Strawberry fruit weight monitoring system based on machine learning

Abstract

The invention provides a strawberry fruit weight monitoring system based on machine learning. The strawberry fruit weight monitoring system comprises a growth monitoring module, a cloud management module and a user terminal module. The growth monitoring module is matched with the LED module through the image sensing module to obtain strawberry fruit images and real scales, and the strawberry fruit images and the real scales are transmitted to a cloud end through the wireless communication module (1). And the cloud management module covers several processes of data receiving, image segmentation, volume calculation, mass calculation, intelligent judgment and result output. The volume calculation module provides an accurate real scale reference through the LED module, data deviation caused by manual calibration errors in traditional measurement is avoided, and accuracy and consistency of strawberry shape data acquisition are ensured. The user terminal module presents the growth trend and quality change of the strawberries through a visual chart and a curve, and supports a user to define a threshold value, thereby greatly facilitating the user to monitor the growth condition of the strawberries in real time.

Description

Technical Field

[0001] The present invention relates to the field of smart agriculture, and in particular to a strawberry fruit weight monitoring system based on machine learning. Background Art

[0002] Global strawberry cultivation is expanding, but a lack of accurate weight monitoring and yield estimation methods leads to significant losses during harvesting, storage, and transportation. Frequent disease outbreaks have led to increased pesticide use, raising costs and creating food safety concerns. While machine learning and IoT technologies have demonstrated significant success in other industries with the continuous advancement of artificial intelligence, they are underappreciated in strawberry fruit weight monitoring.

[0003] Traditional strawberry fruit weight monitoring relies heavily on manual picking and weighing, which is inefficient, has high lags, and makes it difficult to obtain real-time data. Contact sensors can easily damage the fruit, are susceptible to significant environmental interference, and produce unstable data, making them unable to meet the precision management needs of modern agriculture. Precision agriculture and artificial intelligence technologies are increasingly being applied in agriculture. Precision agriculture enables precise monitoring of plant growth and timely identification of problems. A machine learning-based strawberry fruit weight monitoring system can accurately determine strawberry weight without damaging the fruit, reducing labor costs and subjective judgment errors, and contributing to the scientific and intelligent development of strawberry cultivation. Summary of the Invention

[0004] The purpose of the present invention is to solve the problem that traditional strawberry fruit weight monitoring cannot accurately measure the weight of strawberries in real time and calculate the growth curve of strawberry fruits. A strawberry fruit weight monitoring system based on machine learning is proposed. The image sensing module cooperates with the LED module to obtain the strawberry fruit image and real scale, and the wireless communication module 1 transmits the image to the cloud. Then, the image segmentation and volume calculation module, the mass calculation and intelligent judgment module in the cloud are used to analyze the growth trend of the strawberry fruit. Finally, the results are summarized in the user terminal module to realize visual monitoring.

[0005] The technical implementation scheme of the present invention is as follows: the machine learning-based strawberry fruit weight monitoring system includes an image sensing module, an LED module, a wireless communication module, a cloud management module and a user terminal module; the cloud management module includes the processes of data reception, image segmentation, volume and mass calculation, analysis and result output.

[0006] Furthermore, the LED module forms optical reference points with a fixed spacing in the strawberry image through two LED light sources at a fixed distance, providing an accurate real-world scale benchmark for subsequent image analysis.

[0007] Furthermore, the image sensing module uses a high-resolution camera to shoot strawberry fruits from multiple angles at fixed time intervals, obtains strawberry image data including LED scale in real time, and quickly transmits it to the cloud management module via wireless communication 1.

[0008] Furthermore, the cloud management module first receives data, obtains multiple frames of strawberry images and LED scale reference information from the image sensing module, and establishes a dynamic image data set.

[0009] Furthermore, the cloud management module performs image segmentation, uses a deep learning semantic segmentation algorithm, and combines it with the real-world size benchmark of the LED scale to accurately extract the outline of the strawberry fruit from the image and calibrate it to the actual physical size.

[0010] Furthermore, the cloud management module performs feature extraction and generates a multidimensional feature vector by calculating geometric features such as the area, perimeter, and compactness of the strawberry fruit contour.

[0011] Furthermore, the cloud management module performs volume calculation, adopts a multi-level three-dimensional modeling algorithm, converts the strawberry fruit contour data into a three-dimensional model and calculates volume parameters.

[0012] Furthermore, the cloud management module trains a regression model based on historical volume and quality data, inputs the real-time volume calculation results into the trained model, outputs the strawberry quality prediction value, and dynamically optimizes the model parameters according to actual conditions.

[0013] Furthermore, the cloud management module performs intelligent judgment, inputs data such as volume change rate and mass growth curve into a pre-trained machine learning model, judges the growth stage and health status of the strawberry fruit by comparing historical data with health standards, and sends the analysis results to the user terminal module.

[0014] Furthermore, the user terminal module can be any digital device with data processing capabilities, such as a mobile phone, a host or a tablet computer, etc. The user terminal module receives and visualizes the analysis results of the cloud management module and displays them to the user in the form of growth curves, health scores, etc.

[0015] Furthermore, the user interaction module receives analysis results sent by the cloud management module and displays the strawberry fruit growth curve, quality change trend, and health status through a graphical interface. It supports user-defined growth parameter thresholds and accepts cultivation measure records manually entered by the user.

[0016] The beneficial effects of the present invention are: 1. The machine learning-based strawberry fruit weight monitoring system in the present invention provides a precise real-world scale benchmark through the LED module, avoiding data deviation caused by manual calibration errors in traditional measurements and ensuring the accuracy and consistency of strawberry morphological data collection. 2. The present invention proposes a strawberry fruit weight monitoring system based on machine learning. It adopts a volume mass calculation method that combines multi-level three-dimensional modeling with machine learning. It uses strawberry volume data as input and predicts mass through a trained regression model. Compared with a single algorithm, it significantly improves the accuracy and efficiency of measurement. 3. The present invention provides a machine learning-based strawberry fruit weight monitoring system. The user interaction module presents strawberry growth trends and quality changes in visual charts and curves, supports user-defined thresholds, and greatly facilitates real-time monitoring of strawberry growth conditions. 4. The machine learning-based strawberry fruit weight monitoring system in the present invention integrates data processing and analysis functions through a cloud management module, automatically completing the entire process from image sensing and feature extraction to growth status judgment, reducing manual intervention, labor costs and subjective judgment errors, and promoting scientific and intelligent strawberry cultivation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Overall design structure diagram of the strawberry fruit weight monitoring system based on machine learning.

[0018] Figure 2 Design structure diagram of the cloud management module of the strawberry fruit weight monitoring system based on machine learning.

[0019] Figure 3 Design structure diagram of the growth monitoring module of the strawberry fruit weight monitoring system based on machine learning. Specific implementation cases

[0020] In order to make relevant personnel in this field better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, other similar embodiments made by those skilled in the art without making creative work should all fall within the scope of protection of this application. At present, the global strawberry planting area continues to expand. The traditional manual monitoring method has problems such as low efficiency, large error, and delayed response, and excessive use of water and fertilizer is prone to soil degradation and environmental pollution. To this end, we have designed a strawberry fruit weight monitoring system based on machine learning to achieve high-precision real-time monitoring of strawberry fruit weight, effectively improve the intelligent management level of strawberry planting, reduce resource waste and reduce disease prevention and control costs.

[0021] like Figure 1 As shown in the figure, the entire system consists of an image sensing module, a cloud management module, and a user terminal module; Figure 2 As shown, the cloud management module covers several processes including data reception, image segmentation, volume calculation, quality calculation, intelligent judgment and result output.

[0022] As shown in Figure 1, the LED module uses two LED light sources and provides a scale benchmark for image analysis through optical markers with fixed spacing, ensuring accurate quantification of strawberry morphological data.

[0023] like Figure 1 As shown in the figure, the image sensing module is equipped with a high-resolution camera to obtain strawberry fruit images in a periodic shooting mode, combined with LED to achieve visual capture of fruit weight changes, and transmit the original image data to the cloud management module in real time.

[0024] like Figure 2 As shown, the cloud management module first receives data, obtains strawberry fruit images and LED scale information from the image sensor module, and establishes a data set containing fruit images at different growth stages.

[0025] like Figure 2 As shown in the figure, the cloud management module performs image preprocessing, uses image segmentation algorithm to extract the outline of the strawberry fruit, combines the LED scale to calibrate the outline size, and converts the fruit image into quantifiable digital information.

[0026] like Figure 2 As shown in the figure, the cloud management module performs feature extraction and calculates the geometric features of the strawberry fruit contour, such as area, perimeter, and aspect ratio, to form a fruit morphological feature vector as an input parameter for subsequent calculations.

[0027] like Figure 2 As shown, the cloud management module performs volume calculation, divides the strawberry fruit into multiple layers along the vertical central axis, calculates the microelement volume through the area of each layer and the distance between layers, and accumulates the total volume of the fruit.

[0028] like Figure 2 As shown, the cloud management module performs quality prediction, inputs the fruit volume data into a pre-trained machine learning regression model, outputs the predicted quality value of the strawberry fruit, and dynamically updates the model parameters to improve accuracy.

[0029] like Figure 2 As shown, the cloud management module finally outputs the results and sends the volume, quality data and growth status analysis results of the strawberry fruit to the user terminal module.

[0030] like Figure 1 As shown, the user terminal module can be used on smart devices such as mobile phones and tablets to receive and display the weight change trends and growth health of strawberries in the form of charts and curves. Users can also customize weight thresholds. When the fruit weight is abnormal, the system automatically issues an early warning, allowing users to keep abreast of the fruit's growth dynamics.

[0031] All features disclosed in this specification, or steps in all methods or processes disclosed, except for mutually exclusive features and / or steps, may be combined in any manner. Any feature disclosed in this specification (including any appended claims and abstract), unless otherwise stated, may be replaced by an equivalent or similar alternative feature. That is, unless otherwise stated, each feature is merely an example of a set of equivalent or similar features.

[0032] The above technical solution only reflects one technical solution of this technical solution. Some changes that may be made to certain parts thereof by technical personnel in this technical field all reflect the principles of this design system and should also fall within the scope of protection of this patent.

Claims

1. A strawberry fruit weight monitoring system based on machine learning, characterized in that: The strawberry fruit weight monitoring system adopts a machine learning algorithm to realize efficient and visual strawberry fruit weight monitoring, comprising a growth monitoring module, a cloud management module, and a user terminal module; the growth monitoring module comprises an LED module, a strawberry image acquisition module, and a wireless communication module (1); the cloud management module comprises a wireless communication module (2), an image segmentation and volume calculation module, a mass calculation and intelligent judgment module, and a wireless communication module (3); the wireless communication module (2) receives image information from the wireless communication module (1) and inputs it into the image segmentation algorithm; the image segmentation and volume calculation module adopts a machine learning algorithm and a volume algorithm to process the input image information and calculate the predicted volume of the strawberry; the mass calculation and intelligent judgment module uses the predicted volume data to perform mass calculation and judge the growth stage and health status of the strawberry; the wireless communication module (3) transmits the predicted data to the user terminal module; the user terminal module comprises a wireless communication module (4), a data visualization module, and a user interaction module; the wireless communication module (4) receives data from the wireless communication module (3) and transmits it to the data visualization module; the data visualization module visually presents the analysis results of the cloud management module and displays them to the user in the form of growth curves, health scores, etc.

2. A strawberry fruit weight monitoring system based on machine learning as claimed in claim 1, characterized in that, The image segmentation and volume calculation module is connected to the wireless communication module (2), receives image data and predicts the volume of strawberry fruit.

3. A strawberry fruit weight monitoring system based on machine learning as claimed in claim 1, characterized in that, The mass calculation and intelligent judgment module is connected to the volume calculation, receives volume data to perform mass calculation and judge the growth stage and health status of the strawberries, thereby realizing real-time and accurate measurement of the weight of the strawberry fruits.

Images