt.

[0053] Calculate the total number of goji berries passing through on the conveyor belt within a fixed time period based on the real-time speed of the conveyor belt and the distribution density of goji berries. The number of goji berries per unit time = conveyor belt speed (m / s) × fixed time period (s) × goji berry distribution density (berries / m);

[0054] Determine the number of images to be collected per second to ensure that all goji berries on the conveyor belt can be covered. For example, if 10 frames of images are collected per meter of the conveyor belt and the conveyor belt speed is 2 m / s, then 20 frames of images need to be collected per second.

[0055] Calculate the number of images to be processed based on the number of goji berries on the conveyor belt within a fixed time period and the image acquisition frequency. The number of images to be processed within a fixed time period = the number of goji berries per unit time × image acquisition frequency;

[0056] Calculate the theoretical processing speed of the image processing system, that is, the number of images to be processed per unit time. The theoretical processing speed of the image processing system (frames / s) = the number of images to be processed per second.

[0057] S2: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed, and classify it into a normal speed synchronization situation and an abnormal speed synchronization situation according to the analysis results.

[0058] Select a fixed time period (such as 1 second, 5 seconds, or 10 seconds) as the reference time period. Calculate the total number of goji berries passing through on the conveyor belt within the fixed time period according to the conveyor belt speed and the distribution density of goji berries, determine the image acquisition frequency, calculate the number of images to be processed, and the theoretical processing speed of the image processing system = the number of images to be processed per second;

[0059] Within the fixed time period, record the time required for the image processing system to complete classification from image acquisition. Use timestamps to record the start and end times of processing each frame of image. According to the recorded actual processing time, calculate the number of images actually processed per unit time, and the actual processing speed of the image processing system = the number of images actually processed within the fixed time period / the fixed time period;

[0060] Compare the theoretical processing speed of the image processing system with the actual processing speed, calculate their difference, and express the deviation of the actual processing speed relative to the theoretical processing speed as a percentage. The specific calculation formula is: speed deviation rate = (actual processing speed - theoretical processing speed) / theoretical processing speed;

[0061] According to the speed deviation rate, classify the speed deviation rate within ±10% as a normal speed synchronization situation, and if it exceeds ±10%, classify it as an abnormal speed synchronization situation.

[0062] S3: For the speed synchronization anomaly, analyze the fluctuation range of the accuracy of wolfberry classification by the image processing system and the latency of data processing by the image processing system, and evaluate the performance stability of the image processing system when classifying wolfberries.

[0063] For the speed synchronization anomaly, generate a classification accuracy fluctuation index based on the fluctuation range of the accuracy of wolfberry classification by the image processing system. The method for obtaining the classification accuracy fluctuation index is as follows:

[0064] Within a fixed time period, record the classification accuracy data A of each frame of image and establish a corresponding data set A = {a1, a2,..., aj,..., an}; where j = 1, 2,..., n, and n is a positive integer greater than 0. Determine the size W of the sliding window (for example, 5 frames or 10 frames can be selected); calculate the local fluctuation value for the classification accuracy data within each sliding window. In the formula, KM is the local fluctuation value, and AQ is the average value of the accuracy data within the sliding window; perform smoothing processing on the calculated fluctuation data to obtain the smoothed classification accuracy fluctuation index. The specific calculation expression is: LG = λ * KM + (1 - λ)LG t-1 ; In the formula, LG is the classification accuracy fluctuation index, and λ is the smoothing coefficient, with a value range of (0 < α < 1).

[0065] The larger the classification accuracy fluctuation index, the lower the performance stability of the image processing system when classifying wolfberries. The fluctuation index reflects the degree of dispersion of the classification accuracy. A larger index means that the accuracy of the classification results varies greatly at different time periods. This change may be caused by inconsistent system processing speeds, conveyor belt speed fluctuations, image quality fluctuations, or other factors.

[0066] Low performance stability will lead to the unreliability of the classification results and may fail to identify and classify the quality and grade of wolfberries. For the production process, this instability will affect the consistency and quality of the final product, increasing the defective rate and production costs. In addition, a system with unstable performance requires frequent adjustment and maintenance, further increasing the operational complexity and costs.

[0067] Therefore, the size of the classification accuracy fluctuation index is an important indicator for measuring the system's performance stability. By continuously monitoring and optimizing the fluctuation index, the stability and accuracy of the system can be improved, ensuring the efficiency and reliability of the wolfberry screening and grading process, thereby enhancing production efficiency and product quality.

[0068] Generate an image data processing latency index based on the latency of data processing by the image processing system. The method for obtaining the image data processing latency index is as follows:

[0069] Obtain the processing delay time of each frame of image in real time to form a time series dataset D = {d1, d2,..., dm}; perform preprocessing operations such as denoising and standardization on the delay data to make the data suitable for time series analysis.

[0070] Use the ADF test to check whether the delay time series is stationary. If it is not stationary, perform differencing processing. Use the ACF and PACF plots to determine the parameters p, d, q of the ARIMA model. Use the delay time series data to fit the ARIMA model and estimate the model parameters. The calculation expression of the ARIMA model is: where, Y t is the observed value at time t, k is the constant term, φ i is the coefficient of the autoregressive part, θ j is the coefficient of the moving average part, s t is the white noise error term; Use historical data to fit the ARMA model to obtain the parameters φ i and θ j , use the fitted ARMA model to predict future values to obtain the predicted value DM, calculate the error between the actual delay and the predicted delay, and calculate the image data processing delay index according to the statistical characteristics of the error. The specific calculation expression is: In the formula, HG is the image data processing delay index.

[0071] The larger the image data processing delay index, the lower the performance stability of the image processing system when classifying wolfberries. A larger delay index indicates that the delay time of the image processing system fluctuates greatly in different time periods, which means that the processing speed of the system is inconsistent and may be fast or slow. This instability will lead to a decrease in the timeliness and accuracy of image processing and classification results, affecting the overall grading efficiency.

[0072] A system with low performance stability is prone to classification errors or omissions during actual operation. Especially when processing high-load or complex images, this fluctuation may be more obvious. For wolfberry screening and grading, unstable processing performance will affect the consistency and quality of products, increase the defective rate, and thus affect the overall efficiency of the production line and the market competitiveness of products.

[0073] To improve the performance stability of the system, it is necessary to continuously monitor and optimize the delay index of the image processing system. By analyzing and adjusting system parameters, improving hardware and algorithms, and reducing the fluctuation of processing delay, the stability and accuracy of the classification system can be improved, ensuring the efficiency and reliability of the wolfberry screening and grading process.

[0074] Normalize the classification accuracy fluctuation index and the image data processing delay index, and calculate the performance stability coefficient of the image processing system for wolfberry classification based on the normalized classification accuracy fluctuation index and image data processing delay index.

[0075] For example, the present invention can calculate the performance stability coefficient of the image processing system for wolfberry classification using the following formula. The calculation expression is: In the formula, WP is the performance stability coefficient, LG is the classification accuracy fluctuation index, HG is the image data processing delay index, a1 and a2 are the proportionality coefficients of the classification accuracy fluctuation index and the image data processing delay index respectively, and a2 > a1 > 0.

[0076] S4: According to the evaluation results, divide the performance stability of the image processing system for wolfberry classification under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance.

[0077] Compare the performance stability coefficient of the image processing system for wolfberry classification obtained with the gradient thresholds. In this application, the gradient thresholds include a first threshold and a second threshold, and the first threshold is less than the second threshold. Compare the performance stability coefficient of the image processing system for wolfberry classification with the first threshold and the second threshold respectively;

[0078] If the performance stability coefficient of the image processing system for wolfberry classification is greater than the second threshold, it indicates that the performance stability of the image processing system for wolfberry classification is high, and it is classified into the performance stability category; it shows that the system already has relatively high performance stability, and maintain the current hardware configuration and algorithm.

[0079] If the performance stability coefficient of the image processing system for wolfberry classification is greater than or equal to the first threshold and less than or equal to the second threshold, it is classified into the possible performance stability category; adjust the parameters of the image processing algorithm to improve the processing speed and accuracy.

[0080] If the performance stability coefficient of the image processing system for wolfberry classification is less than the first threshold, it is classified into the performance instability category, and improve the image processing and classification algorithms.

[0081] S5: When the performance of the image processing system is of possible stability, further analyze the performance stability of the image processing system for wolfberry classification within subsequent fixed time periods, and dynamically adjust the conveyor belt speed according to the analysis results to improve the overall efficiency of wolfberry screening and grading.

[0082] When the performance of the image processing system is potentially stable, that is, the performance stability coefficient generated within a fixed time period is greater than or equal to the first threshold and less than or equal to the second threshold, a corresponding data set is established for the performance stability coefficients greater than or equal to the first threshold and less than or equal to the second threshold generated in subsequent fixed time periods, and the mean value within the data set is calculated. The performance stability coefficients within the data set are compared and analyzed with the mean value of the performance stability coefficients, and the conveyor belt speed is dynamically adjusted according to the analysis results.

[0083] If the performance stability coefficient within the data set is greater than or equal to the mean value of the performance stability coefficients and less than or equal to the second threshold, the real-time speed of the conveyor belt is reduced to improve the system stability. The specific adjustment formula is: In the formula, V new is the adjusted conveyor belt speed, V at is the current conveyor belt speed, β1 is the adjustment coefficient representing the proportion of speed increase, WP is the performance stability coefficient, WP v is the mean value of the performance stability coefficients, WP max is the second threshold;

[0084] If the performance stability coefficient within the data set is greater than or equal to the first threshold and less than or equal to the mean value of the performance stability coefficients, the real-time speed of the conveyor belt is increased to improve the processing efficiency. The specific adjustment formula is: In the formula, V new is the adjusted conveyor belt speed, V at is the current conveyor belt speed, β2 is the adjustment coefficient representing the proportion of speed decrease, WP is the performance stability coefficient, WP v is the mean value of the performance stability coefficients, WP min is the first threshold.

[0085] In this embodiment, by measuring the real-time speed of the conveyor belt under different operating conditions, determining the number of images to be processed within a fixed time period according to the real-time speed of the conveyor belt and the distribution density of goji berries, and determining the theoretical processing speed of the image processing system based on the number of images; comparing and analyzing the theoretical processing speed of the image processing system with its actual processing speed, and classifying it into a normal speed synchronization situation and an abnormal speed synchronization situation according to the analysis results; for the abnormal speed synchronization situation, analyzing the fluctuation range of the accuracy of goji berry classification by the image processing system and the delay of data processing by the image processing system, and evaluating the performance stability of the image processing system when classifying goji berries; according to the evaluation results, dividing the performance stability of the image processing system when classifying goji berries under different operating conditions of the conveyor belt, and dynamically adjusting the conveyor belt speed according to the performance stability classification can ensure the efficiency and stability of the goji berry screening and grading process, improve the overall efficiency and accuracy of the system, reduce the defective rate and production cost, and enhance the consistency and quality of the product.

[0086] Embodiment 2. Please refer to Figure 2 As shown in the figure, the goji berry screening and grading system based on machine vision in this embodiment includes a conveyor belt speed acquisition module, a speed comparison and analysis module, a performance stability evaluation module, a performance classification module, and a dynamic adjustment module;

[0087] Conveyor belt speed acquisition module: Measure the real-time speed of the conveyor belt under different operating conditions, determine the number of images to be processed within a fixed time period according to the real-time speed of the conveyor belt and the distribution density of goji berries, and determine the theoretical processing speed of the image processing system based on the number of images;

[0088] Speed comparison and analysis module: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed, and classify it into a normal speed synchronization situation and an abnormal speed synchronization situation according to the analysis results;

[0089] Performance stability evaluation module: For the abnormal speed synchronization situation, analyze the fluctuation range of the accuracy of goji berry classification by the image processing system and the delay of data processing by the image processing system, and evaluate the performance stability of the image processing system when classifying goji berries;

[0090] Performance classification module: According to the evaluation results, divide the performance stability of the image processing system when classifying goji berries under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance;

[0091] Dynamic adjustment module: When the performance of the image processing system is likely to be stable, further analyze the performance stability of the image processing system during subsequent fixed time periods for wolfberry classification, and dynamically adjust the conveyor belt speed according to the analysis results to improve the overall efficiency of wolfberry screening and grading.

[0092] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0093] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0094] It should be understood that the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0095] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0096] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0097] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, and all should be covered within the protection scope of this application.

Claims

1. A wolfberry screening and grading method based on machine vision, characterized in that: It includes the following steps: S1: Measure the real-time speed of the conveyor belt under different operating conditions. According to the real-time speed of the conveyor belt and the distribution density of goji berries, determine the number of images to be processed within a fixed time period. Based on the number of images, determine the theoretical processing speed of the image processing system; S2: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed. According to the analysis results, classify it into a normal speed synchronization situation and an abnormal speed synchronization situation; S3: For the abnormal speed synchronization situation, analyze the fluctuation range of the classification accuracy of goji berries by the image processing system and the delay situation of data processing by the image processing system, and evaluate the performance stability of the image processing system when classifying goji berries; Normalize the classification accuracy fluctuation index and the image data processing delay index, and calculate the performance stability coefficient of the image processing system when classifying goji berries through the normalized classification accuracy fluctuation index and image data processing delay index; S4: According to the evaluation results, classify the performance stability of the image processing system when classifying goji berries under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance; S5: When the performance of the image processing system is possibly stable, further analyze the performance stability of the image processing system when classifying goji berries within the subsequent fixed time period. According to the analysis results, dynamically adjust the conveyor belt speed to improve the overall efficiency of goji berry screening and grading. Specifically: when the performance of the image processing system is possibly stable, that is, the performance stability coefficient generated within the fixed time period is greater than or equal to the first threshold and less than or equal to the second threshold, establish a corresponding data set for the performance stability coefficients greater than or equal to the first threshold and less than or equal to the second threshold generated within the subsequent fixed time period, and calculate the mean value within the data set. Compare and analyze the performance stability coefficients within the data set with the mean value of the performance stability coefficients, and dynamically adjust the conveyor belt speed according to the analysis results.

2. The machine vision-based wolfberry screening and grading method according to claim 1, characterized in that: In S2, the theoretical processing speed of the image processing system = the number of images to be processed per second; within a fixed time period, record the time required for the image processing system to complete classification from image acquisition, use timestamps to record the start and end times of processing each frame of the image, and calculate the number of images actually processed per unit time based on the recorded actual processing time. The actual processing speed of the image processing system = the number of images actually processed within the fixed time period / the fixed time period; compare the theoretical processing speed of the image processing system with the actual processing speed, calculate their difference, and express the deviation of the actual processing speed from the theoretical processing speed as a percentage. The specific calculation formula is: speed deviation rate = (actual processing speed - theoretical processing speed) / theoretical processing speed; according to the speed deviation rate, classify the speed deviation rate within ±10% as a normal speed synchronization situation, and if it exceeds ±10%, classify it as an abnormal speed synchronization situation.

3. The machine vision-based wolfberry screening and grading method according to claim 1, wherein: In S3, for the case of abnormal speed synchronization, a classification accuracy fluctuation index is generated according to the fluctuation range of the classification accuracy of wolfberries by the image processing system. The method for obtaining the classification accuracy fluctuation index is as follows: During a fixed time period, record the classification accuracy data of each frame of image, and establish a corresponding set of classification accuracy data A = {a1, a2,..., aj,..., an}; where j = 1, 2,..., n, and n is a positive integer greater than 0, determine the size w of the sliding window; calculate the local fluctuation value of the classification accuracy data within each sliding window, ; where KM is the local fluctuation value, and AQ is the mean of the accuracy data within the sliding window; perform smoothing processing on the calculated fluctuation data to obtain the smoothed classification accuracy fluctuation index. The specific calculation expression is: ; where LG is the classification accuracy fluctuation index, is the smoothing coefficient.

4. The method for screening and grading Chinese wolfberries based on machine vision according to claim 3, wherein: In S3, an image data processing delay index is generated according to the delay situation of data processing by the image processing system. The method for obtaining the image data processing delay index is as follows: Obtain the processing delay time of each frame of image in real time to form a time series data set D = {d1, d2,..., dm}; use the ACF and PACF diagrams to determine the parameters p, d, q of the ARIMA model, and use the delay time series data to fit the ARIMA model to estimate the model parameters. The calculation expression of the ARIMA model is: ; where, is the observed value at time t, k is the constant term, is the coefficient of the autoregressive part, is the coefficient of the moving average part, is the white noise error term; use the delay time series data to fit the ARIMA model to obtain the parameters and , use the fitted ARIMA model to predict future values to obtain the predicted value DM, calculate the error between the actual delay and the predicted delay, and calculate the image data processing delay index according to the statistical characteristics of the error. The specific calculation expression is: ; in the formula, HG is the image data processing delay index.

5. The machine vision-based wolfberry screening and grading method according to claim 1, characterized in that: In S4, the performance stability of the image processing system for wolfberry classification under different operating conditions of the conveyor belt is divided into three categories: performance stability, possible performance stability, and performance instability. Specifically: Compare the obtained performance stability coefficient of the image processing system for wolfberry classification with the gradient thresholds. The gradient thresholds include a first threshold and a second threshold, and the first threshold is less than the second threshold. Compare the performance stability coefficient of the image processing system for wolfberry classification with the first threshold and the second threshold respectively; If the performance stability coefficient of the image processing system for wolfberry classification is greater than the second threshold, the performance stability of the image processing system for wolfberry classification is high, and it is classified into the performance stability category, maintaining the current hardware configuration and algorithm; If the performance stability coefficient of the image processing system for wolfberry classification is greater than or equal to the first threshold and less than or equal to the second threshold, it is classified into the possible performance stability category, and the parameters of the image processing algorithm are adjusted; If the performance stability coefficient of the image processing system for wolfberry classification is less than the first threshold, it is classified into the performance instability category, and the image processing and classification algorithms are improved.

6. The machine vision-based wolfberry screening and grading method according to claim 1, characterized in that: If the performance stability coefficient in the data set is greater than the mean of the performance stability coefficients and less than or equal to the second threshold, increase the real-time speed of the conveyor belt to improve system stability. The specific adjustment formula is: ; In the formula, is the adjusted conveyor belt speed, is the current speed of the conveyor, is the adjustment coefficient, representing the proportion of speed increase. WP is the performance stability coefficient, is the mean of the performance stability coefficients, is the second threshold; If the performance stability coefficient in the data set is greater than or equal to the first threshold and less than the mean value of the performance stability coefficient, then reduce the real-time speed of the conveyor belt to improve the processing efficiency. The specific adjustment formula is as follows: ; In the formula, is the speed of the conveyor belt after adjustment, is the current speed of the conveyor, is the adjustment coefficient, representing the proportion of speed reduction. WP is the performance stability coefficient, is the mean value of the performance stability coefficient, is the first threshold.

7. A wolfberry screening and grading system based on machine vision, which is used to implement the wolfberry screening and grading method based on machine vision according to any one of claims 1-6, and is characterized in that: It includes a conveyor belt speed acquisition module, a speed comparison and analysis module, a performance stability evaluation module, a performance classification module, and a dynamic adjustment module; Conveyor belt speed acquisition module: Measure the real-time speed of the conveyor belt under different operating conditions, determine the number of images to be processed within a fixed time period according to the real-time speed of the conveyor belt and the distribution density of wolfberries, and determine the theoretical processing speed of the image processing system according to the number of images; Speed comparison and analysis module: Compare and analyze the theoretical processing speed of the image processing system with its actual processing speed, and classify it into a normal speed synchronization situation and an abnormal speed synchronization situation according to the analysis results; Performance stability evaluation module: For the abnormal speed synchronization situation, analyze the fluctuation range of the classification accuracy of wolfberries by the image processing system and the delay situation of data processing by the image processing system, and evaluate the performance stability of the image processing system for wolfberry classification; Performance classification module: According to the evaluation results, divide the performance stability of the image processing system for wolfberry classification under different operating conditions of the conveyor belt into three categories: performance stability, possible performance stability, and performance instability, and take corresponding measures to optimize the system performance; Dynamic adjustment module: When the performance of the image processing system is possibly stable, further analyze the performance stability of the image processing system for wolfberry classification within the subsequent fixed time period, and dynamically adjust the conveyor belt speed according to the analysis results to improve the overall efficiency of wolfberry screening and grading.

Images