Fruit picking data detection device

Abstract

The invention discloses a fruit picking data detection device, and relates to the technical field of fruit picking, the fruit picking data detection device comprises a measuring device and an upper computer, the measuring device comprises a data acquisition module and a central processing module, and the measuring device is arranged at a target position on a fruit tree; the data acquisition module is used for acquiring motion data of the measuring device in real time in the fruit picking process and sending the motion data to the central processing module; the central processing module is used for obtaining the position and the posture of the measuring device in real time by adopting a posture recognition and trajectory tracking model according to the motion data collected in real time, and sending the position and the posture of the measuring device to the upper computer in real time; the upper computer is in wireless communication connection with the central processing module; the motion data, the position and the posture of the measuring device are used as the motion data, the position and the posture in the fruit picking process, and real-time collection and monitoring of the fruit motion data in the fruit vibration picking process can be achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fruit picking, in particular to a fruit picking data detection device. BACKGROUND

[0002] With the development of agricultural automation, large-scale and mechanized harvesting is widely used in the harvesting process of agricultural and forestry fruits. The labor efficiency is greatly improved and the labor intensity is reduced, which is the prominent feature of mechanization in crop picking and harvesting process. However, there is still the problem of incomplete fruit picking, for example, the picking rate of oil tea fruit side branch clamping vibration picking equipment is 84.92%, and the flower bud damage rate is 4.27%. And during the whole mechanical picking and harvesting period, the mechanical load produces great mechanical impact on the target fruit (especially the perishable fruit), which reduces the fruit quality and thus the economic benefit. For example, nearly 78% of blueberries are mechanically damaged after being harvested by the harvester, losing economic benefits.

[0003] Although the current electronic fruit can detect the vibration impact on the fruit, it cannot detect the motion of the fruit in the actual picking process in real time on the spot, so it cannot evaluate the real-time motion trajectory and collision situation of the fruit when it is excited. It is necessary to store the data in the SD card and then upload it to the data analysis system, which not only reduces the efficiency of data analysis, but also reduces the timeliness of the data, and cannot grasp the real-time dynamic information on the spot in time. SUMMARY

[0004] The purpose of the present application is to provide a fruit picking data detection device, which can realize real-time collection and monitoring of fruit motion data during fruit vibration picking.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] The present application provides a fruit picking data detection device, which comprises a measuring device and an upper computer, the measuring device comprises a data acquisition module and a central processing module, and the measuring device is arranged at a target position on a fruit tree;

[0007] The data acquisition module is used for collecting the motion data of the measuring device in real time during fruit picking, and sending the motion data to the central processing module;

[0008] The central processing module is used for obtaining the position and attitude of the measuring device in real time according to the real-time collected motion data, adopting a posture recognition and trajectory tracking model, and sending the position and attitude of the measuring device to the upper computer in real time; and the upper computer is in wireless communication connection with the central processing module;

[0009] The host computer is used to receive the motion data, position and attitude of the measuring device in real time, and use the motion data, position and attitude of the measuring device as the motion data, position and attitude during the fruit picking process.

[0010] Optionally, the motion data includes acceleration, angular velocity, and distance, wherein the distance is the distance between the measuring device and the positioning beacon;

[0011] The data acquisition module includes a detection module and a distance measurement module;

[0012] The detection module is used to collect the acceleration and angular velocity of the measuring device, and the distance measurement module is used to collect the distance of the measuring device.

[0013] Optionally, the pose recognition and trajectory tracking model is obtained by training a neural network model using a training set;

[0014] Training a neural network model using a training set specifically includes:

[0015] Collect motion sample data within a set time period; the motion sample data includes the acceleration, angular velocity, and distance of the measuring device, wherein the distance is the distance between the measuring device and the positioning beacon;

[0016] The motion sample data was cleaned using a Butterworth filter;

[0017] Position and pose are calculated based on the cleaned motion sample data.

[0018] The absolute median difference method is used to identify outliers in the calculated position and pose, and the Winsorization method is used to replace the identified outliers to obtain the valid position and pose.

[0019] The motion sample data after data cleaning within each time step is used as input, and the effective position and pose are used as label data to train the neural network model, thereby obtaining the posture recognition and trajectory tracking model.

[0020] Optionally, position and pose calculations are performed based on the cleaned motion sample data, specifically including:

[0021] The acceleration and angular velocity data are fused to obtain the attitude of the measuring device at each moment, and the attitude is represented by an attitude quaternion.

[0022] The position of the measuring device at each moment is obtained by fusing the acceleration, angular velocity and distance data.

[0023] Optionally, the neural network model employs a long short-term memory network.

[0024] Optionally, the fruit picking data detection device further includes a wireless transmission module and an ISP serial port module. The wireless transmission module is integrated into the central processing module and is used for wireless communication between the central processing module and the host computer. The ISP serial port module is connected to the central processing module and is used for wired communication between the central processing module and the host computer.

[0025] Optionally, the detection module includes an acceleration detection module and an angular velocity detection module; the acceleration detection module is used to acquire the acceleration of the measuring device, and the angular velocity detection module is used to acquire the angular velocity of the measuring device.

[0026] The central processing module is also used to correct the acceleration detection module using a first error model and to correct the angular velocity detection module using a second error model.

[0027] The first error model is expressed as: a m = (I+M) a +S a (a) t +g)+b a +n a ;

[0028] The second error model is expressed as: ω m = (I+M) ω +S ω )ω t +b ω +n ω ;

[0029] Among them, a m For acceleration measurements, a t Let I be the true value of acceleration, and ω be the identity matrix. m ω is the measured value of angular velocity. t M is the true value of angular velocity. a and M ω Both are cross-axis coupling error matrices, S a and S ω Both are scale factor error matrices, where g is the gravitational acceleration vector, and b a and b ω All are zero bias values, n a and n ω All of these are random errors.

[0030] Optionally, the central processing module comprises a main processing chip U1, a capacitor C1 and a reset circuit, the reset circuit comprises a resistor R1, a capacitor C2 and a reset switch S1; one end of the resistor R1 is connected with a first power voltage, the other end of the resistor R1, one end of the reset switch S1 and one end of the capacitor C2 are all connected with a reset pin of the main processing chip U1, the other end of the reset switch S1 and the other end of the capacitor C2 are all grounded, a reference voltage external input pin of the main processing chip U1 and one end of the capacitor C1 are all connected with the first power voltage; the other end of the capacitor C1 and a ground pin of the main processing chip U1 are all grounded.

[0031] The main processing chip U1 is a dual-core 32-bit ARM single-chip microcomputer.

[0032] Optionally, the detection module comprises a detection chip U2, a resistor R2, a resistor R3, a resistor R4, a resistor R5, a capacitor C3 and a capacitor C4, an I / O power input pin of the detection chip U2 and one end of the capacitor C3 are connected with a second power voltage, the other end of the capacitor C3 is grounded, an address selection pin of the detection chip U2 is connected with one end pin of the resistor R2, the other end of the resistor R2 is grounded, a function synchronization pin of the detection chip U2 is connected with one end of the resistor R3, the other end of the resistor R3 is grounded, a power input pin of the detection chip U2 is connected with one end of the capacitor C4, the other end of the capacitor C4 is grounded, an analog interrupt pin of the detection chip U2 is connected with a first interrupt pin of the main processing chip U1, an IIC serial clock pin of the detection chip U2 is connected with an IIC serial clock pin of the main processing chip U1 and one end of the resistor R4 respectively, the other end of the resistor R4 is connected with the first power voltage, an IIC serial data input pin of the detection chip U2 is connected with an IIC serial data input pin of the main processing chip U1 and one end of the resistor R5 respectively, the other end of the resistor R5 is connected with the first power voltage.

[0033] Optionally, the distance measurement module comprises a wireless carrier communication chip U3, a quartz crystal resonator Y1, a resistor R6, a capacitor C5, a capacitor C6, a capacitor C7, a capacitor C8, a capacitor C9, a capacitor C10, a capacitor C11, a capacitor C12, a capacitor C13, a capacitor C14, a capacitor C15, a capacitor C16, a filter FB1 and an antenna W1.

[0034] The first power input pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C5, and the other end of the capacitor C5 is grounded; the second power input pin of the wireless carrier communication chip U3 is connected with one end of the filter FB1 and one end of the capacitor C6 respectively, the other end of the filter FB1 is connected with the first power voltage, and the other end of the capacitor C6 is grounded; the third power input pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C7, one end of the capacitor C8 and one end of the capacitor C9 respectively, the other end of the capacitor C7, the other end of the capacitor C8 and the other end of the capacitor C9 are all grounded; the fourth power input pin of the wireless carrier communication chip U3, one end of the capacitor C10, one end of the capacitor C11, one end of the capacitor C12 and one end of the capacitor C13 are all connected with the first power voltage, the other end of the capacitor C10, the other end of the capacitor C11, the other end of the capacitor C12 and the other end of the capacitor C13 are all grounded; the first antenna pin of the wireless carrier communication chip U3 is connected with one end of the resistor R6, and the other end of the resistor R6 is grounded; the second antenna pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C14, and the other end of the capacitor C14 is connected with the antenna W1; the analog interrupt pin of the wireless carrier communication chip U3 is connected with the second interrupt pin of the main control chip U1; the first grounding pin, the second grounding pin, the third grounding pin and the fourth grounding pin of the wireless carrier communication chip U3 are all grounded after being connected; the crystal input pin of the wireless carrier communication chip U3 is connected with the No.1 pin of the quartz crystal resonator Y1; the crystal output pin of the wireless carrier communication chip U3 is connected with the No.3 pin of the quartz crystal resonator Y1; the SPI clock pin of the wireless carrier communication chip U3 is connected with the clock pin of the main control chip U1; the SPI output pin of the wireless carrier communication chip U3 is connected with the first host SPI host output pin of the main control chip U1; the SPI input pin of the wireless carrier communication chip U3 is connected with the first host SPI host input pin of the main control chip U1; the chip selection pin of the wireless carrier communication chip U3 is connected with the SPI master-slave common selection pin of the main control chip U1; wherein the first pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C15, the other end of the capacitor C15 is connected with the No.2 pin of the quartz crystal resonator Y1 after being grounded; the No.4 pin of the quartz crystal resonator Y1 is grounded; the No.3 pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C16, and the other end of the capacitor C16 is grounded.

[0035] According to the specific embodiments provided in the application, the following technical effects are disclosed:

[0036] The application provides a fruit picking data detection device, which realizes real-time collection of motion data of a measuring device arranged at a target position of a fruit tree, adopts a posture recognition and track tracking model to obtain the position and posture of the measuring device in real time, and sends the obtained motion data, position and posture to an upper computer through wireless communication by a central processing module, so that the upper computer obtains the real-time motion data, position and posture in the fruit picking process, and realizes real-time collection and monitoring of fruit motion data in the fruit vibration picking process. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0038] Figure 1 A structural schematic diagram of a fruit picking data detection device provided by an embodiment of the present application;

[0039] Figure 2 A structural schematic diagram of a central processing module provided by an embodiment of the present application;

[0040] Figure 3 A structural schematic diagram of a reset circuit in the central processing module provided by an embodiment of the present application;

[0041] Figure 4 A structural schematic diagram of a distance measuring module in a data acquisition module provided by an embodiment of the present application;

[0042] Figure 5 A connection structural schematic diagram of a quartz crystal resonator Y1 in a data acquisition module provided by an embodiment of the present application;

[0043] Figure 6 A connection structural schematic diagram of a detection chip U2 in a data acquisition module provided by an embodiment of the present application;

[0044] Figure 7 A data storage module provided by an embodiment of the present application;

[0045] Figure 8 A connection structural schematic diagram of a connector base J1 in an ISP serial port module provided by an embodiment of the present application;

[0046] Figure 9 A connection structural schematic diagram of a serial port chip U4 in an ISP serial port module provided by an embodiment of the present application;

[0047] Figure 10Figure 1 is a schematic diagram of a connection structure of a charging management chip U5 in a power management module according to an embodiment of the present application;

[0048] Figure 11 Figure 2 is a schematic diagram of a connection structure of a linear voltage regulator chip U6 in the power management module according to an embodiment of the present application;

[0049] Figure 12 Figure 3 is a schematic diagram of a connection structure of a linear voltage regulator chip U7 in the power management module according to an embodiment of the present application;

[0050] Figure 13 Figure 4 is a schematic diagram of a work flow according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0052] The above-mentioned purposes, features and advantages of the present application can be more obvious and easy to understand. The present application will be described in further detail below with reference to the drawings and specific embodiments.

[0053] In an exemplary embodiment, the present application provides a fruit picking data detection device, as shown in the figure. Figure 1 The fruit picking data detection device comprises a measurement device and a host computer. The measurement device comprises a data acquisition module and a central processing module. The measurement device is arranged at a target position on a fruit tree.

[0054] The data acquisition module is configured to acquire motion data of the measurement device in real time during fruit picking, and send the motion data to the central processing module.

[0055] The central processing module is configured to obtain the position and posture of the measurement device in real time according to the real-time acquired motion data, using a posture recognition and trajectory tracking model, and send the position and posture of the measurement device to the host computer in real time. The host computer is in wireless communication connection with the central processing module.

[0056] The host computer is configured to receive the motion data, position and posture of the measurement device in real time, and take the motion data, position and posture of the measurement device as the motion data, position and posture in the fruit picking process.

[0057] The application acquires motion data of the measuring device in real time through the measuring device arranged at the target position of the fruit tree, obtains the position and posture of the measuring device in real time by adopting a posture recognition and trajectory tracking model, and sends the motion data, position and posture obtained in real time to the host computer through wireless communication by the central processing module, so that the host computer obtains the motion data, position and posture in real time during the fruit picking process, and realizes real-time acquisition and monitoring of the fruit motion data during the fruit vibration picking process.

[0058] In an exemplary embodiment, the fruit picking data detection device further comprises a power management module, a data storage module, a wireless transmission module and an ISP serial port module, the wireless transmission module is integrated into the central processing module, and the wireless transmission module is used for wireless communication between the central processing module and the host computer; the ISP serial port module is connected with the central processing module, and the ISP serial port module is used for wired communication between the central processing module and the host computer.

[0059] The data storage module is used for storing the acceleration, angular velocity and distance processed by the central processing module.

[0060] The detection module comprises an acceleration detection module and an angular velocity detection module; the acceleration detection module is used for acquiring the acceleration of the measuring device, and the angular velocity detection module is used for acquiring the angular velocity of the measuring device.

[0061] The central processing module is connected with the angular velocity detection module and the acceleration detection module in the data acquisition module through an IIC interface, and the central processing module is connected with the distance measuring module through an SPI interface. The central processing module is integrated with a posture solving and trajectory solving program. The power management module provides working voltage for the whole system, that is, the power management module provides working voltage for the central processing module, the data acquisition module and the data storage module. The fruit picking data detection device has the advantages of simple structure, stable and reliable work, low price, portability, low requirement for professional technology and facilitation of popularization; the fruit picking data detection device can realize real-time transmission of the motion posture, motion trajectory and vibration signal of the fruit in the fruit and vegetable vibration picking process through a wireless network, and facilitate real-time monitoring of the fruit and vegetable vibration.

[0062] The fruit picking data detection device records the impact, motion trajectory after vibration and posture change after vibration of the fruit by using the picking device to excite the tree body, solves the problem that the motion of the electronic fruit in the picking process cannot be detected in real time in the prior art, can effectively replace the use of a high-speed camera, not only saves a large amount of cost but also greatly improves the portability of the equipment, facilitates the implementation and popularization of the project, solves the problem of low data timeliness and can realize remote technical support of professional technicians on the scene in time.

[0063] The real-time obtained motion data, position and pose are used for optimizing the picking parameters of the fruit picking device, improving the fruit picking rate and reducing the fruit damage rate.

[0064] The fruit picking data detection device comprises a shell, a central processing module, a data acquisition module, a power management module, a data storage module, a wireless transmission module and an ISP serial port module installed in the shell.

[0065] In an exemplary embodiment, the motion data comprises acceleration, angular velocity and distance, and the distance is the distance between the measuring device and the positioning beacon.

[0066] The data acquisition module comprises a detection module and a distance measurement module.

[0067] The detection module is used for acquiring the acceleration and angular velocity of the measuring device, and the distance measurement module is used for acquiring the distance of the measuring device.

[0068] In an exemplary embodiment, the pose recognition and trajectory tracking model is obtained by training a neural network model using a training set. The pose recognition and trajectory tracking model comprises at least one trained neural network model.

[0069] The neural network model is trained using a training set, specifically comprising:

[0070] (1) collecting motion sample data in a set time period; the motion sample data comprises acceleration, angular velocity and distance of the measuring device, and the distance is the distance between the measuring device and the positioning beacon.

[0071] (2) performing data cleaning on the motion sample data using a Butterworth filter.

[0072] (3) performing position and pose calculation according to the motion sample data after data cleaning.

[0073] (4) identifying outliers of the calculated position and pose using the absolute median deviation method (MAD), and replacing the identified outliers using the Winsorization method to obtain effective position and pose.

[0074] (5) training the neural network model using the motion sample data after data cleaning in each time step as input and the effective position and pose as label data (output data), to obtain the pose recognition and trajectory tracking model.

[0075] In an exemplary embodiment, the position and pose calculation according to the motion sample data after data cleaning specifically comprises:

[0076] The acceleration and the angular velocity are data fused to obtain the attitude of the measuring device at each moment, and the attitude is represented by an attitude quaternion.

[0077] The acceleration, the angular velocity and the distance are data fused to obtain the position of the measuring device at each moment.

[0078] In an exemplary embodiment, the neural network model employs a Long Short-Term Memory (LSTM) network.

[0079] The acceleration detection module of the application can detect the impact of the fruit in the vibration state, the angular velocity detection module can detect the angular velocity change of the fruit in the vibration state, and the acceleration and the angular velocity are data fused through the LSTM network to calculate the attitude change and the trajectory change of the fruit in the vibration state. Thus, the motion mode of the fruit in the actual external vibration state is obtained, and it is further known that which motion trajectory can better realize fruit harvesting, and the picking parameters of the picking machine are optimized. The real-time attitude and trajectory calculated can replace the use function of the traditional high-speed camera, which not only greatly reduces the cost and greatly increases the portability, but also facilitates the real-time and popularization of the project.

[0080] Through wireless transmission technology, the data can be remotely and real-timely transmitted, which is beneficial to the real-time detection of the data of the fruit vibration picking and improves the timeliness of the data and facilitates the remote technical support of the technicians on the site.

[0081] The device of the application has the advantages of simple structure, stable and reliable work, low price, portability, low requirement for professional technology, and facilitation of popularization.

[0082] In an exemplary embodiment, as shown in Figure 2 and Figure 3 The central processing module includes a main processing chip U1, a capacitor C1 and a reset circuit, the reset circuit includes a resistor R1, a capacitor C2 and a reset switch S1; one end of the resistor R1 is connected with a first power voltage, the other end of the resistor R1, one end of the reset switch S1 and one end of the capacitor C2 are all connected with a reset pin of the main processing chip U1, the other end of the reset switch S1 and the other end of the capacitor C2 are all grounded, an external input pin of a reference voltage of the main processing chip U1 and one end of the capacitor C1 are all connected with the first power voltage; the other end of the capacitor C1 and a grounding pin of the main processing chip U1 are all grounded.

[0083] The first power voltage is provided by a power management module.

[0084] The main processing chip U1 is a dual-core 32-bit ARM single-chip microcomputer. The dual-core 32-bit ARM single-chip microcomputer is used as a central processing system to quickly process data information. The application can record acceleration data, angular velocity data, attitude data, and trajectory data of fruit vibration in real time.

[0085] The product model of the main processing chip U1 is ESP32-WROOM-32E-N4 of Shanghai Espressif Information Technology Co., Ltd.

[0086] In an exemplary embodiment, as shown in Figure 6 The detection module includes a detection chip U2, resistors R2, R3, R4, R5, a capacitor C3, and a capacitor C4. The I / O power supply input pin VDDIO, the first reserved unused pin RESV, the chip select pin nCS, and one end of the capacitor C3 of the detection chip U2 are connected to the second power supply voltage. The other end of the capacitor C3 is grounded. The address selection pin AD0 / SDO of the detection chip U2 is connected to one end of the resistor R2. The other end of the resistor R2 is grounded. The function synchronization pin FSYNC of the detection chip U2 is connected to one end of the resistor R3. The other end of the resistor R3 is grounded. The power supply input pin VDD of the detection chip U2 is connected to one end of the capacitor C4. The other end of the capacitor C4 is grounded. The analog interrupt pin INT of the detection chip U2 is connected to the first interrupt pin GPIO34 of the main processing chip U1. The IIC serial clock pin SDA / SDI of the detection chip U2 is connected to the IIC serial clock pin IO21 of the main processing chip U1 and one end of the resistor R4. The other end of the resistor R4 is connected to the first power supply voltage. The IIC serial data input pin SCL / SCLK of the detection chip U2 is connected to the IIC serial data input pin IO22 of the main processing chip U1 and one end of the resistor R5. The other end of the resistor R5 is connected to the first power supply voltage. The second reserved unused pin RESV of the detection chip U2 is connected to the ground pin.

[0087] The detection chip U2 is used to realize acceleration detection and angular velocity detection. The detection chip U2 can use the product of model MPU9250 of TDKInvenSense Company.

[0088] The second power supply voltage is provided by the power management module.

[0089] In an exemplary embodiment, as shown in Figure 4 and Figure 5As shown, the distance measurement module includes a wireless carrier communication chip U3, a quartz crystal resonator Y1, a resistor R6, a capacitor C5, a capacitor C6, a capacitor C7, a capacitor C8, a capacitor C9, a capacitor C10, a capacitor C11, a capacitor C12, a capacitor C13, a capacitor C14, a capacitor C15, a capacitor C16, a filter FB1, and an antenna W1.

[0090] The first power input pin VDD1 of the wireless carrier communication chip U3 is connected with one end of the capacitor C5, and the other end of the capacitor C5 is grounded; the second power input pin VDD2a of the wireless carrier communication chip U3 is connected with one end of the filter FB1 and one end of the capacitor C6 respectively, the other end of the filter FB1 is connected with the first power voltage, and the other end of the capacitor C6 is grounded; the third power input pin VDD2b of the wireless carrier communication chip U3 is connected with one end of the capacitor C7, the capacitor C8 and the capacitor C9 respectively, and the other end of the capacitor C7, the other end of the capacitor C8 and the other end of the capacitor C9 are all grounded; the fourth power input pin VDD3 of the wireless carrier communication chip U3, the capacitor C10, the capacitor C11, the capacitor C12 and the capacitor C13 are all connected with the first power voltage, and the other end of the capacitor C10, the other end of the capacitor C11, the other end of the capacitor C12 and the other end of the capacitor C13 are all grounded; the first antenna pin RF2 of the wireless carrier communication chip U3 is connected with one end of the resistor R6, and the other end of the resistor R6 is grounded; the second antenna pin RF1 of the wireless carrier communication chip U3 is connected with one end of the capacitor C14, and the other end of the capacitor C14 is connected with the antenna W1; the analog interrupt pin IRQ of the wireless carrier communication chip U3 is connected with the second interrupt pin GPIO4 of the main control chip U1; the first grounding pin GND, the second grounding pin GND, the third grounding pin GND and the fourth grounding pin GND of the wireless carrier communication chip U3 are all grounded after being connected; the crystal input pin XTO of the wireless carrier communication chip U3 is connected with the No.1 pin of the quartz crystal resonator Y1; the crystal output pin XTI of the wireless carrier communication chip U3 is connected with the No.3 pin of the quartz crystal resonator Y1; the SPI clock pin SPICK of the wireless carrier communication chip U3 is connected with the clock pin GPIO14 of the main control chip U1; the SPI output pin SPIMISO of the wireless carrier communication chip U3 is connected with the first host SPI host output pin GPIO12 of the main control chip U1; the SPI input pin SPIMOSI of the wireless carrier communication chip U3 is connected with the first host SPI host input GPIO13 pin of the main control chip U1; the chip selection pin SPICSn of the wireless carrier communication chip U3 is connected with the SPI master-slave common selection pin GPIO15 of the main control chip U1; wherein the No.1 pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C15, the other end of the capacitor C15 is connected with the No.2 pin of the quartz crystal resonator Y1 after being grounded; the No.4 pin of the quartz crystal resonator Y1 is grounded; the No.3 pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C16, and the other end of the capacitor C16 is grounded.

[0091] The wireless carrier communication chip U3 can adopt the product of DW3110TR13 model of Qorvo company.

[0092] In one exemplary embodiment, as shown in Figure 7 The data storage module includes a storage chip F1, a resistor R7 and a resistor R8; wherein the power input pin VCC of the storage chip F1 is connected with the first power voltage; the chip select pin CS# of the storage chip F1 is connected with the SPI master-slave common selection pin 5 of the main control chip U1; the data output pin DO of the storage chip F1 is connected with the second host SPI host output pin GPIO19 of the main control chip U1; the input pin DI of the storage chip F1 is connected with the second host SPI host input pin GPIO23 of the main control chip U1; the serial clock pin CLK of the storage chip F1 is connected with the clock pin GPIO18 of the main control chip U1; the write protection pin IO2 of the storage chip F1 is connected with one end of the resistor R7, and the other end of the resistor R7 is connected with the first power voltage; the hold or reset input pin IO3 of the storage chip F1 is connected with one end of the resistor R8; the other end of the resistor R8 is connected with the first power voltage; and the ground pin GND of the storage chip F1 is grounded.

[0093] The storage chip F1 can adopt the product of W25Q128JVSIQ model of WINBOND company.

[0094] In one exemplary embodiment, as shown in Figure 8 and Figure 9As shown, the ISP serial port module includes connector base J1, serial port chip U4, capacitor C17, resistor R9, resistor R10, resistor R11, LED lamp L1; wherein the first power input pin VBUS of connector base J1, the second power input pin VBUS of connector base J1, the third power input pin VBUS of connector base J1 are connected with the upper computer; the fourth power input pin VBUS of connector base J1 is connected with one end of resistor R9 and the upper computer, the other end of resistor R9 is connected with one end of LED lamp; the other end of LED lamp L1 is grounded; the first initial mode recognition pin of connector base J1 is connected with one end of resistor R10; the second initial mode recognition pin CC1 of connector base J1 is connected with one end of resistor R11; the ground pin GND of connector base J1, the other end of resistor R10, the other end of resistor R11 and the shell fixing pin SH of connector base J1 are connected and grounded; wherein the first pin UD+ of serial port chip U4 is connected with the positive differential pin DP1 of connector base J1; the second pin UD- of serial port chip U4 is connected with the negative differential pin DN1 of connector base J1; the third pin GND of serial port chip U4 is grounded; the fifth pin V3 of serial port chip U4 is connected with one end of capacitor C17, the other end of capacitor C17 is grounded; the sixth pin RXD of serial port chip U4 is connected with the data transmission pin TXD0 of main processing chip U1; the seventh pin TXD of serial port chip U4 is connected with the data reception pin RXD0 of main processing chip U1; the eighth pin VCC of serial port chip U4 is connected with the first power voltage. The pin VBUS is provided with 5-volt voltage by the upper computer.

[0095] Connector base J1 can adopt the product of TYPE-C-31-M-12 model of Hanrong Electronics Company. Serial port chip U4 can adopt the product of CH340N model of Nanjing Qinheng Microelectronics Company.

[0096] In an exemplary embodiment, as shown, Figure 10- Figure 12 the power management module includes charging management chip U5, linear voltage regulator chip U6, linear voltage regulator chip U7, resistor R12, resistor R13, resistor R14, battery B1, LED lamp L2, LED lamp L3, capacitor C18, capacitor C19, capacitor C20, capacitor C21, capacitor C22, capacitor C23 and capacitor C24.

[0097] The temperature detection pin TEMP of the charging management chip U5 is grounded; the charging current setting pin PROG of the charging management chip U5 is connected with one end of the resistor R12, and the other end of the resistor R12 is grounded; the grounding pin GND of the charging management chip U5 is grounded; the power input pin VCC of the charging management chip U5 is connected with the power input pin of the connector base J1; the enable input pin CE of the charging management chip U5 is connected with the power input pin of the connector base J1; the charging indication pin CHRG of the charging management chip U5 is connected with one end of the resistor R13, and the other end of the resistor R13 is connected with one end of the LED lamp L2, and the other end of the LED lamp L2 is connected with the power input pin of the connector base J1; the charging indication completion pin STDBY of the charging management chip U5 is connected with one end of the resistor R14, and the other end of the resistor R14 is connected with one end of the LED lamp L3, and the other end of the LED lamp L3 is connected with the power input pin of the connector base J1; the battery pin BAT of the charging management chip U5 is connected with the positive electrode of the battery B1, and the negative electrode of the battery B1 is grounded.

[0098] The input pin IN of the linear voltage regulator chip U6 is connected with one end of the capacitor C18 and one end of the capacitor C19 and connected with the battery pin BAT of the charging management chip U5; the output pin OUT of the linear voltage regulator chip U6 is connected with one end of the capacitor C20 and one end of the capacitor C21 and then outputs a 3.3-volt voltage, that is, a first power voltage; the other end of the capacitor C18, the other end of the capacitor C19, the other end of the capacitor C20 and the other end of the capacitor C21 are connected with the grounding pin GND of the linear voltage regulator chip U6 and then grounded.

[0099] The enable pin EN of the linear voltage regulator chip U7 is connected with the signal control pin GPIO25 of the main processing chip U1; the noise reduction pin NR of the linear voltage regulator chip U7 is connected with one end of the capacitor C22, and the other end of the capacitor C22 is grounded; the capacitor input pin IN of the linear voltage regulator chip U7 is connected with one end of the capacitor C23 and connected with the output pin OUT of the linear voltage regulator chip U6; the other end of the capacitor C23 is grounded; the tenth nominal voltage output pin OPV4 of the linear voltage regulator chip U7 is connected with the grounding pin GND of the linear voltage regulator chip U7 and grounded; the control loop error amplifier input pin SENSE / FB of the linear voltage regulator chip U7 is connected with the power output pin OUT of the linear voltage regulator chip U7 and one end of the capacitor C24 and then outputs a 1.8-volt voltage, that is, a second power voltage, and the other end of the capacitor C24 is grounded.

[0100] The charging management chip U5 can adopt a product of model TP4056 of MSKSEMI Company. The linear voltage regulator U6 can adopt a product of model AMS1117-3.3 of AMS Company. The linear voltage regulator U7 can adopt a product of model TPS7A4700RGWT of Texas Instruments Company.

[0101] In an exemplary embodiment, as shown in Figure 13 The working process of the fruit picking data detection device is as follows:

[0102] The measuring device of the present application is hung on the fruit tree, and the tree is excited by the picking machine to record the impact on the fruit and the changes in posture and trajectory after the impact. When the whole fruit picking data detection device is powered on, the host computer first initializes the central processing module, including circuit reset, internal clock reset, timer zeroing and other actions. Next, the distance measurement module is initialized, including clock reset, communication frequency setting, etc. The acceleration detection module and the angular velocity detection module are initialized, and finally the acceleration detection module and the angular velocity detection module are initialized, including the detection range, sampling frequency, resolution setting, acceleration correction and error compensation of the acceleration detection module. The angular velocity detection module is initialized, including the detection range, sampling frequency, resolution setting, angular velocity correction and error compensation. Before using the device, the error types of the acceleration detection module and the angular velocity detection module are analyzed and the error model is established. The errors of the acceleration detection module and the angular velocity detection module are divided into: bias, scale, misalignment, temperature-dependent bias, random walk and noise, etc.

[0103] The acceleration detection module and the angular velocity detection module are respectively composed of an accelerometer and a gyroscope. The error types of the accelerometer and the gyroscope are divided into deterministic errors and random errors.

[0104] The central processing module is also used to correct the acceleration detection module using a first error model (error model of the acceleration detection module) and correct the angular velocity detection module using a second error model (error model of the angular velocity detection module).

[0105] The first error model is represented as: a m =(I+M a +S a )(a t +g)+b a +n a (1);

[0106] The second error model is represented as: ω m = (I + M ω + S ω ) ω t + b ω + n ω (2);

[0107] Wherein, a m is an acceleration measurement value (actual output value of the acceleration detection module), a t is an acceleration true value, I is a unit matrix, ω m is an angular velocity measurement value (actual output value of the angular velocity detection module), ω t is an angular velocity true value, M a and M ω are both cross-axis coupling error matrices, S a and S ω are both scale factor error matrices, g is a gravity acceleration vector, b a and b ω are both zero offset values, n a and n ω are both random errors.

[0108] By placing the sensor (accelerometer or gyroscope) horizontally and stationary for more than 6 hours, Allan variance analysis is performed on the acquired axis data and an Allan variance curve is drawn, wherein the vertical coordinate reading of the intersection point of the extension line of the line segment with a slope of 0 on the Allan variance double logarithmic curve and t=1 is the value of the zero offset error, the vertical coordinate of the intersection point of the extension line of the line segment with a slope of-0.5 and t=1 is the value of the random walk error, and the vertical coordinate of the intersection point of the extension line of the line segment with a slope of-1 and t=1 is the value of the noise error.

[0109] For the cross-axis coupling error matrix and the scale factor error matrix of the acceleration detection module, six-position method is used for measurement, that is, the XYZ axes of the acceleration measurement module are respectively vertically upward and vertically downward and stationary for 15 minutes, and the original output of the acceleration detection module is collected six times to take the average value. The scale factor error matrix and the cross-axis coupling error matrix are calculated according to the least square method.

[0110] For the scale factor error matrix and the cross-axis coupling error matrix of the angular velocity detection module, the sensor is installed on the turntable, and clockwise rotation and counterclockwise rotation of 60° are respectively performed around the XYZ three axes, and the cross-axis coupling error matrix and the scale factor error matrix of the angular velocity detection module are solved according to the least square method.

[0111] According to the above formula (1), formula (2) and the measurement error value, the correction and error compensation of the acceleration detection module and the angular velocity detection module can be completed through the central processing module.

[0112] If the calibrated sensor is placed on a horizontal plane, let the XYZ three-axis point to vertical downward respectively, watch the accelerometer reading, quaternion reading, sensor and beacon distance reading from the host computer. If any of the three values has a problem, it is determined that the initialization fails, and the initialization of the three modules is returned to be executed again. If the initialization is successful, continue to execute downward, the acceleration detection module starts to detect the acceleration signal, the angular velocity detection module detects the angular velocity signal, and the distance measurement module detects the distance signal. And the detected acceleration signal and angular velocity signal are transmitted to the central processing module through the IIC communication protocol, and the detected distance signal is transmitted to the central processing module through the SPI communication protocol. The central processing module processes the data through the built-in LSTM network to obtain the attitude data and the trajectory data, and transmits the acceleration signal, the angular velocity signal, the distance signal, the attitude data and the trajectory data to the host computer through the wireless communication module.

[0113] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0114] The principles and implementation modes of the present application are described by using specific examples in the present application. The above embodiment is only used to help understand the method of the present application and its core idea. For those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In summary, the content of the present application should not be understood as a limitation.

Claims

1. A fruit picking data detection device characterized by, The fruit picking data detection device comprises a measuring device and a host computer, the measuring device comprises a data acquisition module and a central processing module, and the measuring device is arranged at a target position on a fruit tree; The data acquisition module is used for collecting motion data of the measuring device in real time during fruit picking, and sending the motion data to the central processing module; The central processing module is used for obtaining the position and posture of the measuring device in real time according to the real-time collected motion data, adopting a posture recognition and trajectory tracking model, and sending the position and posture of the measuring device to the host computer in real time; the host computer is in wireless communication connection with the central processing module; The host computer is used for receiving the motion data, position and posture of the measuring device in real time, and taking the motion data, position and posture of the measuring device as the motion data, position and posture in the fruit picking process.

2. The fruit picking data detection apparatus according to claim 1, characterized by The motion data comprises acceleration, angular velocity and distance, and the distance is the distance between the measuring device and a positioning beacon; The data acquisition module comprises a detection module and a distance measurement module; The detection module is used for collecting the acceleration and angular velocity of the measuring device, and the distance measurement module is used for collecting the distance of the measuring device.

3. The fruit picking data detection apparatus according to claim 1, characterized by The posture recognition and trajectory tracking model is obtained by training a neural network model with a training set; The training of the neural network model with the training set comprises the following steps: Collecting motion sample data in a set time period; the motion sample data comprises acceleration, angular velocity and distance of the measuring device, and the distance is the distance between the measuring device and a positioning beacon; Performing data cleaning on the motion sample data by using a Butterworth filter; Solving the position and posture according to the data cleaned motion sample data; Identifying outliers of the solved position and posture by using an absolute median deviation method, and replacing the identified outliers by using a Winsorization method to obtain effective position and posture; Training the neural network model by taking the data cleaned motion sample data in each time step as input and taking the effective position and posture as label data to obtain the posture recognition and trajectory tracking model.

4. The fruit picking data detection apparatus according to claim 3, characterized by The position and posture solving according to the data cleaned motion sample data comprises the following steps: Performing data fusion on acceleration and angular velocity to obtain the posture of the measuring device at each moment, and the posture is represented by a posture quaternion; Performing data fusion on acceleration, angular velocity and distance to obtain the position of the measuring device at each moment.

5. The fruit picking data detection apparatus according to claim 3, characterized by The neural network model adopts a long short-term memory network.

6. The fruit picking data detection apparatus according to claim 1, characterized by The fruit picking data detection device further comprises a wireless transmission module and an ISP serial port module, the wireless transmission module is integrated into the central processing module, and the wireless transmission module is used for wireless communication between the central processing module and the host computer; the ISP serial port module is connected with the central processing module, and the ISP serial port module is used for wired communication between the central processing module and the host computer.

7. The fruit picking data detection apparatus according to claim 2, characterized by The detection module comprises an acceleration detection module and an angular velocity detection module; the acceleration detection module is configured to collect acceleration of the measuring device, and the angular velocity detection module is configured to collect angular velocity of the measuring device; The central processing module is further configured to correct the acceleration detection module by using a first error model and correct the angular velocity detection module by using a second error model; The first error model is represented as: a m = (I + M a + S a )(a t + g) + b a + n a ; The second error model is represented as: ω m = (I + M ω + S ω ) ω t + b ω + n ω ; where a m is the acceleration measurement value, a t is the acceleration true value, I is the identity matrix, ω m is the angular velocity measurement value, ω t is the angular velocity true value, M a and M ω are the cross-axis coupling error matrices, S a and S ω are the scale factor error matrices, g is the gravity acceleration vector, b a and b ω are the bias values, n a and n ω are the random errors.

8. The fruit picking data detection apparatus according to claim 2, characterized by The central processing module comprises a main processing chip U1, a capacitor C1 and a reset circuit, the reset circuit comprises a resistor R1, a capacitor C2 and a reset switch S1, one end of the resistor R1 is connected with a first power supply voltage, the other end of the resistor R1, one end of the reset switch S1 and one end of the capacitor C2 are all connected with a reset pin of the main processing chip U1, the other end of the reset switch S1 and the other end of the capacitor C2 are both grounded, and the reference voltage external input pin of the main processing chip U1 and one end of the capacitor C1 are both connected with the first power supply voltage; the other end of the capacitor C1 and the ground pin of the main processing chip U1 are both grounded. The main processing chip U1 is a dual-core 32-bit ARM single-chip microcomputer.

9. The fruit picking data detection apparatus according to claim 8, characterized by The detection module comprises a detection chip U2, a resistor R2, a resistor R3, a resistor R4, a resistor R5, a capacitor C3 and a capacitor C4, an I / O power supply input pin of the detection chip U2 and one end of the capacitor C3 are connected with a second power supply voltage, the other end of the capacitor C3 is grounded, an address selection pin of the detection chip U2 is connected with one end pin of the resistor R2, the other end of the resistor R2 is grounded, a function synchronization pin of the detection chip U2 is connected with one end of the resistor R3, the other end of the resistor R3 is grounded, a power supply input pin of the detection chip U2 is connected with one end of the capacitor C4, the other end of the capacitor C4 is grounded, an analog interrupt pin of the detection chip U2 is connected with a first interrupt pin of the main processing chip U1, an IIC serial clock pin of the detection chip U2 is connected with an IIC serial clock pin of the main processing chip U1 and one end of the resistor R4 respectively, the other end of the resistor R4 is connected with the first power supply voltage, an IIC serial data input pin of the detection chip U2 is connected with an IIC serial data input pin of the main processing chip U1 and one end of the resistor R5 respectively, and the other end of the resistor R5 is connected with the first power supply voltage.

10. The fruit picking data detection apparatus according to claim 1, characterized by The distance measurement module comprises a wireless carrier communication chip U3, a quartz crystal resonator Y1, a resistor R6, a capacitor C5, a capacitor C6, a capacitor C7, a capacitor C8, a capacitor C9, a capacitor C10, a capacitor C11, a capacitor C12, a capacitor C13, a capacitor C14, a capacitor C15, a capacitor C16, a filter FB1 and an antenna W1; The first power input pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C5, and the other end of the capacitor C5 is grounded; the second power input pin of the wireless carrier communication chip U3 is connected with one end of the filter FB1 and one end of the capacitor C6 respectively, the other end of the filter FB1 is connected with the first power voltage, and the other end of the capacitor C6 is grounded; the third power input pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C7, the capacitor C8 and the capacitor C9 respectively, the other end of the capacitor C7, the other end of the capacitor C8 and the other end of the capacitor C9 are grounded; the fourth power input pin of the wireless carrier communication chip U3, one end of the capacitor C10, one end of the capacitor C11, one end of the capacitor C12 and one end of the capacitor C13 are connected with the first power voltage respectively, the other end of the capacitor C10, the other end of the capacitor C11, the other end of the capacitor C12 and the other end of the capacitor C13 are grounded; the first antenna pin of the wireless carrier communication chip U3 is connected with one end of the resistor R6, and the other end of the resistor R6 is grounded; the second antenna pin of the wireless carrier communication chip U3 is connected with one end of the capacitor C14, and the other end of the capacitor C14 is connected with the antenna W1; the analog interrupt pin of the wireless carrier communication chip U3 is connected with the second interrupt pin of the main control chip U1; the first grounding pin, the second grounding pin, the third grounding pin and the fourth grounding pin of the wireless carrier communication chip U3 are connected with each other and grounded; the crystal input pin of the wireless carrier communication chip U3 is connected with the No.1 pin of the quartz crystal resonator Y1; the crystal output pin of the wireless carrier communication chip U3 is connected with the No.3 pin of the quartz crystal resonator Y1; the SPI clock pin of the wireless carrier communication chip U3 is connected with the clock pin of the main control chip U1; the SPI output pin of the wireless carrier communication chip U3 is connected with the first host SPI host output pin of the main control chip U1; the SPI input pin of the wireless carrier communication chip U3 is connected with the first host SPI host input pin of the main control chip U1; the chip selection pin of the wireless carrier communication chip U3 is connected with the SPI master-slave common selection pin of the main control chip U1; wherein the first pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C15, the other end of the capacitor C15 is connected with the No.2 pin of the quartz crystal resonator Y1 and grounded; the No.4 pin of the quartz crystal resonator Y1 is grounded; the No.3 pin of the quartz crystal resonator Y1 is connected with one end of the capacitor C16, and the other end of the capacitor C16 is grounded.

Images