CN212324756U - Online prediction device for feeding amount of combine harvester - Google Patents
Online prediction device for feeding amount of combine harvester Download PDFInfo
- Publication number
- CN212324756U CN212324756U CN202022104562.4U CN202022104562U CN212324756U CN 212324756 U CN212324756 U CN 212324756U CN 202022104562 U CN202022104562 U CN 202022104562U CN 212324756 U CN212324756 U CN 212324756U
- Authority
- CN
- China
- Prior art keywords
- acquisition module
- combine harvester
- prediction device
- main controller
- image acquisition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Combines (AREA)
Abstract
The utility model provides an online prediction device for the feeding amount of a combine harvester, which comprises a main controller, a speed acquisition module and an image acquisition module, wherein the speed acquisition module and the image acquisition module are both connected with the main controller; the speed acquisition module is arranged on the inner side of a driving wheel of the combine harvester, and the image acquisition module is fixed on a harvester ceiling through a bracket; the utility model provides a support all utilizes the draw-in groove to adjust along the length of horizontal direction and vertical direction to satisfy the focus of difference and the field of vision scope demand of shooting. The utility model discloses can realize different models and the on-line prediction of joint harvest festival feed rate of shooting field of vision scope.
Description
Technical Field
The utility model belongs to intelligence agricultural machinery equipment field, concretely relates to combine harvester feeding volume on-line prediction device.
Background
With the rapid development of agricultural mechanization, the combined harvester as the main agricultural machine is gradually widely applied to agricultural production, thereby greatly promoting the development of agricultural economy in China. However, many problems begin to appear in the wide application, for example, when the harvesting environment of the combine harvester is complicated (the plant height, the density of crops and the condition of uneven land) during the field operation, an operator needs to immediately adjust the operation speed of the combine harvester to control the feeding amount within a stable range so as to maintain the harvesting efficiency, and the combine harvester may malfunction because of improper control or no timely adjustment caused by insufficient experience of the operator, thereby greatly reducing the harvesting efficiency; if the feeding amount is too large, the threshing roller can be blocked, and the threshing and cleaning effects are reduced and the loss is serious; if the feeding amount is too small, the power of the combined harvester cannot be used to the maximum, labor and time are wasted, and even the best harvesting time of crops can be missed; therefore, the feed detection level of the combine harvester needs to be improved urgently.
SUMMERY OF THE UTILITY MODEL
Exist not enoughly among the prior art, the utility model provides a combine harvester feeding volume on-line prediction device for satisfy different models and shoot the combine harvest festival feeding volume on-line prediction of field of vision scope.
The utility model discloses a realize above-mentioned technical purpose through following technological means.
The on-line prediction device for the feeding amount of the combine harvester comprises a main controller, a speed acquisition module and an image acquisition module, wherein the speed acquisition module and the image acquisition module are connected with the main controller; the speed acquisition module is arranged on the inner side of a driving wheel of the combine harvester, and the image acquisition module is fixed on a harvester ceiling through a support.
The technical scheme also comprises a power supply voltage stabilizing module, a man-machine interaction module and a CAN communication module which are connected with the controller.
According to the technical scheme, the speed acquisition module is a Hall sensor, the Hall sensor comprises a Hall sensor probe and magnetic steel, the magnetic steel is pasted on a rotating shaft on the inner side of a driving wheel of the combine harvester, the Hall sensor probe generates a pulse signal every time passing through one magnetic steel, and the pulse signal is transmitted to the main controller through the signal output end.
Above-mentioned technical scheme, the support includes angle bar, stock, quarter butt and inferior gram force board, and the angle bar is fixed on the harvester ceiling, and the long pole one end is still fixed to the angle bar, and another section of stock is connected with quarter butt one end is perpendicular, and the inferior gram force board is fixed to the quarter butt other end, fixes image acquisition module on the inferior gram force board.
Above-mentioned technical scheme, stock and quarter butt all set up in the draw-in groove, all are equipped with the round hole on stock, quarter butt and the draw-in groove, and through the cooperation of round hole, stock and quarter butt can stretch out and draw back in the draw-in groove.
The utility model has the advantages that: the utility model provides a camera passes through the support to be fixed on the harvester ceiling, and the support all utilizes the draw-in groove to adjust along the length of horizontal direction and vertical direction to satisfy the different focuses of camera and the field of vision scope of shooting. The utility model discloses a speed acquisition module acquires the real-time operation speed of combine, acquires the picture of the place ahead crop in real time through image acquisition module, obtains the area of the place ahead crop, and then obtains combine's feeding volume size. The utility model discloses to actual results crop in-process, the feeding volume prediction of different models and the combine of shooting field of vision scope has better effect, has effectively alleviated the big lagged characteristic of the big time delay of harvester, can provide the operation foundation for the driver well, improves the results quality, also provides technical support for the combine is intelligent simultaneously.
Drawings
FIG. 1 is a structural diagram of an on-line feed quantity prediction device of a combine harvester according to the present invention;
FIG. 2 is a schematic view of the whole structure of the combine harvester of the present invention;
FIG. 3 is a schematic diagram of the Hall sensor of the present invention;
fig. 4 is a schematic structural diagram of the laser sensor of the present invention;
FIG. 5 is a schematic view of the bracket structure for mounting the camera according to the present invention;
FIG. 6 is a flow chart of the front crop image processing of the present invention;
FIG. 7 is a flow chart of the feed amount prediction according to the present invention;
FIG. 8 is a human-computer interface diagram of the on-line feeding amount prediction device of the combine harvester of the present invention.
Wherein: 1-camera, 2-bracket, 201-M8 round hole, 202-angle iron, 203-M6 round hole, 204-clamping groove, 205-long rod, 206-right angle sleeve, 207-M15 round hole, 208-M16 round hole, 3-screen, 4-laser ranging sensor, 401-sensor column, 402-M16 screw cap, 403-laser emitting head, 404-laser receiving head, 5-bracket, 6-Hall sensor, 601-magnetic steel, 602-sensor probe and 603-signal output end.
Detailed Description
The invention will be further described with reference to the drawings and the following examples, but the scope of the invention is not limited thereto.
As shown in figure 1, the on-line prediction device for the feeding amount of the combine harvester comprises a main controller (ARM controller), a speed acquisition module, an image acquisition module, a stubble and crop height acquisition module, a power supply voltage stabilization module, a man-machine interaction module and a CAN communication module, the speed acquisition module, the image acquisition module, the stubble and crop height acquisition module, the power supply voltage stabilization module, the man-machine interaction module and the CAN communication module are connected with the main controller, the speed acquisition module, the image acquisition module, the stubble and crop height acquisition module transmit acquired information to the main controller, the main controller predicts the feeding amount at the next moment through processing, and then transmits the predicted value to an upper computer through the CAN communication module.
As shown in fig. 3, the speed acquisition module is a hall sensor, the hall sensor is installed on a cross beam on the inner side of the driving wheel 6 of the combine harvester (fig. 2), the hall sensor comprises a hall sensor probe 602 and magnetic steel 601, the magnetic steel 601 coated with AB glue on the N pole is adhered to a rotating shaft on the inner side of the driving wheel 6, four magnetic steels 601 are adhered to one circle of the driving wheel 6, one magnetic steel 601 is adhered at every 90 degrees, the hall sensor probe 602 can generate a pulse signal every time passing through one magnetic steel 601, and the pulse signal is transmitted to the main controller through a signal output end 603; the sampling time of the Hall sensor is generally set to be 1s, and the main controller utilizes a formula
(m/s) calculating the real-time operation speed of the combine harvester, whereinN is the total number of pulses obtained by the main controller in 1s, N is the number of the magnetic steels 601 on the rotating shaft, and d is the size (m) of the outer diameter of the driving wheel 6.
As shown in fig. 4, the stubble-remaining and crop height collecting module comprises two laser ranging sensors 4, which are respectively used for calculating stubble-remaining and crop heights; the laser distance measuring sensor 4 for calculating the stubble height is fixed through the L-shaped support 5, the vertical plate of the support 5 is welded at the forefront end of the nearside divider (shown in figure 2), then the sensor column 401 is fixed in the clamping groove of the horizontal plate of the support to ensure that the sensor column is vertically downward, the upper side and the lower side of the sensor column 401 are fixed by using gaskets and M16 screw caps 402, and the sensor column 401 is ensured to be normally stable under severe vibration working environment; the bottom end of the sensor column 401 is provided with a laser emitting head 403 and a laser receiving head 404; the main controller calculates the time from the ray emitted from the laser emitting head 403 to the laser receiving head 404 after being reflected by the non-transparent material, and then uses the formula
The height of the stubble can be calculated, wherein c is the speed of light (m/s), t1The time(s) of the laser back and forth, D is the relative distance (m) from the divider to the cutter; the laser ranging sensor 4 for calculating the height of the crop is fixed at the M16 round hole 208 of the acrylic plate of the bracket 2, specifically: inserting the sensor column 401 into the M16 circular hole 208, fixing the sensor column with a gasket and an M16 nut 402, wherein the bottom end of the sensor column 401 is provided with a laser emitting head 403 and a laser receiving head 404; the main controller calculates the time from the reflection of the ray from the laser emitting head 403 to the laser receiving head 403 by the non-transparent material, and the formula is used
The height of the crop can be calculated, where t2The time(s) of the laser round trip, H is the total height (m) of the laser ranging sensor 4 to the ground; the measured value of the laser ranging sensor 4 can be accurate to 1mm, and both meet the precision requirement.
As shown in fig. 5, a bracket 2 for fixing a camera 1 firstly fixes an angle iron 202 on a ceiling of a harvester (fig. 2), four M8 round holes 201 are uniformly punched on the horizontal side surface of the angle iron 202, the distance between the M8 round holes 201 is 20mm, a bolt penetrates through the M8 round holes 201 and is fixed with the ceiling of the harvester, four M6 round holes 203 are punched on the vertical side surface of the angle iron 202, one end of a long rod 205 is fixed through the bolt, the long rod 205 is arranged in a clamping groove 204, and the long rod 205 is stretched by the clamping groove 204 according to the length of a reel of the combine harvester, wherein the stretching range is 1.5-3M; the other end of the long rod 205 is connected with one end of a short rod by a right-angle sleeve 206, the short rod is also provided with a clamping groove 204, the length is adjusted according to the difference of the focal length of a camera and the shooting visual field range, and the adjusting range is 0.5-1 m; the other end of the short rod is fixed with a rectangular acrylic plate, and the acrylic plate is provided with an M15 round hole 207 so as to fix the camera 1. The long rod 205 is arranged inside the clamping groove 204, and the specific setting mode is as follows: the bottom of the outer side of the clamping groove 204 is provided with a plurality of M6 round holes in an array manner, the two sections of long rods 205 inside the clamping groove 204 are provided with a plurality of M6 round holes in an array manner, the whole length can be adjusted by stretching the two sections of long rods 205, and when the proper position is adjusted, the whole length is fixed by placing bolts and nuts in the two corresponding round holes so as to meet the requirement of the whole process stability. The arrangement mode of the clamping groove on the short rod is the same as that of the long rod.
The camera 1 acquires the picture of the front crop in real time and transmits the picture to the main controller, so that the area expression of the front crop is obtained as follows:
wherein S is the shot area (m) at the calibrated height H2) The specific calibration process is as follows: firstly fixing a camera 1 at a height H away from the ground, then shooting black and white lattices, calculating the actual area S of shooting by accumulating the number of the black and white lattices, calculating the average value of S by shooting for multiple times, and substituting the average value into the formula to obtain the area of a front crop below the fixed height; according to the formula
Calculating the feeding amount, wherein s is the crop area and n1The number of the ears, M the average quality of the single crop, M the value of the feeding amount, k and lambda as influence factors, V the real-time operation speed of the combine harvester, and g the swath width.
The camera 1 acquires the picture of the front crop in real time and transmits the picture to the main controller, and the main controller processes the acquired picture to obtain the number of the panicle heads, and the specific process is as follows:
firstly, carrying out gray level processing: extracting specific values of RGB of the crop picture, obtaining a gray value gray by adopting a weighted average method, carrying out weighted average on the three components by different weights according to importance and relevant characteristics, and carrying out weighted average on the RGB three components according to the following formula to obtain more reasonable gray because human eyes have highest sensitivity to green and lowest sensitivity to blue: f (i ', j') +0.59G (i ', j') +0.11B (i ', j'), (i ', j') represents a pixel point of the image; and (3) making R-G-B-gray to realize graying of the crop picture.
And secondly, median filtering treatment: an image is divided into a plurality of different windows, pixels in the windows are arranged according to the size, and the median gray level is used as the gray level value of the window.
③ OTSU threshold segmentation: establishing a histogram, determining a proper threshold value by using a maximum inter-class variance method, then taking 1 for pixel points larger than the threshold value and 0 for pixel points smaller than the threshold value, realizing binarization processing of the image, and removing a soil background part.
Image morphology processing: because the noise still exists in the image after the segmentation, and gaps with different sizes exist among grains, the cavity exists after the image is segmented, and the cavity is gradually filled up by performing corrosion and expansion operation on the image through a 3 x 3 cross type.
Detecting angular points and counting spike heads: setting an inspection window on the image, moving the inspection window in each direction by small displacement (u, v), exploring the change of the window in a mode of average energy, and extracting a pixel point at the central position as an angular point when the change range is larger than an expected threshold value; the average energy is calculated as: e (u, v) ═ Σ W [ I (x + u, y + v) -I (x, y) ], where W is a gaussian function, I (x + u, y + v) is the image grayscale value after translation, and I (x, y) is the image grayscale value before translation; the number of the angular points is directly related to the number of the connected spikes, the regions without the angular points are generally isolated spikes, the positions with the angular points are provided with adhered spikes, and the number of the spikes is one more than the number of the angular points, so that the number of the spikes in the whole region can be calculated by detecting the number of the regions and the number of the angular points; the whole process flow is shown in fig. 6.
The problem of feed prediction of the combine harvester is substantially a nonlinear function fitting problem, and the size of the feed prediction is difficult to accurately calculate through a simple linear formula, so that the initial weight and the threshold of a neural network are optimized by utilizing the nonlinear extremum optimizing capability of a particle swarm algorithm, the size of the feed can be accurately predicted through the nonlinear fitting capability of the neural network, a flow chart is shown in FIG. 7, and the specific process of a feed prediction model is as follows:
s1, designing BP neural network, which is a multi-layer feedforward network trained according to error back propagation (error back propagation for short) and has faster processing speed and stronger fault-tolerant rate, and for any continuous function in a closed interval, the network can be approximated by using a single hidden layer forward neural network, and under normal conditions, a 3-layer BP neural network can realize mapping from any n dimension to m dimension, so the number of layers of BP neural network selected in this embodiment is 3, the input quantity is the number of ears of crops, the real-time operation speed of a harvester, the stubble and the crop height, and the mapping function is f (x)1,x2…xn) In the formula x1,x2…xnThe output is the value of the feed amount for a factor that affects the feed amount size. The BP neural network has the advantages of simple process, small operand and strong compatibility, but also has the defects of slow convergence speed of derivative values and learning rate of response functions, and can be trapped in a local minimum state due to uncertainty of error functions; therefore, aiming at the defects of the BP neural network, the BP neural network is improved and optimized by introducing a particle swarm optimization.
S2, continuously optimizing the initial weight and threshold of the neural network by the particle swarm optimization
In the particle swarm optimization, the dimension of the whole space is the sum of all initial weights and thresholds in the BP neural network;
initializing a particle swarm: determining the initial position and speed of the particle in space;
particle fitness value: calculating expected output and predicted output, and taking the sum of absolute values of respective errors as individual fitness F, wherein the algorithm formula is as follows (1):
in the formula: n is2Number of nodes representing output, yiIs the expected output of the ith point in the neural network, oiAbs () is an operator of absolute error, and k' represents a coefficient of the equation, for the prediction output of the ith point;
finally, calculating the fitness value F of the particles by combining the initial position of each particle with the formula (1)it[i]；
Updating individual extreme values: the optimal position found by the ith particle in the whole space is used as an individual extremum, as shown in formula (2):
Pbest＝[pi1,pi2,...,pid]T,i＝1,2,...,n2 (2)
the fitness value F of each particleit[i]And individual extremum Pbest(i) Making a size comparison if Fit[i]>Pbest(i) If the individual extreme value is Fit[i]Otherwise, P is selectedbest(i)；
Updating the group extremum: the value of the optimal position searched by the particle group in the whole process is called the extreme value of the group, and is shown as the following formula (3):
Gbest＝[Pg1,Pg2,...,Pgd]T,g＝1,2,...,n2 (3)
the fitness value F of each particleit[i]And group extremum Gbest(g) Making a size comparison if Fit[i]>Gbest(g) F for the extreme value of the populationit[i]Otherwise, G is usedbest(g)；
Updating the particle speed and position: during each particle iteration, the particles adopt individual extrema and population extrema, and update their own velocity and position in conjunction with equations (4) and (5):
in the formula: w represents an inertial weight; d1, 2, ·, D; k is the iteration number of the system; v. ofidDenotes the velocity, X, of the particleidIndicating the position of the particle; c. C1And c2Is an acceleration factor, typically a non-negative constant; r is1And r2Is [0, 1 ]]A random number in between;
the initial weight and threshold value, the expected output and the prediction output of the BP neural network are acquired by depending on training samples, the training samples are manually collected in the field, and a plurality of groups of crops with different areas, different stubble heights and different crop heights are manually harvested to acquire basic data.
S3, assigning the optimal individuals obtained by the particle swarm algorithm to the initial weight and the threshold value of the neural network to finish the training of the neural network, wherein the trained neural network is a feed amount prediction model; the number of the ears of the crops, the real-time operation speed of the harvester, the stubble and the crop height are used as the input of the feed amount prediction model, and the output value is the final predicted value of the feed amount.
As shown in fig. 8, the human-computer interaction module is a touch display screen interface, and the touch screen is communicated with the main controller through a serial port to transmit, so as to display the key information processed by the main controller in real time; the screen 3 of the man-machine interaction module is fixedly arranged at the upper right part of the driver seat (shown in figure 2), so that a driver can know the harvesting information conveniently during operation; the content displayed on the screen 3 includes the display of each key data and the real-time display of the acquired front crop picture, and manual data input, such as an approximate grass-valley ratio value measured manually in advance, can be performed through an electronic keyboard of the screen 3. The man-machine interaction module also has an alarm function, and the alarm lamp has three states: when the predicted value of the feeding amount is in a normal state (the difference value of the predicted value is within +/-10% of a rated value and is obtained by calculation of a main controller), the alarm lamp is in a green state; when the predicted value of the feeding amount is in an abnormally small state (the difference value of the predicted values is less than the rated value minus 10 percent), the alarm lamp is in a blue state; when the predicted value of the feeding amount is in an abnormal large state (the difference value of the predicted values is more than 10 percent of the rated value), the alarm lamp is in a red state.
The CAN communication module is a differential signal line formed by two signal lines CNA _ H and CAN _ L, and is used for communication in the form of differential signals, and has strong anti-interference capability.
The normal operating voltage that main control unit was mainly considered to power voltage stabilizing module is 12V, can appear the machine start-up controller in the twinkling of an eye when directly using the power on the combine harvester problem of falling the electric, if the combine harvester often opens and stops to have the damage to the controller, uses voltage stabilizing module to play the guard action to main control unit to a certain extent, increase of service life.
The embodiment is a preferred embodiment of the present invention, but the present invention is not limited to the above embodiment, and any obvious improvement, replacement or modification which can be made by those skilled in the art without departing from the essence of the present invention belongs to the protection scope of the present invention.
Claims (5)
1. The on-line prediction device for the feeding amount of the combine harvester is characterized by comprising a main controller, a speed acquisition module and an image acquisition module, wherein the speed acquisition module and the image acquisition module are connected with the main controller; the speed acquisition module is arranged on the inner side of a driving wheel of the combine harvester, and the image acquisition module is fixed on a harvester ceiling through a support (2).
2. The on-line feed quantity prediction device of the combine harvester according to claim 1, further comprising a power supply voltage stabilization module, a human-computer interaction module and a CAN communication module connected with the controller.
3. The on-line prediction device of the feeding amount of the combine harvester according to claim 1, wherein the speed acquisition module is a hall sensor, the hall sensor comprises a hall sensor probe (602) and magnetic steel (601), the magnetic steel (601) is adhered to a rotating shaft on the inner side of the drive wheel (6) of the combine harvester, the hall sensor probe (602) generates a pulse signal once when passing through one magnetic steel (601), and the pulse signal is transmitted to the main controller through the signal output end (603).
4. The on-line prediction device of the feeding amount of the combine harvester according to claim 1, wherein the support (2) comprises an angle iron (202), a long rod (205), a short rod and an acrylic plate, the angle iron (202) is fixed on the ceiling of the harvester, the angle iron (202) also fixes one end of the long rod (205), the other section of the long rod (205) is vertically connected with one end of the short rod, the acrylic plate is fixed at the other end of the short rod, and an image acquisition module is fixed on the acrylic plate.
5. The on-line feed quantity prediction device of the combine harvester as claimed in claim 4, wherein the long rod (205) and the short rod are both disposed in the slot (204), and round holes are disposed on the long rod (205), the short rod and the slot (204), and the long rod (205) and the short rod can extend and retract in the slot (204) through the cooperation of the round holes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022104562.4U CN212324756U (en) | 2020-09-23 | 2020-09-23 | Online prediction device for feeding amount of combine harvester |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022104562.4U CN212324756U (en) | 2020-09-23 | 2020-09-23 | Online prediction device for feeding amount of combine harvester |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212324756U true CN212324756U (en) | 2021-01-12 |
Family
ID=74071192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202022104562.4U Active CN212324756U (en) | 2020-09-23 | 2020-09-23 | Online prediction device for feeding amount of combine harvester |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212324756U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239715A (en) * | 2021-02-04 | 2021-08-10 | 南京大学 | Rape harvest feeding amount detection method and device based on image processing |
-
2020
- 2020-09-23 CN CN202022104562.4U patent/CN212324756U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239715A (en) * | 2021-02-04 | 2021-08-10 | 南京大学 | Rape harvest feeding amount detection method and device based on image processing |
| CN113239715B (en) * | 2021-02-04 | 2024-05-28 | 南京大学 | Rape harvesting feeding amount detection method and device based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Benson et al. | Machine vision-based guidance system for agricultural grain harvesters using cut-edge detection | |
| CN103891697A (en) | Drug spraying robot capable of moving indoors autonomously and variable drug spraying method thereof | |
| US10602665B2 (en) | Two armed robotic system for adjusting the height of an agricultural tool | |
| CN112598701B (en) | Automatic tracking and monitoring video acquisition system and method for farm targets | |
| CN113906900B (en) | Sugarcane harvester and method for adjusting position and posture of cutter head of sugarcane harvester based on multi-sensor fusion | |
| CN212324756U (en) | Online prediction device for feeding amount of combine harvester | |
| CN112056087B (en) | Induction system of small-sized segmented crawler sugarcane harvester and control method | |
| AU2022256171B2 (en) | Weeding robot and method, apparatus for planning weeding path for the same and medium | |
| CN115067062B (en) | System and method for preventing and controlling blocking faults of header of combine harvester | |
| CN109380146A (en) | Live pig self-operated measuring unit and method | |
| CN109947115A (en) | A kind of mowing machine control system and its control method | |
| CN112115988B (en) | Wheat ear counting method and device and self-walking trolley | |
| CN112237089A (en) | Online prediction device and method for feeding amount of combine harvester | |
| CN111680587A (en) | Multi-target tracking-based chicken flock activity real-time estimation method and system | |
| CN107830891A (en) | Aquaculture water quality pH value many reference amounts data acquisition device and data processing method | |
| CN113326743B (en) | Method for extracting and analyzing fish school movement behavior parameters under cultivation background condition | |
| CN110414384A (en) | Intelligent rice and wheat harvester leading line tracking | |
| Wang et al. | Multi-sensor signal acquisition and data processing analysis of combine harvester. | |
| CN206118799U (en) | Cultured fish direction survey system of moving about | |
| CN105892456B (en) | One kind being used for uniline crop plant strain head track mark automatic tracking control method | |
| CN115451965B (en) | Relative heading information detection method for transplanting system of transplanting machine based on binocular vision | |
| CN115280960B (en) | Combined harvester steering control method based on field vision SLAM | |
| CN113545219B (en) | Combine harvester field head steering system and method and combine harvester | |
| CN115868443A (en) | Accurate feeding device and method based on unmanned aerial vehicle | |
| CN116795157A (en) | Greenhouse environment monitoring and adjusting method and system based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |