Device and method for nondestructive detection of egg properties

Abstract

The present invention provides a nondestructive detection device and method for egg properties, which belongs to the field of nondestructive detection of agricultural products. The device includes: a property detection module, a detection box, at least three detection cameras at different angles, a weighing platform, and a roundness detector; a plurality of rubber-coated motor rollers for driving eggs to roll around a long axis are installed at the end of a bracket on the weighing platform; the roundness detection module collects the up and down displacement change value of a vibration detection rod during the rolling process of an egg after the vibration detection rod moves to the height of the egg with an electric push rod and rotates to the top parallel to the long axis of the egg with a driving motor; the property detection module calculates the egg volume and egg shape index according to multi-angle images by three-dimensional reconstruction, calculates the density loss rate and egg ellipsoid, and determines the egg properties according to the density loss rate, egg shape index and egg ellipsoid. The device reduces the volume measurement error, improves the accuracy of freshness detection, and can improve the efficiency of egg property detection through integrated detection without increasing the detection process and detection space.

Description

Technical Field

[0001] The present invention relates to the field of non-destructive testing of agricultural products, and in particular to a device and method for non-destructive testing of egg properties. Background Art

[0002] Chicken, duck, and goose eggs are rich in nutrients and are highly sought after by consumers. Egg freshness is not only a key indicator of protein content but also closely linked to consumer health and a crucial indicator of hatchability. Therefore, accurate egg quality testing is crucial during egg production and distribution.

[0003] Currently, a method for determining egg freshness involves calculating the egg's density loss rate based on its initial and current densities. This is then applied to an established model combining density loss rates and Haugh units to calculate the Haugh units. This method uses a microcontroller to control a camera module to capture images of the egg under test. Image processing and analysis are then used to determine the egg's major and minor axis data. A corresponding mathematical model is then used to calculate the egg's initial mass and volume for density calculation.

[0004] However, the above method predicts the volume of eggs through image projection analysis, which has large relative errors and low prediction accuracy and has certain limitations. Summary of the Invention

[0005] In view of the problems existing in the prior art, the present invention provides a device and method for non-destructive detection of egg properties.

[0006] The present invention provides a nondestructive egg property detection device, comprising: a property detection module, a detection box, at least three detection cameras arranged at different angles on the top of the detection box, a weighing platform arranged at the bottom of the detection box, and a roundness detector arranged next to the weighing platform. The roundness detector comprises an elastically retractable electric push rod, a drive motor, a vibration detection rod, and a roundness detection module. The weighing platform is fixed with a bracket, and a plurality of rubber-coated motor rollers for driving the egg to roll around its long axis are installed at the end of the bracket. The roundness detection module is used to collect the vertical displacement change value of the vibration detection rod during the egg rolling process after the vibration detection rod moves to the height of the egg with the electric push rod and rotates to a position directly above the egg's long axis with the drive motor. The property detection module is used to perform three-dimensional reconstruction based on multi-angle images acquired by the detection camera to calculate the egg volume and egg shape index, calculate the density loss rate based on the egg volume and the egg weight obtained by the weighing platform, calculate the egg ellipsoidality based on the vertical displacement change value, and determine the egg property based on the density loss rate, egg shape index, and egg ellipsoidality.

[0007] According to the present invention, a non-destructive detection device for egg properties is provided. The property detection module includes: a three-dimensional reconstruction unit, which is used to obtain an image from each detection camera and perform three-dimensional reconstruction based on each image to calculate the major semiaxis, minor semiaxis, and a third semiaxis perpendicular to the major semiaxis and the minor semiaxis; a volume calculation unit, which is used to calculate the egg volume based on the major semiaxis, the minor semiaxis, and the third semiaxis; an egg shape index calculation unit, which is used to calculate the egg shape index based on the major semiaxis and the minor semiaxis; a density calculation unit, which is used to calculate the current density of the egg based on the egg volume and the egg weight obtained by the weighing platform, and calculate the density loss rate based on the preset density of the egg type and the current density; a roundness calculation unit, which is used to determine the egg ellipsoidality based on the upper and lower displacement change values; and a property output unit, which is used to determine the egg property based on the density loss rate, the egg shape index, and the egg ellipsoidality.

[0008] According to a non-destructive detection device for egg properties provided by the present invention, the egg properties include egg freshness and egg hatching success prediction. Accordingly, the property detection module is specifically used to: when it is detected that the input egg is used for food, input the density loss rate into a trained first detection model, output the egg Haugh unit value, and determine the egg freshness based on the Haugh unit value; when it is detected that the input egg is used for hatching, input the density loss rate, the egg shape index and the egg ellipsoidality into a trained second detection model, and output the egg hatching success prediction; wherein, the first detection model is obtained by training with the density loss rate as input data based on multiple egg samples with known Haugh unit values, and the second detection model is obtained by training with the density loss rate, the egg shape index and the egg ellipsoidality as input data based on multiple egg samples with known hatching ratios.

[0009] According to the present invention, a nondestructive detection device for egg properties further includes a display and a human-computer interaction device; the human-computer interaction device is used to receive input of egg usage; and the display is used to display egg properties.

[0010] According to a nondestructive testing device for egg properties provided by the present invention, the roundness calculation unit is specifically used to: determine the maximum minor semiaxis and the minimum third semiaxis according to the upper and lower displacement change values; and determine the egg ellipsoidality according to the ratio of the minimum third semiaxis to the maximum minor semiaxis.

[0011] According to the nondestructive detection device for egg properties provided by the present invention, three detection cameras are respectively located directly above and on both sides of the eggs.

[0012] According to a non-destructive testing device for egg properties provided by the present invention, a support plate is provided on the upper surface of the weighing platform, a light-transmitting hole is provided in the middle of the support plate, and an LED white light for fill light is installed in the light-transmitting hole; a reflector for focusing light is fixed on the upper surface of the support plate, the reflector is sleeved on the outer side of the rubber-coated motor roller, and the upper end of the reflector is lower than half of the egg.

[0013] According to a nondestructive testing device for egg properties provided by the present invention, two groups of rubber-coated motor rollers are provided, each group of rubber-coated motor rollers is distributed in an arc shape, and the two groups of rubber-coated motor rollers are symmetrically arranged on both sides of the midline of the egg's long axis.

[0014] The present invention also provides a non-destructive detection method for egg properties, comprising: acquiring an image from each detection camera, and performing three-dimensional reconstruction based on each image to calculate the egg's major semiaxis, minor semiaxis, and a third semiaxis perpendicular to both the major and minor semiaxis; calculating the egg volume based on the major semiaxis, the minor semiaxis, and the third semiaxis; calculating an egg shape index based on the major semiaxis and the minor semiaxis; calculating the egg's current density based on the egg volume and the egg weight obtained by the weighing platform, and calculating a density loss rate based on a preset density of the egg type and the current density; determining the egg's ellipsoidality based on the up-and-down displacement change value; and determining the egg's properties based on the density loss rate, the egg shape index, and the egg's ellipsoidality.

[0015] According to the present invention, a non-destructive detection method for egg properties is provided, wherein the egg properties are determined based on the density loss rate, egg shape index, and egg ellipsoidality. The method comprises: when it is detected that the input eggs are intended for consumption, inputting the density loss rate into a trained first detection model, outputting an egg Haugh unit value, and determining the egg freshness based on the Haugh unit value; when it is detected that the input eggs are intended for hatching, inputting the density loss rate, the egg shape index, and the egg ellipsoidality into a trained second detection model, and outputting a prediction degree of hatching success of the egg; wherein the first detection model is obtained by training multiple egg samples with known Haugh unit values ​​using the density loss rate as input data, and the second detection model is obtained by training multiple egg samples with known hatching ratios using the density loss rate, egg shape index, and egg ellipsoidality as input data.

[0016] The device and method for nondestructive egg trait testing provided by the present invention predict egg volume through multi-angle image analysis, reducing volume measurement errors and thus improving the accuracy of freshness testing. Furthermore, combined with the egg ellipsoid measurement of a roundness detector, deformed eggs with low ellipsoidality can be promptly detected, facilitating scenarios such as hatching, further improving the reliability of egg trait measurement. Furthermore, the device integrates the testing process, eliminating the need for additional testing procedures and space, thereby comprehensively improving the efficiency of egg trait testing and reducing testing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a schematic diagram of the main structure of the non-destructive testing device for egg properties according to an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the three-dimensional structure of the non-destructive detection device for egg properties according to an embodiment of the present invention;

[0020] Figure 3 This is the second schematic diagram of the three-dimensional structure of the non-destructive testing device for egg properties according to an embodiment of the present invention;

[0021] Figure 4 Schematic diagram of the support structure of an embodiment of the present invention.

[0022] Figure numerals: 1. Detection box; 2. Detection camera; 3. Display; 4. Weighing platform; 5. Support plate; 6. Light hole; 7. LED white light; 8. Bracket; 9. Rubber-coated motor roller; 10. Reflector; 11. Electric push rod; 12. Drive motor; 13. Roundness detection module; 14. Vibration detection rod. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0024] The following combination Figures 1-4 The present invention describes a device and method for non-destructive detection of egg properties. Figure 1 This is a schematic diagram of the main structure of the non-destructive testing device for egg properties according to an embodiment of the present invention. Figure 2 and Figure 3 This is a schematic diagram of the three-dimensional structure of the non-destructive testing device for egg properties according to an embodiment of the present invention. Figure 4 FIG. 1 is a schematic diagram of the supporting mechanism structure of an embodiment of the present invention, as shown in FIG. Figure 1-4 As shown, the present invention provides a non-destructive detection device for egg properties, comprising:

[0025] A property detection module, a detection box 1, at least three detection cameras 2 arranged at different angles on the top of the detection box 1, a weighing platform 4 arranged at the bottom of the detection box 1, and a roundness detector arranged next to the weighing platform 4. The roundness detector includes an elastically retractable electric push rod 11, a drive motor 12, a vibration detection rod 14 and a roundness detection module 13; a bracket 8 is fixed on the weighing platform 4, and a plurality of rubber-coated motor rollers 9 are installed at the end of the bracket 8 for driving the eggs to roll around the long axis.

[0026] The roundness detection module 13 is used to collect the vertical displacement change value of the vibration detection rod 14 during the rolling process of the egg after the vibration detection rod 14 moves to the egg height with the electric push rod 11 and rotates to the top parallel to the long axis of the egg with the drive motor 12.

[0027] The property detection module is used to perform three-dimensional reconstruction based on the multi-angle images obtained by the detection camera 2 to calculate the egg volume and egg shape index, calculate the density loss rate based on the egg volume and the egg weight obtained by the weighing platform 4, calculate the egg ellipsoidality based on the up and down displacement change value, and determine the egg property based on the density loss rate, egg shape index and egg ellipsoidality.

[0028] The upper portion of the inspection box 1 is equipped with a camera 2 for photographing eggs. First, the trait detection module uses the camera 2 to capture multi-angle images of the egg. When the rubber-coated motor roller 9 is powered on, it rotates with the egg. The camera 2 captures the rotating egg from multiple angles, with the captured images labeled a1, ..., an. Based on the 3D reconstruction of these images, the lengths of the three semi-axes are measured to calculate the average values ​​ra, rb, and rc. The semi-major axis ra is the longest semi-axis of the ellipsoid, typically referring to the radius along the longest axis; the semi-minor axis rb is the second-longest semi-axis of the ellipsoid, typically referring to the radius along the second-longest axis; and the tertiary semi-axis rc is the third semi-axis of the ellipsoid, typically referring to the radius perpendicular to the major and minor semi-axes.

[0029] The egg volume V is calculated by fitting an ellipsoidal shape model through three-dimensional reconstruction:

[0030] V = 4πra·rb·rc / 3

[0031] The weighing platform 4 can serve as a support mechanism for placing eggs and is fixed to the bottom of the detection box 1. The weighing end of the weighing platform is mounted with a support plate 5, and a plurality of brackets 8 are fixed to the upper surface of the support plate. The ends of the brackets 8 are mounted with rubber-coated motor rollers 9 for driving the eggs. The plurality of rubber-coated motor rollers 9 are in contact with the outer surface of the eggs.

[0032] Considering that although three-dimensional reconstruction can calculate a more accurate volume using three semi-axes, it is computationally intensive and subject to significant errors when used to determine egg ellipsoidality, a roundness detector for detecting egg ellipsoidality is also installed at the bottom of the detection box 1 of the present invention. Preferably, the roundness detector includes an electric push rod 11 fixed to the bottom of the detection box, the telescopic end of the electric push rod 11 being fixed to a drive motor 12 via a pressure sensor, the output shaft of the drive motor 12 being fixed to a roundness detection module 13, and a vibration detection rod 14 being mounted on the roundness detection module, which can be rotated to a position directly above the long axis of the egg and then in contact with the surface of the egg.

[0033] The electric push rod 11 is used to control the lifting and lowering of the drive motor 12, and the output shaft of the drive motor 12 is connected to the vibration detection rod 14 through the roundness detection module 13, so that the drive motor 12 can rotate with the vibration detection rod 14 to the top of the egg, so that the roundness detection module 13 can detect the ellipsoidality of the rotating egg through the vibration detection rod 14. After the electric push rod 11 descends, the vibration detection rod 14 contacts the surface of the egg, and the pressure sensor cuts off the power to the electric push rod 11 after detecting the pressure change, to prevent the electric push rod 11 from being continuously energized, causing the vibration detection rod 14 to squeeze the egg too much and cause damage.

[0034] During the detection process, the rubber-coated motor roller 9 continues to rotate with the egg. At this time, the output shaft of the drive motor 12 is controlled to rotate, so that the vibration detection rod 14 installed on the roundness detection module moves to the top of the center axis of the egg. The telescopic end of the electric push rod 11 moves downward with the drive motor, and makes the vibration detection rod contact the egg. When the pressure of the pressure sensor at the telescopic end of the electric push rod changes, the electric push rod is powered off, and the roundness detection module obtains the up and down displacement change value of the vibration detection rod and sends it to the roundness calculation unit to calculate the value Q of the egg ellipsoidality.

[0035] The eggs are weighed on a weighing platform 4 to obtain the egg mass M. The current egg density ρ = M / V is further calculated. The initial density ρ0 (i.e., the preset density) and the current egg density ρ are then set based on the egg type, and the egg density loss rate ρ1 is calculated. The initial density can be predetermined for different egg types.

[0036] The property detection module can be set locally or in the cloud. The property detection module receives the multi-angle image data sent by the detection camera 2 to perform three-dimensional reconstruction to calculate the egg volume, and then calculates the density loss rate based on the egg weight data sent by the weighing platform, and receives the upper and lower displacement change value data sent by the roundness detection module 13 to calculate the egg ellipsoidality.

[0037] Egg ellipsoidality is a key factor influencing hatching success rates. Eggs that are closer to a perfect ellipsoid have a higher hatching rate, while eggs with lower or more misshapen ellipsoids have a lower hatching rate. The device of the present invention can collect egg ellipsoidality information during the 3D reconstruction process, thereby simplifying the egg inspection process.

[0038] Finally, the trait output unit of the trait detection module detects egg traits based on the density egg shape index, density loss rate and egg ellipsoidality.

[0039] The nondestructive egg trait testing device of the present invention predicts egg volume through multi-angle image analysis, reducing volume measurement errors and thus improving the accuracy of freshness testing. Furthermore, combined with the egg ellipsoid measurement of a roundness detector, it can promptly detect deformed eggs with low ellipsoidality, facilitating scenarios such as hatching, further improving the reliability of egg trait measurement. Furthermore, the device integrates the testing process, eliminating the need for additional testing procedures and space, thereby comprehensively improving the efficiency of egg trait testing and reducing testing costs.

[0040] In some embodiments, the trait detection module includes: a three-dimensional reconstruction unit, used to acquire images from each detection camera, and perform three-dimensional reconstruction based on each image to calculate the major semiaxis, minor semiaxis, and a third semiaxis perpendicular to the major semiaxis and minor semiaxis of the egg; a volume calculation unit, used to calculate the egg volume based on the major semiaxis, the minor semiaxis, and the third semiaxis; an egg shape index calculation unit, used to calculate the egg shape index based on the major semiaxis and the minor semiaxis; a density calculation unit, used to calculate the current density of the egg based on the egg volume and the egg weight obtained by the weighing platform, and calculate the density loss rate based on the preset density of the egg type and the current density; a roundness calculation unit, used to determine the egg ellipsoidality based on the up and down displacement change value; a trait output unit, used to determine the egg trait based on the density loss rate, egg shape index, and egg ellipsoidality.

[0041] In some embodiments, the egg traits include egg freshness and egg hatching success prediction. Accordingly, the trait detection module is specifically used to: when it is detected that the input egg is for consumption, the density loss rate is input into the trained first detection model, the egg Haugh unit value is output, and the egg freshness is determined based on the Haugh unit value; when it is detected that the input egg is for hatching, the density loss rate, the egg shape index and the egg ellipsoidality are input into the trained second detection model, and the egg hatching success prediction is output; wherein, the first detection model is obtained by training with the density loss rate as input data based on multiple egg samples with known Haugh unit values, and the second detection model is obtained by training with the density loss rate, egg shape index and egg ellipsoidality as input data based on multiple egg samples with known hatching ratios.

[0042] In an embodiment of the present invention, the corresponding egg properties are determined according to different uses such as consumption and hatching, and the use can be input by the user through the human-computer interface. For example, the options are displayed on the touch screen and the user selects, providing the following menu "Please enter the use, A: food; B breeding eggs". When the use is for consumption, the freshness of the egg is judged, and the obtained density loss rate ρ1 is imported into the established first detection model of the density loss rate ρ1 and the Haugh unit HU to calculate the Haugh unit, and the freshness of the egg is judged based on the Haugh unit. When the egg is used for hatching, the second detection model comprehensively considers factors such as the density loss rate, egg shape index and egg ellipsoidality, thereby improving the hatching efficiency and reducing the hatching cost. Among them, the first and second detection models can be established and learned and trained respectively by the current method, such as using a linear regression model and a machine learning model.

[0043] In some embodiments, the device further comprises a display 3 and a human-computer interaction device; the human-computer interaction device is used to receive input of egg usage; and the display 3 is used to display egg properties.

[0044] The human-computer interaction device can be a button or a touch screen. If a touch screen is used, it also serves as display 3. The user can use the human-computer interaction device to input whether the egg is to be eaten or hatched, etc. Display 3 can be installed at the top of the detection box 1 and can achieve wireless communication with the host computer via a built-in Bluetooth communication module.

[0045] In some embodiments, the roundness calculation unit is specifically configured to: determine the maximum minor semi-axis and the minimum third semi-axis based on the vertical displacement change; and determine the egg ellipsoidality based on the ratio of the minimum third semi-axis to the maximum minor semi-axis. Specifically, the egg ellipsoidality value Q = minimum third semi-axis rc / maximum minor semi-axis rb × 100%. The egg center position can be pre-calibrated, and then the vertical displacement change detected by the roundness detection module during the egg rolling process can be used to calculate the maximum minor semi-axis and the minimum third semi-axis.

[0046] In some embodiments, the three detection cameras 2 are respectively located above and on both sides of the egg, so that images can be collected from multiple angles and the surface information of the egg can be captured in all directions, thereby improving the accuracy of calculating the egg volume after three-dimensional reconstruction.

[0047] In some embodiments, a support plate 5 is provided on the upper surface of the weighing platform 4, a light-transmitting hole 6 is opened in the middle of the support plate 5, and an LED white light lamp 7 for fill light is installed in the light-transmitting hole 6; a reflector 10 for focusing light is fixed on the upper surface of the support plate 5, and the reflector 10 is sleeved on the outside of the rubber-coated motor roller 9, and the upper end of the reflector 10 is lower than half of the egg.

[0048] See Figure 4Among them, an LED white light lamp is installed in the light-transmitting hole, and the exposure emitted by the LED white light lamp is used to illuminate the eggs. When the white light illuminates the eggs, the color and external size of the eggs can be fully displayed, which is conducive to the comprehensive detection of egg color, egg shape index, freshness and egg ellipsoidality.

[0049] In some embodiments, two sets of rubber-coated motor rollers 9 are provided, each set of rubber-coated motor rollers 9 being arc-shaped. The two sets of rubber-coated motor rollers 9 are symmetrically arranged on either side of the egg's long axis midline. The two sets of arc-shaped rubber-coated motor rollers 9 are symmetrically arranged on either side of the egg's long axis midline to effectively support the egg during rolling.

[0050] The following describes the non-destructive detection method for egg characteristics provided by the present invention. The non-destructive detection method for egg characteristics described below and the non-destructive detection device for egg characteristics described above can be referenced to each other.

[0051] The present invention provides a method for nondestructive detection of egg properties based on any one of the above-mentioned nondestructive detection devices for egg properties, comprising:

[0052] S1, acquiring an image from each detection camera, and performing three-dimensional reconstruction based on each image to calculate the egg's major semi-axis, minor semi-axis, and a third semi-axis perpendicular to both the major and minor semi-axis;

[0053] S2. Calculating the volume of the egg according to the major semi-axis, the minor semi-axis, and the third semi-axis;

[0054] S3. calculating an egg-shaped index according to the major semi-axis and the minor semi-axis;

[0055] S4, according to the egg product volume and the egg product weight obtained by the weighing platform, calculate the current density of the egg product, and calculate the density loss rate according to the preset density of the egg type and the current density;

[0056] S5, determining the egg ellipsoidality according to the up and down displacement change value;

[0057] S6. Determine egg characteristics according to the density loss rate, egg shape index and egg ellipsoidality.

[0058] In some embodiments, determining the egg traits based on the density loss rate, egg shape index, and egg ellipsoidality comprises:

[0059] When it is detected that the input egg product is for food use, the density loss rate is input into the trained first detection model, a Haugh unit value of the egg product is output, and the freshness of the egg product is determined according to the Haugh unit value;

[0060] When it is detected that the purpose of the input eggs is hatching, the density loss rate, the egg shape index and the egg ellipsoidality are input into the trained second detection model, and a hatching success prediction degree of the eggs is output;

[0061] Among them, the first detection model is obtained after training based on multiple egg samples with known Haugh unit values, using density loss rate as input data; the second detection model is obtained after training based on multiple egg samples with known hatching ratios, using density loss rate, egg shape index and egg ellipsoidality as input data.

[0062] The method embodiments provided in the embodiments of the present invention are implemented through the above-mentioned device embodiments. For specific processes and detailed contents, please refer to the above-mentioned device embodiments, which will not be repeated here.

[0063] The implementation principle and technical effects of the nondestructive egg property testing method provided in the embodiment of the present invention are the same as those of the aforementioned nondestructive egg property testing device embodiment. For the sake of brief description, any matters not mentioned in the embodiment of the nondestructive egg property testing method can be referred to the corresponding content in the aforementioned embodiment of the nondestructive egg property testing device embodiment.

[0064] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0065] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A non-destructive testing device for egg properties, characterized in that: include: A property detection module, a detection box, detection cameras arranged at at least three different angles on the top of the detection box, a weighing platform arranged at the bottom of the detection box, and a roundness detector arranged next to the weighing platform, wherein the roundness detector comprises an elastically retractable electric push rod, a drive motor, a vibration detection rod and a roundness detection module; A bracket is fixed on the weighing platform, and a plurality of rubber-coated motor rollers for driving the eggs to roll around the long axis are installed at the end of the bracket; The roundness detection module is used to collect the up and down displacement change value of the vibration detection rod during the rolling process of the egg after the vibration detection rod moves to the egg height with the electric push rod and rotates to the top parallel to the long axis of the egg with the drive motor; The property detection module is used to perform three-dimensional reconstruction to calculate the egg volume and egg shape index based on the multi-angle images obtained by the detection camera, calculate the density loss rate based on the egg volume and the egg weight obtained by the weighing platform, calculate the egg ellipsoidality based on the up and down displacement change value, and determine the egg property based on the density loss rate, egg shape index and egg ellipsoidality.

2. The nondestructive testing device for egg properties according to claim 1, characterized in that: The trait detection module comprises: A three-dimensional reconstruction unit is used to obtain an image from each detection camera, and perform three-dimensional reconstruction based on each image to calculate the major semi-axis, the minor semi-axis, and the third semi-axis perpendicular to both the major semi-axis and the minor semi-axis of the egg; A volume calculation unit, used for calculating the volume of the egg according to the major semi-axis, the minor semi-axis and the third semi-axis; an egg-shaped index calculation unit, used for calculating the egg-shaped index according to the major semi-axis and the minor semi-axis; A density calculation unit, used to calculate the current density of the egg according to the volume of the egg and the weight of the egg obtained by the weighing platform, and to calculate the density loss rate according to the preset density of the egg type and the current density; A roundness calculation unit, used to determine the egg ellipsoidality according to the up and down displacement change value; The trait output unit is used to determine the egg trait according to the density loss rate, egg shape index and egg ellipsoidality.

3. The nondestructive testing device for egg properties according to claim 1 or 2, characterized in that: The egg properties include egg freshness and egg hatching success prediction. Accordingly, the property detection module is specifically used for: When it is detected that the input egg product is used for food, the density loss rate is input into the trained first detection model, the Haugh unit value of the egg product is output, and the freshness of the egg product is determined according to the Haugh unit value; When it is detected that the purpose of the input eggs is hatching, the density loss rate, the egg shape index and the egg ellipsoidality are input into the trained second detection model, and the hatching success prediction degree of the eggs is output; Among them, the first detection model is obtained after training based on multiple egg samples with known Haugh unit values, using density loss rate as input data, and the second detection model is obtained after training based on multiple egg samples with known hatching ratios, using density loss rate, egg shape index and egg ellipsoidality as input data.

4. The nondestructive testing device for egg properties according to claim 3, characterized in that: It also includes a display, and a human-computer interaction device; The human-computer interaction device is used to receive input of egg usage; The display is used to display egg properties.

5. The nondestructive testing device for egg properties according to claim 2, characterized in that: The roundness calculation unit is specifically used for: Determine the maximum minor semi-axis and the minimum third semi-axis according to the up and down displacement change values; The egg ellipsoidality is determined according to the ratio of the smallest third semi-axis to the largest minor semi-axis.

6. The nondestructive testing device for egg properties according to claim 1, characterized in that: Three detection cameras are located directly above and on both sides of the eggs.

7. The nondestructive testing device for egg properties according to claim 1, characterized in that: A support plate is provided on the upper surface of the weighing platform, a light-transmitting hole is provided in the middle of the support plate, and an LED white light for supplementary lighting is installed in the light-transmitting hole; A reflector for focusing light is fixed on the upper surface of the support plate, and the reflector is sleeved on the outer side of the rubber-coated motor roller, and the upper end of the reflector is lower than one-half of the egg.

8. The nondestructive testing device for egg properties according to claim 1, characterized in that: The rubber-coated motor rollers are provided in two groups, each group of rubber-coated motor rollers is distributed in an arc shape, and the two groups of rubber-coated motor rollers are symmetrically arranged on both sides of the midline of the egg's long axis.

9. A method for nondestructive testing of egg properties based on the nondestructive testing device for egg properties according to any one of claims 1 to 8, characterized in that: include: Acquire an image from each detection camera, and perform three-dimensional reconstruction based on each image to calculate the major semi-axis, the minor semi-axis, and the third semi-axis perpendicular to both the major semi-axis and the minor semi-axis of the egg; Calculate the volume of the egg according to the major semi-axis, the minor semi-axis and the third semi-axis; Calculating an egg-shaped index based on the major semi-axis and the minor semi-axis; Calculate the current density of the eggs according to the volume of the eggs and the weight of the eggs obtained by the weighing table, and calculate the density loss rate according to the preset density of the egg type and the current density; Determine the egg ellipsoidality based on the up and down displacement change value; The egg traits are determined based on the density loss rate, egg shape index and egg ellipsoidality.

10. The method for nondestructive detection of egg properties according to claim 9, characterized in that: Determining egg properties according to the density loss rate, egg shape index and egg ellipsoidality comprises: When it is detected that the input egg product is used for food, the density loss rate is input into the trained first detection model, the Haugh unit value of the egg product is output, and the freshness of the egg product is determined according to the Haugh unit value; When it is detected that the purpose of the input eggs is hatching, the density loss rate, the egg shape index and the egg ellipsoidality are input into the trained second detection model, and the hatching success prediction degree of the eggs is output; Among them, the first detection model is obtained after training based on multiple egg samples with known Haugh unit values, using density loss rate as input data, and the second detection model is obtained after training based on multiple egg samples with known hatching ratios, using density loss rate, egg shape index and egg ellipsoidality as input data.

Images