A navigation precision self-checking system of a farm intelligent inspection vehicle

Abstract

The application discloses a kind of farm intelligent inspection car's navigation precision self-checking system, comprising: data acquisition module, for real-time acquisition of the environmental parameters of farm and the state parameters of intelligent inspection car;Data processing module is used to first carry out data integration to environmental parameters and state parameters, then data processing and analysis are carried out, and target data set is obtained;Model construction module is used to construct initial multi-modal network model, and based on target data set, initial multi-modal network model is trained, and target multi-modal network model is obtained;Monitoring prediction module is used to carry out real-time monitoring based on target multi-modal network model to the running state of intelligent inspection car, according to the monitoring result when the deviation of detected actual path and preset path occurs, automatically triggers self-checking algorithm to carry out path calibration.The application significantly improves the navigation precision of intelligent inspection car, reduces manual intervention through automatic self-checking and calibration, reduces maintenance cost and time.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent inspection, and particularly relates to a navigation precision self-checking system of a farm intelligent inspection vehicle. BACKGROUND

[0002] With the development of modern farming, the scale of farms is expanding, and the traditional manual inspection method has been unable to meet the demand for high efficiency and fine management. As a new emerging automated device, the intelligent inspection vehicle can realize real-time monitoring and automatic management of the farm environment by carrying sensors and actuators. However, the intelligent inspection vehicle itself has the problem of navigation deviation accumulation. After a long time of running, due to factors such as sensor error and wheel slip, the intelligent inspection vehicle may accumulate navigation deviation, causing the inspection path to deviate from the predetermined trajectory. The farm environment is variable, and the existing intelligent inspection vehicle lacks environmental adaptability of the navigation system when facing environmental changes such as slippery ground and moving obstacles, and it is difficult to quickly adjust the navigation strategy. At the same time, lacking a self-checking and calibration mechanism, the existing intelligent inspection vehicle lacks the function of automatically detecting navigation precision, mainly relying on manual periodic calibration, which not only increases the maintenance cost, but also makes it difficult to ensure the timeliness of calibration. And due to the problem of navigation precision, the environmental monitoring data collected by the intelligent inspection vehicle may have deviation, affecting the accuracy of the data, and then affecting the accurate assessment and management decision of the farm environment. Therefore, the navigation precision of the intelligent inspection vehicle is directly related to the inspection effect and data accuracy, and the existing intelligent inspection vehicle mostly lacks effective self-detection and calibration mechanism, and once the navigation system deviates, it will affect the efficiency and quality of the entire inspection process. Therefore, it is urgent to provide a navigation precision self-checking system of a farm intelligent inspection vehicle to complete navigation precision self-checking before intelligent inspection, automatically detect and calibrate navigation precision, and ensure the accuracy of the inspection data. SUMMARY

[0003] To solve the above technical problems, the application provides a navigation precision self-checking system of a farm intelligent inspection vehicle, comprising:

[0004] A data acquisition module is configured to acquire environmental parameters of the farm and state parameters of the intelligent inspection vehicle in real time.

[0005] A data processing module is connected with the data acquisition module and configured to integrate the environmental parameters and the state parameters, and then perform data processing and analysis to obtain a target data set.

[0006] A model construction module is connected with the data processing module and configured to construct an initial multi-modal network model, and train the initial multi-modal network model based on the target data set to obtain a target multi-modal network model.

[0007] The monitoring prediction module is connected with the model construction module, and is configured to monitor a running state of the intelligent inspection vehicle in real time based on the target multi-modal network model, and automatically trigger a self-checking algorithm to calibrate a path according to a monitoring result when a detected actual path deviates from a preset path.

[0008] Preferably, the data acquisition module comprises a first acquisition unit and a second acquisition unit.

[0009] The first acquisition unit is configured to collect environmental parameters of the farm based on a distributed sensor to obtain an environmental image.

[0010] The second acquisition unit is configured to acquire state parameters of the intelligent inspection vehicle.

[0011] The state parameters of the intelligent inspection vehicle include but are not limited to real-time position, speed, acceleration, and direction of the intelligent inspection vehicle.

[0012] Preferably, the distributed sensor includes but is not limited to a laser radar, a camera, and an industrial panoramic camera.

[0013] The industrial panoramic camera is arranged on a roof of the intelligent inspection vehicle and is configured to obtain a road panoramic image of the farm.

[0014] The industrial panoramic camera comprises an automatic control unit, a photographing level control circuit unit, and a tilt photogrammetry unit.

[0015] The photographing level control circuit unit is provided with a flexible flat cable, and the tilt photogrammetry unit is flexibly connected with the automatic control unit through the flexible flat cable. The flexible flat cable is configured to control on / off of the camera, photographing, focusing, and feedback detection of a state of the camera, detect whether the camera is turned on or off, detect whether the camera has completed a photographing action, and detect a real-time state of the camera.

[0016] The tilt photogrammetry unit is connected with the photographing level control circuit unit.

[0017] The tilt photogrammetry unit comprises five high-precision cameras, and the cameras are arranged at a mutual tilt angle of 90 degrees.

[0018] The second acquisition unit at least comprises a GPS unit and an IMU laser radar.

[0019] The GPS unit is configured to obtain a real-time position of the intelligent inspection vehicle.

[0020] The IMU laser radar is configured to obtain speed and direction information of the intelligent inspection vehicle.

[0021] Preferably, the data processing module comprises a data processing unit, an image processing unit, and a feature extraction unit.

[0022] The data processing unit is configured to convert the original data into text data after denoising, and then merge the text data from different sources and formats.

[0023] The image processing unit is configured to perform pixel preprocessing on the environmental image, and then perform image correction to obtain a target image.

[0024] The feature extraction unit is configured to extract features from the processed image and data.

[0025] Preferably, the data processing unit comprises a data cleaning unit, a text processing unit, and a data integration unit.

[0026] The data cleaning unit is configured to remove noise and outliers in the original data, and fill in missing data.

[0027] The text processing unit is configured to sequentially perform word segmentation, dictionary establishment, text vectorization, and text normalization on the text data.

[0028] The data integration unit is configured to unify and merge data from different sources and formats, establish associations between data, and obtain a data view.

[0029] Preferably, the image processing unit comprises a pixel processing unit and an image correction unit.

[0030] The pixel processing unit is configured to sequentially perform pixel normalization, pixel centering, data enhancement, noise reduction processing, size adjustment, and color space conversion on the environmental image to obtain a target image for subsequent use.

[0031] The image correction unit is configured to sequentially perform radiation correction, geometric correction, image registration, image fusion, uniform light and color, image stitching, and image cropping processing on the image processed by the pixel processing unit to obtain a target optical remote sensing image.

[0032] Preferably, the feature extraction unit comprises:

[0033] A time domain feature extraction unit is configured to describe the overall characteristics of the spectral signal by using mean, variance, and standard deviation.

[0034] A frequency domain feature extraction unit is configured to convert the spectral signal to the frequency domain by Fourier transform, thereby analyzing different frequency components, or describe the distribution of the spectral signal in the frequency domain by power spectral density.

[0035] A wavelet energy feature extraction unit is configured to extract the energy of different frequency bands using wavelet transform.

[0036] An adaptive feature extraction unit is configured to adjust parameters of feature extraction according to real-time data using an adaptive filter or an adaptive signal processing algorithm.

[0037] Preferably, the model construction module comprises a model construction unit, a model training unit and a model fusion unit.

[0038] The model construction unit is configured to construct a convolutional neural network model and a feedforward neural network model respectively.

[0039] The model training unit is configured to train the convolutional neural network model based on the target data set, and then train the feedforward neural network model by taking the output of the trained convolutional neural network model as the input of the feedforward neural network model, to obtain a target multi-modal network model.

[0040] Preferably, the model construction unit comprises a first construction unit and a second construction unit.

[0041] The first construction unit is configured to construct two identical convolutional neural network models, add a BatchNorm2d layer, a nonlinear ReLU layer and an attention mechanism module after a two-dimensional convolutional layer in the convolutional neural network model, and generate a twin adversarial network model.

[0042] The second construction unit is configured to generate a convolutional neural network group based on the twin adversarial network model.

[0043] The model training unit further comprises a layer selection unit and a loss function introduction unit.

[0044] The layer selection unit is configured to reduce the input layer and the output layer of the multi-modal network model.

[0045] The loss function introduction unit is configured to introduce a cross-entropy loss function and an attention mechanism module into the multi-modal network model to reconstruct the model, to obtain the target multi-modal neural network.

[0046] Preferably, the monitoring and prediction module comprises a path planning and generation unit, a navigation accuracy self-checking algorithm unit, a real-time calibration and adjustment unit, an environmental feature recognition and matching unit and a control execution unit.

[0047] The path planning and generation unit is configured to generate a shortest path or an optimal path for the vehicle to travel according to task requirements and environmental information.

[0048] The navigation accuracy self-checking algorithm unit is configured to automatically detect the navigation accuracy by comparing the deviation between the actual travel path and the preset path.

[0049] The real-time calibration and adjustment unit is used to automatically start the calibration program when the navigation deviation exceeds the preset threshold, adjust the driving state or sensor parameters of the vehicle, and ensure that the vehicle returns to the correct path;

[0050] The environment feature recognition and matching unit is used to recognize and match specific features in the environment based on image recognition technology, and provide auxiliary positioning information; the specific features include but are not limited to road signs, fences, buildings;

[0051] The control execution unit is used to execute specific control commands according to the self-checking result and calibration instruction, and ensure that the vehicle travels according to the predetermined path; the control commands include but are not limited to adjusting the vehicle speed and steering angle.

[0052] Compared with the prior art, the present application has the following advantages and technical effects:

[0053] The present application significantly improves the navigation accuracy of the intelligent inspection vehicle through multi-sensor fusion and environment feature recognition, and the real-time self-checking and calibration mechanism enables the system to quickly adapt to changes in the breeding farm environment, enhancing the system's adaptability. Through automated self-checking and calibration, human intervention is reduced, maintenance costs and time are reduced, and the accuracy of the inspection data is further improved, providing reliable decision support for breeding farm management. BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings, which form a part of this application, are intended to provide further understanding of the application and are incorporated herein in their entirety, and the illustrative embodiments of the application and their description serve to explain the application. In the drawings:

[0055] Figure 1 The accompanying drawings, which form a part of this application, are intended to provide further understanding of the application and are incorporated herein in their entirety, and the illustrative embodiments of the application and their description serve to explain the application. In the drawings: DETAILED DESCRIPTION

[0056] It should be noted that the embodiments and features in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0057] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order than shown.

[0058] As Figure 1 shown, the present embodiment provides a navigation accuracy self-checking system for an intelligent inspection vehicle in a breeding farm, comprising:

[0059] A data acquisition module is used to acquire real-time environmental parameters of the breeding farm and state parameters of the intelligent inspection vehicle;

[0060] The data processing module is connected with the data acquisition module, and is used for data integration of the environmental parameters and the state parameters, and then data processing and analysis to obtain a target data set;

[0061] The model construction module is connected with the data processing module, and is used for constructing an initial multi-modal network model, and training the initial multi-modal network model based on the target data set to obtain a target multi-modal network model;

[0062] The monitoring prediction module is connected with the model construction module, and is used for real-time monitoring of the running state of the intelligent inspection vehicle based on the target multi-modal network model, and automatically triggering a self-checking algorithm for path calibration according to the monitoring result when the detected actual path deviates from the preset path.

[0063] Further, the data acquisition module includes a first acquisition unit and a second acquisition unit;

[0064] The first acquisition unit is used for collecting the environmental parameters of the breeding farm based on the distributed sensor to obtain an environmental image;

[0065] The second acquisition unit is used for collecting the state parameters of the intelligent inspection vehicle;

[0066] The state parameters of the intelligent inspection vehicle include but are not limited to the real-time position, speed, acceleration and direction of the intelligent inspection vehicle.

[0067] Further, the distributed sensor includes but is not limited to a laser radar, a camera and an industrial panoramic camera;

[0068] The industrial panoramic camera is arranged on the roof of the intelligent inspection vehicle, and is used for obtaining a road panoramic image of the breeding farm;

[0069] The industrial panoramic camera includes an automatic control unit, a photographing level control circuit unit and a tilt photogrammetry unit;

[0070] The photographing level control circuit unit is provided with a flexible flat cable, and the tilt photogrammetry unit is flexibly connected with the automatic control unit through the flexible flat cable; the flexible flat cable is used for controlling the on / off of the camera, photographing, focusing and feedback detection of the state of the camera, detecting whether the camera is turned on / off, detecting whether the camera has completed the photographing action and the real-time state of the camera;

[0071] The tilt photogrammetry unit is connected with the photographing level control circuit unit;

[0072] The tilt photogrammetry unit includes five high-precision cameras, and the cameras are mutually inclined and placed at a 90-degree perpendicular angle.

[0073] Further, the automatic control unit is an STM32F103 microcontroller; the crystal oscillator of the STM32F103 microcontroller is 8MHZ, and the instruction execution interval is 1us. The STM32F103 chip internally includes an AD conversion module, which includes a plurality of AD conversion units, and the AD conversion units are used for AD conversion to measure the voltage state of the camera feedback information. When using the AD conversion to measure the voltage state of the feedback information of the five cameras, a complex external AD conversion circuit is no longer needed, and the STM32F103 chip itself can complete the measurement; the serial port of the STM32F103 chip will be connected with an NB-IoT remote data control module, a Bluetooth control module, a GNSS (Beidou / GPS) positioning module and a TF card recording module; the GPIO port of the STM32F103 chip will be connected with the photographing control unit and the on-off control unit of the camera, and two GPIO ports are needed for each camera to control the on-off and photographing, and 10 GPIO ports are needed for the five cameras of the system to control the on-off and photographing of the five cameras; in addition, two AD conversions are needed for each camera, and 10 AD conversions are needed to detect the feedback of whether the camera is on or whether the camera is photographing, but the AD conversion port of the STM32F103 chip is less, and a kind of round-robin line selection method of AD conversion is needed here; in addition, the system includes five cameras, a central control system and various functional units, and a centralized power supply mode is used to maintain the consistency of the system. The camera at least includes a photographing control unit and an on-off control unit; the photographing control unit and the on-off control unit of the camera are connected with the GPIO port of the STM32F103 microcontroller.

[0074] The second acquisition unit at least includes a GPS unit and an IMU laser radar;

[0075] The GPS unit is used for acquiring the real-time position of the intelligent inspection vehicle;

[0076] The IMU laser radar is used for acquiring the speed and direction information of the intelligent inspection vehicle.

[0077] Further, the data processing module includes a data processing unit, an image processing unit and a feature extraction unit;

[0078] The data processing unit is used for denoising the original data, converting the denoised data into text data, and then merging different sources and formats of the text data;

[0079] The image processing unit is used for pixel preprocessing of the environmental image, then image correction, and obtaining a target image;

[0080] The feature extraction unit is used for feature extraction of the processed image and data.

[0081] Further, the data processing unit comprises a data cleaning unit, a text processing unit, and a data integration unit.

[0082] The data cleaning unit is configured to remove noise and outliers in raw data, and fill in missing data.

[0083] The text processing unit is configured to sequentially perform word segmentation, dictionary establishment, text vectorization, and text normalization on text data.

[0084] The data integration unit is configured to unify and merge data from different sources and formats, establish associations between data, and obtain data views.

[0085] Further, the data cleaning unit comprises:

[0086] The filtering unit is configured to reduce transient fluctuations by calculating the average value of a stationary signal within a preset time through moving average filtering, and then removing burst noise by replacing each data point with the median value within a signal window based on median filtering.

[0087] The wavelet transform unit is configured to decompose signal data into components of different frequencies through wavelet transform, and then reconstruct the signal by discarding or adjusting high-frequency noise.

[0088] The Kalman filter unit is configured to minimize estimation error by recursively filtering the current state and measurement value.

[0089] The singular value decomposition unit is configured to decompose a matrix into singular vectors and singular values, and achieve noise reduction by truncating high-frequency components.

[0090] Further, the image processing unit comprises a pixel processing unit and an image correction unit.

[0091] The pixel processing unit is configured to sequentially perform pixel normalization, pixel centering, data enhancement, noise reduction processing, size adjustment, and color space conversion on environmental images to obtain target images for subsequent use.

[0092] The image correction unit is configured to sequentially perform radiation correction, geometric correction, image registration, image fusion, uniform light and color, image stitching, and image cropping on the images processed by the pixel processing unit to obtain target optical remote sensing images.

[0093] Further, the feature extraction unit comprises:

[0094] The time domain feature extraction unit is configured to describe the overall characteristics of spectral signals through mean, variance, and standard deviation.

[0095] The frequency domain feature extraction unit is configured to convert spectral signals to the frequency domain through Fourier transform to analyze different frequency components, or describe the distribution of spectral signals in the frequency domain through power spectral density.

[0096] a wavelet capability feature extraction unit configured to extract energy of different frequency bands by using wavelet transform;

[0097] an adaptive feature extraction unit configured to adjust parameters of feature extraction according to real-time data using an adaptive filter or an adaptive signal processing algorithm.

[0098] Further, the model construction module comprises a model construction unit, a model training unit and a model fusion unit.

[0099] The model construction unit is configured to construct a convolutional neural network model and a feedforward neural network model respectively.

[0100] The model training unit is configured to train the convolutional neural network model based on a target data set, and then train the feedforward neural network model by taking the output of the trained convolutional neural network model as the input of the feedforward neural network model, to obtain a target multi-modal network model.

[0101] Further, the model construction unit comprises a first construction unit and a second construction unit.

[0102] The first construction unit is configured to construct two identical convolutional neural network models, add a BatchNorm2d layer, a nonlinear ReLU layer and an attention mechanism module after a two-dimensional convolutional layer in the convolutional neural network model, to generate a Siamese adversarial network model.

[0103] The second construction unit is configured to generate a convolutional neural network group based on the Siamese adversarial network model.

[0104] The model training unit further comprises a layer selection unit and a loss function introduction unit.

[0105] The layer selection unit is configured to reduce the input layer and the output layer of the multi-modal network model.

[0106] The loss function introduction unit is configured to introduce a cross-entropy loss function and an attention mechanism module into the multi-modal network model to reconstruct the model, to obtain a target multi-modal neural network.

[0107] Further, the convolutional neural network comprises a first convolutional layer module, a second convolutional layer module, a dense block module, a third convolutional layer module, a fully connected layer unit module and a probability conversion unit module.

[0108] The first convolutional layer module comprises a first convolutional layer module convolutional layer unit, a first convolutional layer module batch normalization layer unit and a first convolutional layer module activation function unit.

[0109] The second convolutional layer module comprises a second convolutional layer module convolutional layer unit, a second convolutional layer module batch normalization layer unit, a second convolutional layer module activation function unit and a second convolutional layer module maximum pooling layer unit.

[0110] The dense block module comprises a plurality of dense connection layer modules, wherein the dense connection layer module comprises a dense connection layer module first batch normalization layer unit, a dense connection layer module first activation function unit, a dense connection layer module first convolutional layer unit, a dense connection layer module second batch normalization layer unit, a dense connection layer module second activation function unit and a dense connection layer module second convolutional layer unit.

[0111] The third convolutional layer module comprises a third convolutional layer module convolutional layer unit, a third convolutional layer module batch normalization layer unit, a third convolutional layer module activation function unit and a third convolutional layer module average pooling layer unit.

[0112] Further, the monitoring and prediction module comprises a path planning and generation unit, a navigation accuracy self-checking algorithm unit, a real-time calibration and adjustment unit, an environmental feature recognition and matching unit and a control execution unit.

[0113] The path planning and generation unit is configured to generate a shortest path or an optimal path for the vehicle to travel according to task requirements and environmental information.

[0114] The navigation accuracy self-checking algorithm unit is configured to automatically detect the navigation accuracy by comparing the deviation of the actual travel path from the preset path.

[0115] The real-time calibration and adjustment unit is configured to automatically start a calibration program to adjust the travel state of the vehicle or the sensor parameters when the navigation deviation exceeds a preset threshold, so as to ensure that the vehicle returns to the correct path.

[0116] The environmental feature recognition and matching unit is configured to recognize and match specific features in the environment based on image recognition technology to provide auxiliary positioning information; the specific features include, but are not limited to, road signs, fences and buildings.

[0117] The control execution unit is configured to execute specific control commands according to the self-checking results and the calibration instructions to ensure that the vehicle travels along the predetermined path; the control commands include, but are not limited to, adjusting the speed and steering angle of the vehicle.

[0118] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A navigation accuracy self-checking system for a farm intelligent inspection vehicle, characterized in that, The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing method for intelligent patrol vehicles. The application relates to a data processing The real-time calibration and adjustment unit is configured to automatically start a calibration program when the navigation deviation exceeds a preset threshold, adjust the driving state or sensor parameters of the vehicle, and ensure that the vehicle returns to the correct path; The environment feature recognition and matching unit is configured to recognize and match specific features in the environment based on image recognition technology, and provide auxiliary positioning information; the specific features include road signs, fences, and buildings; The control execution unit is configured to execute specific control commands according to the self-checking result and the calibration instruction, and ensure that the vehicle drives according to the predetermined path; the control commands include adjusting the speed and steering angle of the vehicle.

2. The navigation accuracy self-checking system of the farm intelligent inspection vehicle according to claim 1, characterized in that, The data acquisition module includes a first acquisition unit and a second acquisition unit; The first acquisition unit is configured to collect environmental parameters of the farm based on distributed sensors, and obtain environmental images; The second acquisition unit is configured to acquire state parameters of the intelligent inspection vehicle; The state parameters of the intelligent inspection vehicle include real-time position, speed, acceleration, and direction of the intelligent inspection vehicle.

3. The navigation accuracy self-checking system of the farm intelligent inspection vehicle according to claim 2, characterized in that, The distributed sensors include a laser radar, a camera, and an industrial panoramic camera; The industrial panoramic camera is arranged on the roof of the intelligent inspection vehicle, and is configured to obtain a road panoramic image of the farm; The industrial panoramic camera includes an automatic control unit, a photographing level control circuit unit, and a tilt photogrammetry unit; The photographing level control circuit unit is provided with a flexible flat cable, and the tilt photogrammetry unit is flexibly connected with the automatic control unit through the flexible flat cable; the flexible flat cable is configured to control the on / off, photographing, focusing of the camera, and feedback detection of the state of the camera, detect whether the camera is turned on / off, whether the camera has completed the photographing action, and the real-time state of the camera; The tilt photogrammetry unit is connected with the photographing level control circuit unit; The tilt photogrammetry unit includes five high-precision cameras, which are arranged at a mutual tilt angle of 90 degrees. The second acquisition unit includes at least a GPS unit and an IMU laser radar; The GPS unit is configured to obtain the real-time position of the intelligent inspection vehicle; The IMU laser radar is configured to obtain the speed and direction information of the intelligent inspection vehicle.

4. The navigation accuracy self-checking system of the farm intelligent inspection vehicle according to claim 1, characterized in that, The data processing unit includes a data cleaning unit, a text processing unit, and a data integration unit; The data cleaning unit is configured to remove noise and outliers in the original data, and fill in missing data; The text processing unit is configured to sequentially perform word segmentation, dictionary establishment, text vectorization, and text normalization processing on the text data; The data integration unit is configured to unify and merge data from different sources and formats, establish associations between data, and obtain data views.

5. The navigation accuracy self-checking system of the farm intelligent inspection vehicle according to claim 1, characterized in that, The image processing unit includes a pixel processing unit and an image correction unit; The pixel processing unit is configured to sequentially perform pixel normalization, pixel centering, data enhancement, noise reduction processing, size adjustment, and color space conversion on the environmental image, and obtain a target image for subsequent use; The image correction unit is used for sequentially performing radiation correction, geometric correction, image registration, image fusion, light and color uniformity, image stitching and image cutting processing on the image processed by the pixel processing unit, so as to obtain a target optical remote sensing image.

6. The navigation accuracy self-checking system of the farm intelligent inspection vehicle according to claim 1, characterized in that, The feature extraction unit comprises: A time domain feature extraction unit is used for describing the overall characteristics of the spectral signal by using mean value, variance and standard deviation; A frequency domain feature extraction unit is used for converting the spectral signal to the frequency domain by using Fourier transform, so as to analyze different frequency components, or describing the distribution of the spectral signal in the frequency domain by using power spectral density; A wavelet energy feature extraction unit is used for extracting the energy of different frequency bands by using wavelet transform; An adaptive feature extraction unit is used for adjusting the parameters of feature extraction according to real-time data by using adaptive filter or adaptive signal processing algorithm.

Images