Apple fruit diameter size grading method and system based on curvature sensor
By installing a curvature sensor on the flexible fingers, the apple fruit diameter is directly measured, which solves the problem of insufficient accuracy of apple grading in the prior art, and achieves high-precision fruit diameter measurement and grading.
Patent Information
- Application Number
- CN202410446644.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-15
- Publication Date
- 2025-08-29
- Estimated Expiration
- 2044-04-15
AI Technical Summary
The prior art is difficult to accurately identify the three-dimensional shape of the apple during the Apple grading process. Especially when the environmental conditions are unstable, the two-dimensional image processing method cannot effectively capture the Apple's overall size, affecting the grading accuracy.
The flexible finger based on the curvature sensor is used to measure the fruit diameter directly by touching the surface of the apple. The curvature sensor is installed on the flexible finger. The data is recorded in combination with the pressure sensor and the microcontroller, and the diameter of the apple is calculated and the accuracy is improved by weighted average.
It significantly improves the accuracy of apple grading, reduces the impact of environmental variables, and achieves high-precision fruit diameter measurement.
Smart Images

Figure CN118168447B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of picking, in particular to the technical field of apple fruit diameter size grading, and specifically refers to an apple fruit diameter size grading method and system based on a curvature sensor. Background Art
[0002] Image processing technology is commonly used to classify apple sizes during apple grading. However, this method relies on stable environmental conditions and struggles to accurately identify the three-dimensional shape of apples, especially when apples obscure each other or cast shadows due to uneven lighting.
[0003] In addition, two-dimensional images make it difficult to capture the full size of the apple, affecting grading accuracy. Summary of the Invention
[0004] In response to the shortcomings of the existing technology, the present invention provides an apple diameter grading method and system based on a curvature sensor. The curvature sensor is installed on a flexible finger. The curvature sensor can directly measure the diameter of the apple by contacting the apple surface, significantly improving the grading accuracy and reducing the impact of environmental variables, thereby improving the accuracy of apple grading.
[0005] The present invention is implemented by the following technical solution: a method for grading apple diameter based on a curvature sensor, comprising the following steps:
[0006] a. Calibrate the curvature sensor and make the resistance value of the curvature sensor correspond to the bending angle of the flexible finger;
[0007] b. Use several flexible fingers, each equipped with a curvature sensor, to hold the apple. The pressure sensor transmits and records the curvature change data to the microcontroller.
[0008] c. Estimate the diameter of the apple by bending the flexible finger into a certain arc and inscribing the imaginary circle of the apple. The formula is:
[0009] ,
[0010] Where D is the diameter of the apple, L is the length of the bent part, and θ is the bending angle of the flexible finger calculated by the curvature sensor;
[0011] d. Calculate the average fruit diameter if each sensor gets a diameter estimate , then the average diameter The weighted average is obtained, and the weight can be distributed according to the symmetry of the curvature sensor position and the shape of the apple. The formula is expressed as:
[0012] ,
[0013] in The weighting coefficient corresponding to the i-th bending sensor, Corresponding to the apple diameter obtained by each sensor.
[0014] When using this solution, a curvature sensor is installed on the flexible finger. The curvature sensor can directly measure the diameter of the apple by contacting the apple surface, significantly improving the grading accuracy and reducing the impact of environmental variables, thereby improving the accuracy of apple grading.
[0015] Preferably, in step a, several cylinders of known and different sizes are taken. During the process of the flexible finger bending to grasp the cylinder, the resistance value of each sensor is recorded when the finger is fully extended and not bent, and when the finger is fully bent and close to the surface of the cylinder. Through a comparison table of resistance value and angle, the resistance value of the curvature sensor is corresponded to the bending angle of the flexible finger.
[0016] When in use, this preferred solution simulates apples of different sizes by using cylinders of different sizes, thereby simulating the grabbing of apples of different sizes.
[0017] Preferably, the system includes a base hingedly connected to a plurality of circumferentially arranged flexible fingers, a drive device mounted on the base that drives the flexible fingers toward the apple, and the curvature sensor disposed on the side of the flexible fingers that contacts the apple. This preferred solution facilitates the flexible mobile phone's ability to grasp an apple through the arrangement of the base and drive device.
[0018] Preferably, the driving device includes a servo arranged corresponding to the flexible finger, a driving gear arranged on the servo output shaft, and a driven gear meshing with the driving gear and arranged on the finger connector, the flexible finger is detachably connected to the finger connector, and the finger connector is hinged to the base.
[0019] When this preferred solution is in use, each flexible finger is moved by a correspondingly arranged servo, so each finger moves independently, which facilitates the individual control of the flexible fingers.
[0020] Preferably, a connecting plate connected to the robotic arm is bolted to the bottom surface of the base. This preferred solution facilitates the use of the robotic arm to drive the flexible fingers to move to the grasping position, thereby improving the degree of mechanization.
[0021] Preferably, the finger connector is connected to the flexible finger via a bolt. This preferred solution facilitates assembly and disassembly of the flexible finger on the base through the provision of the bolt.
[0022] As an advantage, a bottom support for supporting the apple is provided on the top surface of the base. This preferred solution facilitates supporting the apple through the provision of the bottom support.
[0023] The beneficial effects of the present invention are as follows: a curvature sensor is installed on the flexible finger, and the curvature sensor can directly measure the diameter of the apple by contacting the surface of the apple, which significantly improves the accuracy of grading and reduces the impact of environmental variables, thereby improving the accuracy of apple grading; by setting the servo corresponding to the flexible finger, each finger can move independently, which is convenient for realizing the individual control setting of the flexible finger; by setting the connecting plate, it is convenient to use a robot arm to drive the flexible finger to move to the grasping position, thereby improving the mechanization degree of the apple. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a schematic diagram of the structure of the present invention;
[0025] Figure 2 This is a connection diagram of the bending sensor;
[0026] Figure 3 Schematic diagram of the bending sensor calibration:
[0027] Figure 4 This is a schematic diagram of the system when it is moved to the working position;
[0028] Figure 5 This is a schematic diagram of the flexible fingers fully clamping the apple;
[0029] Figure 6 This is a schematic diagram for calculating apple diameter;
[0030] As shown in the figure:
[0031] 1. Bending sensor, 2. Finger connector, 3. Servo, 4. Card slot, 5. Base, 6. Flexible finger, 7. Bottom bracket, 8. Driving gear, 9. Connecting plate, 10. Apple, 11. Collection circuit board, 12. Signal transmission port. DETAILED DESCRIPTION
[0032] In order to clearly illustrate the technical features of this solution, this solution is described below through specific implementation methods.
[0033] Refer to the attached Figure 1-6 The present invention provides an apple diameter grading method and system based on a curvature sensor 1. The system includes a 3D-printed base 5. A screw hole is provided on the bottom surface of the base 5. A bolt threadedly connected to the connecting plate 9 on the robotic arm is connected in the screw hole. The base 5 also has four slots 4 for accommodating a servo 3. The four slots 4 are evenly arranged along the circumference.
[0034] The base 5 is hingedly connected to a finger connector 2 corresponding to the card slot 4 through a hinge shaft. The finger connector 2 is detachably connected to the flexible fingers 6 extending upward through bolts. The four flexible fingers 6 are evenly arranged along the circumference. A driving gear 8 is provided on the output shaft of the servo 3. The driving gear 8 is engaged with a driven gear fixed to the hinge shaft, and the hinge shaft is fixed to the finger connector 2.
[0035] A bottom support 7 for supporting the apple is provided on the top surface of the base 5 .
[0036] The bend sensor 1 is located on the inner side of the flexible finger 6, that is, the side of the flexible finger 6 that contacts the apple. A bend sensor is a device that measures bend angle or deflection. Typically, a flex sensor consists of a variable resistor, which is coated on the surface of the flex sensor and responds to bending. Different bend angles change the sensor's resistance value, and the bend angle can be determined based on this change in resistance. The bend sensor 1 is connected to a data acquisition circuit board, which is equipped with a signal transmission port.
[0037] In particular, the side of the flexible finger 6 that contacts the clamped object can be selected according to the actual shape of the clamped object, for example, Figure 4 and 5 In the example, when grabbing an apple, the corresponding surface can be either a plane or a curved surface that fits the apple.
[0038] A method for grading apple diameter based on a curvature sensor comprises the following steps:
[0039] a. Calibrate the bend sensor. First, use a cylinder to simulate an apple. Take several cylinders of varying known dimensions. As the flexible finger bends to grasp the cylinder, record the resistance of each sensor when the finger is fully extended (not bent) and fully bent (close to the cylinder). Use a resistance-angle comparison table to map the resistance of the bend sensor to the bending angle of the flexible finger.
[0040] b. Connect the base to the output end of the robotic arm through the connecting plate, use the computer to control the robotic arm, and slowly control the robotic arm to move to the working position;
[0041] c. Drive the servos, which drive the finger connectors to rotate through the driving and driven gears, thereby achieving the rotation of the flexible fingers. By controlling the four servos to rotate to corresponding angles, the four flexible fingers are controlled to clamp the apple. At this time, the four servos stop running, and the pressure sensors on the fingers sense the change in bending and record it in the microcontroller;
[0042] d. Estimate the diameter of the apple by using the imaginary circle inscribed in the apple when the flexible finger is bent into a certain arc. The formula is:
[0043] ,
[0044] Where D is the diameter of the apple, L is the length of the curved portion, i.e., the portion covered by the curvature sensor, and θ is the angle of the flexible finger bending calculated by the curvature sensor.
[0045] e. Calculate the average fruit diameter if each sensor gets a diameter estimate. , then the average diameter The weighted average is obtained, and the weight can be distributed according to the symmetry of the curvature sensor position and the shape of the apple. The formula is expressed as:
[0046] ,
[0047] in The weighting coefficient corresponding to the i-th bending sensor, Corresponding to the apple diameter obtained by each sensor.
[0048] Of course, the above description is not limited to the above examples. Technical features not described in the present invention can be achieved by or by adopting existing technologies, which will not be described here. The above embodiments and drawings are only used to illustrate the technical solutions of the present invention and are not limitations of the present invention. The present invention is described in detail with reference to the preferred implementation methods. Ordinary technicians in this field should understand that changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention do not depart from the purpose of the present invention and should also fall within the scope of protection of the claims of the present invention.
Claims
1. A method for grading apple fruit diameter based on a curvature sensor, characterized in that: The following steps are involved: a. Calibrate the curvature sensor and make the resistance value of the curvature sensor correspond to the bending angle of the flexible finger; b. Use several flexible fingers, each equipped with a curvature sensor, to hold the apple. The pressure sensor transmits and records the curvature change data to the microcontroller. c. Estimate the diameter of the apple by bending the flexible finger into a certain arc and inscribing the imaginary circle of the apple. The formula is: Where D is the diameter of the apple, L is the length of the bent part, and θ is the bending angle of the flexible finger calculated by the curvature sensor; d. Calculate the average fruit diameter. If each sensor obtains an estimated diameter value D i , then the average diameter D avg The weighted average is obtained, and the weight can be distributed according to the symmetry of the curvature sensor position and the shape of the apple. The formula is expressed as: where a i The weighting coefficient corresponding to the i-th bending sensor, D i Corresponding to the apple diameter obtained by each sensor.
2. The apple diameter grading method based on a curvature sensor according to claim 1, characterized in that: In step a, several cylinders of known and different sizes are taken. When the flexible finger bends to grasp the cylinder, the resistance value of each sensor is recorded when it is fully extended, that is, when the finger is not bent, and when it is fully bent, that is, when the finger is close to the surface of the cylinder. Through the resistance value and angle comparison table, the resistance value of the bending sensor is corresponded to the bending angle of the flexible finger.
3. The system for apple diameter grading based on curvature sensor according to claim 1 or 2, characterized in that: The invention comprises a base (5) hinged to a plurality of circumferentially arranged flexible fingers (6), a driving device arranged on the base (5) and driving the flexible fingers (6) to push against an apple, and the curvature sensor (1) is arranged on the side of the flexible fingers (6) in contact with the apple.
4. The system for apple diameter grading based on curvature sensor according to claim 3, characterized in that: The driving device comprises a steering gear (3) arranged corresponding to the flexible finger (6), a driving gear (8) arranged on the steering gear output shaft, and a driven gear meshing with the driving gear (8) and arranged on a finger connector (2); the flexible finger (6) is detachably connected to the finger connector (2), and the finger connector (2) is hinged to the base (5).
5. The system for apple diameter grading based on curvature sensor according to claim 3, characterized in that: A connecting plate (9) connected to the mechanical arm is bolted to the bottom surface of the base (5).
6. The system for apple diameter grading based on curvature sensor according to claim 4, characterized in that: The finger connector (2) is connected to the flexible finger (6) via a bolt.
7. The system for apple diameter grading based on curvature sensor according to claim 3, characterized in that: A bottom support (7) for supporting the apple is provided on the top surface of the base (5).
Citation Information
Patent Citations
Intelligent apple picking and sorting machine and picking method thereof
CN113245236A
Curvature measuring system and method for flexible mechanical claw
CN116678307A