Rice color sorter high-precision sorting method and system based on AI real-time compensation

Abstract

The invention relates to the technical field of optical signal analysis during rice sorting, in particular to a rice color sorter high-precision sorting method and system based on AI real-time compensation. A front camera and a rear camera are used for collecting optical signals of a rice sorting area and converting the optical signals into pixel data. Selecting reference row pixel data, and calculating a state factor according to brightness distribution of the reference row pixel data; obtaining an impurity intensity factor by combining the number, distribution and brightness values of impurity pixels in the data of the front camera and the rear camera; stacking factors are obtained through dual-camera pixel number and brightness difference analysis. And finally fusing the state factor, the impurity intensity factor and the stacking factor of each row of pixels to realize accurate illumination compensation in the rice sorting process. According to the method, the illumination condition can be compensated, so that the real characteristics of the rice are clearly captured, and the rice sorting precision is improved.

Description

Technical Field

[0001] This invention relates to the technical field of optical signal analysis during rice sorting, specifically to a method based on... A high-precision sorting method and system for rice color sorters with real-time compensation. Background Technology

[0002] In modern rice processing, rice color sorters, as efficient and intelligent sorting tools, are widely used to remove impurities and substandard grains from rice. Their main advantage lies in their ability to accurately distinguish the color, shape, and size of rice, automatically filtering out impurities, discolored rice, and other substandard grains, thereby improving the quality and market value of the rice. During the sorting process, rice bran dust significantly affects sorting accuracy. When rice bran dust covers the surface of the rice, it obscures the appearance of the rice, further affecting light reflection. This makes it difficult for sensors to accurately capture the true characteristics of the rice. This unclear surface may cause deviations in the color sorter's operation, leading to misjudgments and affecting sorting accuracy.

[0003] In reality, during the rice sorting process, the presence of rice bran dust may lead to... The light signal information collected by the sensor camera weakens, resulting in a decrease in information accuracy, which in turn affects the sorting accuracy. Summary of the Invention

[0004] To address the potential impact of rice bran dust during the rice sorting process... The weakening of light signals acquired by the sensor camera leads to a decrease in information accuracy, which in turn affects the sorting accuracy. The purpose of this invention is to provide a method based on... The high-precision sorting method and system for rice color sorting machines with real-time compensation adopts the following specific technical solution: a method based on... A high-precision rice sorting method with real-time compensation, comprising: acquiring light signals of a rice sorting area at different preset sampling times using a front camera and a rear camera; acquiring pixel information data corresponding to each light signal; selecting any row of pixel information data as reference row pixel data; obtaining a state factor of the reference row pixel data based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data acquired by the front camera and the rear camera; acquiring the state factor of each row of pixel information data within a preset period during rice sorting and transportation; acquiring impurity pixel data in each row of pixel information data; obtaining an impurity intensity factor of the reference row pixel data based on the number, distribution characteristics, and brightness value of the impurity pixel data in the reference row pixel data acquired by the front camera and the rear camera; obtaining a stacking factor of the reference row pixel data based on the difference in the number and brightness of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera; and performing illumination compensation for rice sorting based on the state factor, the impurity intensity factor, and the stacking factor of each row of pixel information data.

[0005] Further, the method for obtaining the state factor includes: obtaining a brightness judgment index for each pixel information data based on the brightness value of each pixel information data in the reference row pixel data acquired by the front camera and the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera; obtaining a first state factor for the reference row pixel data based on the brightness judgment index of the reference row pixel data and the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera; obtaining a second state factor for the reference row pixel data acquired by the rear camera according to the same calculation formula; and using the sum of the first state factor and the second state factor as the state factor of the reference row pixel data.

[0006] Furthermore, the method for obtaining the impurity intensity factor includes: using a clustering algorithm to filter out all impurity pixel data in each row of pixel information data; and obtaining the first impurity intensity in the reference row pixel data acquired by the front camera according to the first impurity intensity factor calculation formula, the first impurity intensity factor calculation formula being as follows: In the formula, The first impurity intensity factor represents the reference row pixel data acquired by the front camera; This indicates the number of impurity pixels in the reference row pixel data acquired by the front-facing camera; This indicates the reference row pixel data acquired by the front-facing camera, the first... The data of the first impurity pixel is related to the first... Distance between impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data; in the reference row pixel data acquired by the rear camera, the second impurity intensity factor of the reference row pixel data acquired by the rear camera is obtained according to the same calculation formula; the sum of the first impurity intensity factor and the second impurity intensity factor is used as the impurity intensity factor of the reference row pixel data.

[0007] Furthermore, the method for obtaining the stacking factor includes: obtaining the stacking factor according to the stacking factor calculation formula, the stacking factor calculation formula being as follows: In the formula, Indicates the stacking factor of the reference row pixel data; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera; This indicates the number of pixel information data in the reference row pixel data acquired by the rear camera; This represents the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each pixel information data; This represents the first pixel in the reference row pixel data acquired by the rear camera. The brightness value of each pixel information data; This represents the absolute value function.

[0008] Furthermore, the method for obtaining the brightness judgment index includes: obtaining the brightness judgment index according to the brightness judgment index calculation formula, the brightness judgment index calculation formula is as follows: In the formula, This refers to the brightness judgment index of each pixel information data in the reference row pixel data; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates the preset brightness threshold.

[0009] Furthermore, the method for obtaining the first state factor includes: obtaining the first state factor according to the first state factor calculation formula, the first state factor calculation formula being as follows: In the formula, The first state factor represents the reference row pixel data acquired by the front camera; This refers to the brightness judgment index of each pixel information data in the reference row pixel data; This indicates the number of pixels belonging to the rice element in the reference row pixel data acquired by the front-facing camera; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera that meets the conditions within the parentheses; This represents a step function. If the value inside the parentheses is less than 0, the function value is 0; if the value inside the parentheses is greater than 0, the function value is 1; if the value inside the parentheses is equal to 0, the function value is 0. .

[0010] A type based on A high-precision rice color sorting system with real-time compensation, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned method based on... The steps of a high-precision rice color sorting method with real-time compensation.

[0011] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method based on... The steps of a high-precision rice color sorting method with real-time compensation.

[0012] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the above-described method based on... The steps of a high-precision rice color sorting method with real-time compensation.

[0013] This invention has the following beneficial effects: Since the rice color sorter is constantly moving, the rice sorting area collected at different times varies. Furthermore, due to potential material accumulation in the rice sorting area, there may be significant differences in the light signal information from different sampling angles. Therefore, a front camera and a rear camera are used to collect the light signals of the rice sorting area at different preset sampling times; pixel information data corresponding to each light signal is obtained; since the pixel information obtained by the line scan camera each time is obtained by superimposing the dust state and the material state, all material pixels in a row of pixel data consist of two parts: those affected by dust and those not affected by dust. The comparison of these two types of pixels can reflect the degree of dust influence. Based on the brightness value distribution characteristics of each pixel in the reference row pixel data collected by the front and rear cameras respectively, a state factor for the reference row pixel data is obtained. Since the rice color sorter mainly separates rice from impurities, the impurity distribution of each row of pixel data is analyzed to obtain an impurity intensity factor. When materials pile up, friction between materials and machine vibration occur, resulting in more rice bran dust. The more severe the pile-up, the more significant the impact on impurity judgment. To reduce the factors affecting impurity judgment, the material pile-up situation is assessed. Based on the state factor, impurity intensity factor, and pile-up factor of each row of pixel data, illumination compensation is performed for rice sorting. This invention can compensate for illumination conditions, thereby clearly capturing the true characteristics of rice and improving the sorting accuracy of rice. Attached Figure Description

[0014] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A method based on an embodiment of the present invention is provided. Flowchart of a high-precision rice color sorting method with real-time compensation; Figure 2 A method based on an embodiment of the present invention is provided. Block diagram of a high-precision rice color sorting system with real-time compensation. Detailed Implementation

[0016] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following description, in conjunction with the accompanying drawings and preferred embodiments, explains the invention based on... A high-precision rice color sorting method and system with real-time compensation, its specific implementation, structure, features, and effects are described in detail below. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0018] The following detailed description, in conjunction with the accompanying drawings, illustrates a method based on the present invention. A detailed scheme for a high-precision rice color sorting method and system with real-time compensation.

[0019] Please see Figure 1 This illustrates an embodiment of the present invention based on... A high-precision sorting method for rice color sorting machine with real-time compensation, the method includes: step S1: using a front camera and a rear camera to collect light signals of the rice sorting area at different preset sampling times; and obtaining pixel information data corresponding to each light signal.

[0020] This invention is mainly applied to scenarios where rice bran dust during rice sorting affects the reflection of light signals. In this invention, the light signals from the rice sorting area are first collected for subsequent analysis.

[0021] It should be noted that the embodiments of the present invention employ a linear array. The sensor camera collects light signal information. Since the rice sorting machine is constantly moving, the rice sorting area collected at different times varies. Furthermore, due to potential material accumulation in the rice sorting area, the light signal information from different collection angles may differ significantly. Therefore, in one embodiment of this invention, a front camera and a rear camera are used to collect light signals from the rice sorting area at different preset sampling times. To facilitate subsequent analysis, the light signals are converted into electrical signals, which are then converted into digital image signals by a conversion circuit. The resolution is 2048 pixels, the scanning direction is horizontal, the scanning type is linear scanning, and the scanning frequency is 3000 Hz. That is, each scan obtains one line of scanning information, each line consisting of 2048 pixels, and the scan rate is 3000 times per second. The preset sampling time is set to 0.1 seconds. It should be noted that the preset sampling time can be set arbitrarily and is not limited here.

[0022] Step S2: Select any row of pixel information data as the reference row pixel data; based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data collected by the front camera and the rear camera respectively, obtain the state factor of the reference row pixel data; during rice sorting and transportation, obtain the state factor of each row of pixel information data within a preset period; obtain the impurity pixel data in each row of pixel information data; based on the number, distribution characteristics, and brightness value of the impurity pixel data in the reference row pixel data acquired by the front camera and the rear camera, obtain the impurity intensity factor of the reference row pixel data; based on the difference in the number and brightness of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera, obtain the stacking factor of the reference row pixel data.

[0023] The material is continuously conveyed via a conveyor belt. As the material is continuously conveyed, the amount of rice bran dust also increases, and this increase is more pronounced when conveying normal material. This is because the material is the main carrier of the rice bran dust. The material enters the conveyor device through a vibrator and moves continuously. During this process, the rice bran dust on the surface of the material is lifted, forming dust. Due to the random dispersion characteristics of dust, it is in a state of continuous generation and displacement. The material conveying is also continuously changing. The information obtained by the line scan camera when acquiring pixel information is obtained by capturing the material through the changing dust state and collecting the current state. That is, the pixel information obtained by the line scan camera each time is obtained by superimposing the dust state and the material state. Therefore, all material pixels in a row of pixel data consist of two parts: those affected by dust and those not affected by dust. The comparison of the two types of pixels can reflect the degree of dust influence. In this embodiment of the invention, the state factor of the reference row pixel data is obtained based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data acquired by the front camera and the rear camera respectively.

[0024] Preferably, in one embodiment of the present invention, the method for obtaining the state factor includes: obtaining a brightness judgment index for each pixel information data based on the brightness value of each pixel information data in the reference row pixel data obtained by the front camera and the maximum brightness value of the pixel information data in the reference row pixel data obtained by the front camera and the rear camera; the calculation formula for the brightness judgment index is as follows: In the formula, This refers to the brightness judgment index of each pixel information data in the reference row pixel data; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates a preset brightness threshold. In one embodiment of the present invention, the brightness threshold is set to 0.8. It should be noted that the brightness threshold can be set by the user and is not limited here.

[0025] In the formula for calculating the brightness judgment index, the reference row pixel data is used. Brightness value of each pixel information data Average maximum brightness value in reference row pixel data acquired from different cameras The ratio between them will be the first The brightness values ​​of each pixel are normalized to facilitate comparison with a brightness threshold; and when the ratio is less than the brightness threshold, i.e. It is believed that the pixel information data at this location is severely obscured by dust, requiring illumination compensation. When the ratio exceeds a brightness threshold, i.e. At that time, it was determined that the pixel information data at that location was not severely obscured by dust, and therefore no illumination compensation was required.

[0026] In the reference row pixel data acquired by the front camera, based on the brightness judgment index of the reference row pixel data and the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front and rear cameras, the first state factor of the reference row pixel data is obtained; the calculation formula of the first state factor is as follows: In the formula, The first state factor represents the reference row pixel data acquired by the front camera; This refers to the brightness judgment index of each pixel information data in the reference row pixel data; This indicates the number of pixels belonging to the rice element in the reference row pixel data acquired by the front-facing camera; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera that meets the conditions within the parentheses; This represents a step function. If the value inside the parentheses is less than 0, the function value is 0; if the value inside the parentheses is greater than 0, the function value is 1; if the value inside the parentheses is equal to 0, the function value is 0. .

[0027] In the first state factor calculation formula, the more pixel information data that satisfy the brightness judgment index greater than 0, the fewer pixel information data that require illumination compensation. In this case, negative correlation normalization is performed to obtain... If at this time The smaller the value, the more pixels meet the brightness threshold, and the smaller the corresponding first state factor; when At this time That is, by accumulating the pixel information data whose brightness values ​​do not meet the brightness threshold, and combining it with... The final result The larger the sum, the more pixel information data whose brightness values ​​do not meet the brightness threshold, and the more the reference row pixel data needs illumination compensation. At this time, the first state factor is larger.

[0028] It should be noted that the calculation method of the state factor of the reference row pixel data acquired by the rear camera is exactly the same as that of the first state factor of the reference row pixel data acquired by the front camera. Therefore, in the reference row pixel data acquired by the rear camera, the state factor of the reference row pixel data acquired by the rear camera is obtained according to the same calculation formula and used as the second state factor; the sum of the first state factor and the second state factor is used as the state factor of the reference row pixel data.

[0029] Since the rice color sorter mainly separates rice from impurities, in this embodiment of the invention, the impurity distribution of the pixel information data in each row is analyzed to obtain the impurity intensity factor.

[0030] Preferably, in one embodiment of the present invention, the method for obtaining the impurity intensity factor includes: defining the number of clusters as 3 using a clustering algorithm, obtaining rice pixel clusters, impurity pixel clusters and background pixel clusters respectively. In this embodiment of the present invention, the pixel information data within the impurity pixel clusters is obtained as the impurity pixel data in each row of pixel information data, and then further analyzed.

[0031] In the reference row pixel data acquired by the front camera, the first impurity intensity is obtained according to the first impurity intensity factor calculation formula, which is as follows: In the formula, The first impurity intensity factor represents the reference row pixel data acquired by the front camera; This indicates the number of impurity pixels in the reference row pixel data acquired by the front-facing camera; This indicates the reference row pixel data acquired by the front-facing camera, the first... The data of the first impurity pixel is related to the first... Distance between impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data.

[0032] In the first impurity intensity factor calculation formula, the number of impurity pixel data The more impurities there are, the greater the number of impurities in the reference row pixel data, and the larger the first impurity intensity factor; the smaller the average distance between impurity pixel data, the denser the impurity distribution. The larger the value, the larger the intensity factor of the first impurity; the greater the difference in brightness between different impurities, the more complex the types of impurities contained. The larger the sum, the better. for This indicates that two pixels are adjacent, and adjacent pixels belong to the same impurity, therefore they do not participate. The calculation of the value, when Not for When The resulting values ​​are used as weights and a weighted average is performed to obtain... , The larger the value, the more types of impurities there are, and the greater the intensity factor of the first impurity.

[0033] It should be noted that the calculation method of the second impurity intensity factor of the reference row pixel data acquired by the rear camera is exactly the same as that of the first impurity intensity factor of the reference row pixel data acquired by the front camera. Therefore, in the reference row pixel data acquired by the rear camera, the second impurity intensity factor of the reference row pixel data acquired by the rear camera is obtained according to the same calculation formula; the sum of the first impurity intensity factor and the second impurity intensity factor is used as the impurity intensity factor of the reference row pixel data.

[0034] When materials are stacked, friction between materials and machine vibration will occur, resulting in more rice bran dust. Moreover, the more severe the stacking, the more obvious the impact on impurity judgment. In order to reduce the factors affecting impurity judgment, the stacking of materials is judged in this embodiment of the invention.

[0035] Preferably, in one embodiment of the present invention, the method for obtaining the stacking factor includes: obtaining the stacking factor according to the stacking factor calculation formula, the stacking factor calculation formula being as follows: In the formula, Indicates the stacking factor of the reference row pixel data; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera; This indicates the number of pixel information data in the reference row pixel data acquired by the rear camera; This represents the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each pixel information data; This represents the first pixel in the reference row pixel data acquired by the rear camera. The brightness value of each pixel information data; This represents the absolute value function.

[0036] The stacking factor calculation formula calculates the difference in brightness values ​​between each pair of corresponding pixels. The larger the value, the more pronounced the tendency for the preceding and following pixels to not belong to the same object. In other words, the objects captured by the front and rear cameras are different, so the tendency for the materials to stack is more pronounced, and the larger the stacking factor is.

[0037] Step S3: Perform illumination compensation for rice sorting based on the state factor, impurity intensity factor, and stacking factor of each row of pixel information data.

[0038] One embodiment of the present invention provides a method for light compensation in rice sorting, specifically including: arbitrarily selecting pixel information data for each row at three consecutive preset sampling times, calculating the impurity intensity factor and stacking factor of each row of pixel information data, performing maximum and minimum normalization on the impurity intensity factor and stacking factor of the three rows of pixel information data respectively, and using the average of the normalized values ​​of the impurity intensity factor and the stacking factor as the material influence factor.

[0039] Let the initial luminous flux be... The unit is lumens, and the luminous flux after compensation is... And the unit is the same as the initial luminous flux, determined by the state factor. Material Influence Factor , combined ,get The details are as follows: In other words, when impurities are present, the more obvious the influence of dust, the greater the intensity of impurities and their stacking, the more light compensation is obtained, thus increasing the light flux and completing the light compensation.

[0040] In summary, the following methods are employed: front and rear cameras are used to collect light signals from the rice sorting area at different preset sampling times; pixel information data corresponding to each light signal is obtained; a row of pixel information data is randomly selected as the reference row pixel data; based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data collected by the front and rear cameras, the state factor of the reference row pixel data is obtained; during rice sorting and transportation, the state factor of each row of pixel information data within a preset period is obtained; impurity pixel data in each row of pixel information data is obtained; based on the number, distribution characteristics, and brightness value of impurity pixel data in the reference row pixel data acquired by the front and rear cameras, the impurity intensity factor of the reference row pixel data is obtained; based on the differences in the number and brightness of pixel information data in the reference row pixel data acquired by the front and rear cameras, the stacking factor of the reference row pixel data is obtained; and illumination compensation is performed on the rice sorting based on the state factor, impurity intensity factor, and stacking factor of each row of pixel information data.

[0041] A second objective of one embodiment of the present invention is to provide an intelligent processing system for uterine tumor images, such as... Figure 2 As shown, the system includes a memory, a processor, and a computer program. The memory stores the corresponding computer program, and the processor runs the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1-S3, specifically including: a light signal acquisition module 101, used to acquire light signals from the rice sorting area at different preset sampling times using a front camera and a rear camera; and to acquire pixel information data corresponding to each light signal; a light signal analysis module 102, used to select any row of pixel information data as reference row pixel data; and to obtain reference values ​​based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data acquired by the front camera and the rear camera. The system includes: a state factor for the reference row pixel data; a state factor for the pixel information data of each row within a preset period during rice sorting and transportation; acquisition of impurity pixel data in each row pixel information data; an impurity intensity factor for the reference row pixel data based on the number, distribution characteristics, and brightness value of the impurity pixel data in the reference row pixel data acquired by the front and rear cameras; and a stacking factor for the reference row pixel data based on the differences in the number and brightness of the pixel information data in the reference row pixel data acquired by the front and rear cameras. An illumination compensation module 103 is used to perform illumination compensation for rice sorting based on the state factor, impurity intensity factor, and stacking factor of the pixel information data of each row.

[0042] A third objective of this invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the methods described in steps S1-S3.

[0043] The fourth objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in steps S1-S3.

[0044] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0045] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method based on A high-precision rice color sorting method with real-time compensation, characterized in that... The method includes: acquiring light signals from a rice sorting area at different preset sampling times using a front-facing camera and a rear-facing camera; obtaining pixel information data corresponding to each light signal; selecting any row of pixel information data as reference row pixel data; obtaining a state factor of the reference row pixel data based on the brightness value distribution characteristics of each pixel information data in the reference row pixel data acquired by the front-facing camera and the rear-facing camera; acquiring the state factor of each row of pixel information data within a preset period during rice sorting and transportation; acquiring impurity pixel data in each row of pixel information data; obtaining an impurity intensity factor of the reference row pixel data based on the number, distribution characteristics, and brightness value of the impurity pixel data in the reference row pixel data acquired by the front-facing camera and the rear-facing camera; obtaining a stacking factor of the reference row pixel data based on the difference in the number and brightness of the pixel information data in the reference row pixel data acquired by the front-facing camera and the rear-facing camera; and performing illumination compensation for rice sorting based on the state factor, the impurity intensity factor, and the stacking factor of each row of pixel information data.

2. A method based on claim 1 A high-precision rice color sorting method with real-time compensation, characterized in that... The method for obtaining the state factor includes: obtaining a brightness judgment index for each pixel information data based on the brightness value of each pixel information data in the reference row pixel data acquired by the front camera and the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera; obtaining a first state factor for the reference row pixel data based on the brightness judgment index of the reference row pixel data and the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front camera and the rear camera; obtaining a second state factor for the reference row pixel data acquired by the rear camera based on the same calculation formula; and using the sum of the first state factor and the second state factor as the state factor of the reference row pixel data.

3. A method based on claim 1 A high-precision rice color sorting method with real-time compensation, characterized in that... The method for obtaining the impurity intensity factor includes: using a clustering algorithm to filter out all impurity pixel data in each row of pixel information data; and obtaining the first impurity intensity in the reference row pixel data acquired by the front camera according to the first impurity intensity factor calculation formula, which is as follows: In the formula, The first impurity intensity factor represents the reference row pixel data acquired by the front camera; This indicates the number of impurity pixels in the reference row pixel data acquired by the front-facing camera; This indicates the reference row pixel data acquired by the front-facing camera, the first... The data of the first impurity pixel is related to the first... Distance between impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data; This indicates the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each impurity pixel data; in the reference row pixel data acquired by the rear camera, the second impurity intensity factor of the reference row pixel data acquired by the rear camera is obtained according to the same calculation formula; the sum of the first impurity intensity factor and the second impurity intensity factor is used as the impurity intensity factor of the reference row pixel data.

4. A method based on claim 1 A high-precision rice color sorting method with real-time compensation, characterized in that... The method for obtaining the stacking factor includes: obtaining the stacking factor according to the stacking factor calculation formula, which is shown below: In the formula, Indicates the stacking factor of the reference row pixel data; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera; This indicates the number of pixel information data in the reference row pixel data acquired by the rear camera; This represents the first pixel in the reference row pixel data acquired by the front camera. The brightness value of each pixel information data; This represents the first pixel in the reference row pixel data acquired by the rear camera. The brightness value of each pixel information data; This represents the absolute value function.

5. A method based on claim 2 A high-precision rice color sorting method with real-time compensation, characterized in that... The method for obtaining the brightness judgment index includes: obtaining the brightness judgment index according to the brightness judgment index calculation formula, the brightness judgment index calculation formula is as follows: In the formula, This refers to the brightness judgment index of each pixel information data in the reference row pixel data; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates the preset brightness threshold.

6. A method based on claim 2 A high-precision rice color sorting method with real-time compensation, characterized in that... The method for obtaining the first state factor includes: obtaining the first state factor according to the first state factor calculation formula, which is shown below: In the formula, The first state factor represents the reference row pixel data acquired by the front camera; This refers to the brightness judgment index of each pixel information data in the reference row pixel data; This indicates the number of pixels belonging to the rice element in the reference row pixel data acquired by the front-facing camera; Indicates the first pixel in the reference row pixel data The brightness value of each pixel information data; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the front-facing camera; This represents the maximum brightness value of the pixel information data in the reference row pixel data acquired by the rear camera; This indicates the number of pixel information data in the reference row pixel data acquired by the front camera that meets the conditions within the parentheses; This represents a step function. If the value inside the parentheses is less than 0, the function value is 0; if the value inside the parentheses is greater than 0, the function value is 1; if the value inside the parentheses is equal to 0, the function value is 0. .

7. A method based on A high-precision rice color sorting system with real-time compensation, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that... When the processor executes the computer program, it implements the method based on any one of claims 1 to 6. The steps of a high-precision rice color sorting method with real-time compensation.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method based on any one of claims 1 to 6. The steps of a high-precision rice color sorting method with real-time compensation.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method based on any one of claims 1 to 6. The steps of a high-precision rice color sorting method with real-time compensation.

Images