Complex Field Environment Research Articles

Research on Dynamic Seal Friction Torque Compensation for a Low-Slow-Small UAV Tracking System

To ensure reliable and accurate operation in a complex field environment for Low-Slow-Small unmanned aerial vehicle (LSS-UAV) tracking systems, a dynamic seal shafting structure consisting of a labyrinthine structure and a magnetic fluid seal ring is designed to protect important equipment, such as the infrared sensor, visible CCD and the laser rangefinder from erosion and oxidation by the external environment. A friction torque model is established for the system’s dynamic seal structure to ensure tracking accuracy of the system. The simulation results show that the closed-loop speed accuracy of the system is improved by nearly 10 fold after adding friction torque compensation. The actual test results show that including friction torque compensation can effectively reduce the start-up delay and speed fluctuation error, and the speed fluctuation error is reduced by more than 80% compared to that without friction torque compensation. The tracking accuracy of the dynamic LSS-UAV is reduced from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$56.44 \mu $ </tex-math></inline-formula> rad to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$14.86 \mu $ </tex-math></inline-formula> rad after adding friction torque compensation, which meets the requirement of smooth and accurate tracking for LSS-UAV tracking systems, and verifies the effectiveness and accuracy of compensation for the dynamic seal friction torque.

Detection of Camellia oleifera Fruit in Complex Scenes by Using YOLOv7 and Data Augmentation

Rapid and accurate detection of Camellia oleifera fruit is beneficial to improve the picking efficiency. However, detection faces new challenges because of the complex field environment. A Camellia oleifera fruit detection method based on YOLOv7 network and multiple data augmentation was proposed to detect Camellia oleifera fruit in complex field scenes. Firstly, the images of Camellia oleifera fruit were collected in the field to establish training and test sets. Detection performance was then compared among YOLOv7, YOLOv5s, YOLOv3-spp and Faster R-CNN networks. The YOLOv7 network with the best performance was selected. A DA-YOLOv7 model was established via the YOLOv7 network combined with various data augmentation methods. The DA-YOLOv7 model had the best detection performance and a strong generalisation ability in complex scenes, with mAP, Precision, Recall, F1 score and average detection time of 96.03%, 94.76%, 95.54%, 95.15% and 0.025 s per image, respectively. Therefore, YOLOv7 combined with data augmentation can be used to detect Camellia oleifera fruit in complex scenes. This study provides a theoretical reference for the detection and harvesting of crops under complex conditions.

Robust Registration of Rail Profile and Complete Detection of Outliers in Complex Field Environment

The accurate measurement of rail wear is critical in track quality inspection. Usually, by matching the measured profile with the standard one based on the unworn rail waist double circle segment (DCS), and comparing their railhead differences, we obtain the rail wear. However, in the complex field environment, this task becomes tricky. For profile registration, one is that the location of rail waist becomes difficult with lots of outliers mixed in the profile, and the other is that the obtained rail waist could be polluted or incomplete. For wear measurement, the outliers scattered on the railhead could cause serious errors. This paper is devoted to solving the above problems. For problem 1, firstly, the rail waist is located after a preprocessing procedure. Then, utilizing the proposed hybrid model called R-H-ICP, we realize the profile registration with a process from coarse to fine. For problem 2, by using the standard profile and the reconstructed one with wear constraints to serve as the template separately, and computing the distance from each point of railhead on measured profile to the template, both the distinct and the inapparent outliers are detected precisely. The efficiency and superiority of proposed methods were verified by vast experiments. For the former, compared with DCS and ICP, the R-H-ICP not only improves the profile utilization ratio obviously, also guarantees the registration accuracy as far as possible. For the latter, the F1-Measure average score of outlier detection reaches 0.998, which outperforms some classical models markedly.

Point-line feature fusion based field real-time RGB-D SLAM

3D reconstruction of crops is important for researching their biological properties, canopy light distribution and robotic harvesting. However, the complex field environment makes the real-time 3D reconstruction of crops difficult. Due to the low-textured in the field, it is difficult to obtain effective features to construct accurate and real-time 3D maps of the field from existing single-feature SLAM methods. In this paper, we propose a novel RGB-D SLAM based on point-line feature fusion for the real-time field 3D scene reconstruction. By optimizing the point-line features joint poses, we first build a 3D scene map of the field based on the point-line feature structure. Then, a joint point cloud filtering method is designed based on the keyframes optimization of the point-line feature. Finally, we obtain the consistently high-quality dense map in the global respect. The overall performance in terms of pose estimation and reconstruction is evaluated on public benchmarks and shows improved performance compared to state-of-the-art methods. Qualitative experiments on the field scenes show that our method enables real-time 3D reconstruction of crops with high robustness.

Research on Field Soybean Weed Identification Based on an Improved UNet Model Combined With a Channel Attention Mechanism.

Aiming at the problem that it is difficult to identify two types of weeds, grass weeds and broadleaf weeds, in complex field environments, this paper proposes a semantic segmentation method with an improved UNet structure and an embedded channel attention mechanism SE module. First, to eliminate the semantic gap between low-dimensional semantic features and high-dimensional semantic features, the UNet model structure is modified according to the characteristics of different types of weeds, and the feature maps after the first five down sampling tasks are restored to the same original image through the deconvolution layer. Hence, the final feature map used for prediction is obtained by the fusion of the upsampling feature map and the feature maps containing more low-dimensional semantic information in the first five layers. In addition, ResNet34 is used as the backbone network, and the channel attention mechanism SE module is embedded to improve useful features. The channel weight is determined, noise is suppressed, soybean and grass weeds are identified, and broadleaf weeds are extracted through digital image morphological processing, and segmented images of soybean plants, grass weeds and broadleaf weeds are generated. Moreover, compared with the standard semantic segmentation models, FCN, UNet, and SegNet, the experimental results show that the overall performance of the model in this paper is the best. The average intersection ratio and average pixel recognition rate in a complex field environment are 0.9282 and 96.11%, respectively. On the basis of weed classification, the identified weeds are further refined into two types of weeds to provide technical support for intelligent precision variable weed spraying.

Real-Time Human Motion Capture Based on Wearable Inertial Sensor Networks

Wearable inertial motion capture, a new type of motion capture technology, mainly estimates the human posture in 3-D space through multisensor data fusion. The available method for sensor fusion is usually aided by magnetometers to remove the drift error in yaw angle estimation, which in turn limits their application in the presence of a complex magnetic field environment. In this article, an extended Kalman filter (EKF) data fusion method is proposed to fuse the 9-axis sensor data. Meanwhile, the heuristic drift reduction (HDR) method is used to calibrate the accumulated error of a heading angle. In addition, the position in 3-D space is estimated by the foot-mounted zero-velocity-update (ZUPT) technique. Combining 3-D attitude and position, a biomechanical model of the human body is established to track the motion of a real human body. The EKF algorithm and position estimation methods are benchmarked against the golden standard, optical motion capture system, for various indoor experiments. In addition, various outdoor experiments are also conducted to verify the reliability of the proposed method. The results show that the proposed algorithm outperforms the available attitude estimation model in motion tracking and is feasible for 3-D human motion capture.

Camera Calibration for Long-Distance Photogrammetry Using Unmanned Aerial Vehicles

The traditional target-dependent camera calibration method has been widely used in close-distance and small field of view scenes. However, in view of the field coordinate measurement in the large-scale monitoring area under the complex field environment, the standard target can hardly meet the requirements of covering most of the camera’s field of view. In view of the above problem, a stereo camera calibration method is studied, using the unmanned aerial vehicles (UAV) as feature points, combined with the high-precision position information measured by the real-time kinematic (RTK) positioning system it carries. The measured UAV coordinates are unified in World Geodetic System 1984 (WGS-84). Therefore, through several preset points, the measurement reference coordinate system which is the new world coordinate system we need can be established in any monitoring area, which greatly improves the flexibility of measurement. The experimental results show that the measurement accuracy of the proposed method can reach 0.5% in the monitoring area with a diameter of 100 m. The calibration method has a wide range of application and does not need the traditional standard target, and the measurement reference coordinate system can be established according to the actual needs. It is suitable for field spatial coordinate measurement in long-distance and complex terrain environment.

A hybrid network architecture by integrating both 2.4 GHz network and Sub-GHz network and its application in field environment surveillance system

Various networks, many of which are composed of embedded systems, are interconnected to form Internet of Things (IoT), in order to cooperate to provide more intelligent service for people. It can be imagined that the networks integration in IoT will be challenged, because different networks are heterogeneous and differ in terms of topology, coverage, data rate, power consumption, etc. That's to say that the key for networks integration will be focused on how to combine the benefits of various networks effectively. In this paper, a hybrid network architecture aiming at combining the benefits of two commonly used wireless networks, 2.4 GHz network and Sub-GHz network, is proposed. The architecture consists of four parts: 2.4 GHz Network, Sub-GHz Network, Cloud-Based Server and Mobile Application. It should be noted that our design intent is to make full use of the advantages of various networks, while minimizing the new standardization or changes to current network specifications. Then a field surveillance environment system is implemented to present proposed architecture's potentiality of being adaptive to complex scenarios, and how to build a practical system based on proposed architecture. Not only the system overall design is presented, in which the specific protocols used in 2.4 GHz network and Sub-GHz network are chosen according to the field environment surveillance scenario, but also the detailed hardware and software implementation of the system is presented. Finally, the experimental performance evaluation of field environment surveillance system is presented. The experimental results show that the proposed architecture and implemented system are adaptive to complex field environment, and have good agreement with our design intent.

Research on Identification Technology of Field Pests with Protective Color Characteristics

Accurate identification of field pests has crucial decision-making significance for integrated pest control. Most current research focuses on the identification of pests on the sticky card or the case of great differences between the target and the background. There is little research on field pest identification with protective color characteristics. Aiming at the problem that it is difficult to identify pests with protective color characteristics in the complex field environment, a field pest identification method based on near-infrared imaging technology and YOLOv5 is proposed in this paper. Firstly, an appropriate infrared filter and ring light source have been selected to build an image acquisition system according to the wavelength with the largest spectral reflectance difference between the spectral curves of the pest (Pieris rapae) and its host plants (cabbage), which are formed by specific spectral characteristics. Then, field pest images have been collected to construct a data set, which has been trained and tested through YOLOv5. Experimental results demonstrate that the average time required to detect one pest image is 0.56 s, and the mAP reaches 99.7%.

Spatial Location of Sugarcane Node for Binocular Vision-Based Harvesting Robots Based on Improved YOLOv4

Spatial location of sugarcane nodes using robots in agricultural conditions is a challenge in modern precision agriculture owing to the complex form of the sugarcane node when wrapped with leaves and the high computational demand. To solve these problems, a new binocular location method based on the improved YOLOv4 was proposed in this paper. First, the YOLOv4 deep learning algorithm was improved by the Channel Pruning Technology in network slimming, so as to ensure the high recognition accuracy of the deep learning algorithm and to facilitate transplantation to embedded chips. Secondly, the SIFT feature points were optimised by the RANSAC algorithm and epipolar constraint, which greatly reduced the mismatching problem caused by the similarity between stem nodes and sugarcane leaves. Finally, by using the optimised matching point to solve the homography transformation matrix, the space location of the sugarcane nodes was for the first time applied to the embedded chip in the complex field environment. The experimental results showed that the improved YOLOv4 algorithm reduced the model size, parameters and FLOPs by about 89.1%, while the average precision (AP) of stem node identification only dropped by 0.1% (from 94.5% to 94.4%). Compared with other deep learning algorithms, the improved YOLOv4 algorithm also has great advantages. Specifically, the improved algorithm was 1.3% and 0.3% higher than SSD and YOLOv3 in average precision (AP). In terms of parameters, FLOPs and model size, the improved YOLOv4 algorithm was only about 1/3 of SSD and 1/10 of YOLOv3. At the same time, the average locational error of the stem node in the Z direction was only 1.88 mm, which totally meets the demand of sugarcane harvesting robots in the next stage.

Geoelectric field response characteristics analysis of floor roadway surrounding rock fracture caused due to coal seam mining

The fracture of rocks surrounding the floor roadway during the mining of the working face of a coal mine is a complicated spatiotemporal process due to the superimposed action of multiple stress fields on the surrounding rock mass. Using the surrounding rock of a floor roadway in the working face of the Huainan Pan’er Mine as the research subject, we conducted real-time monitoring using geoelectric field monitoring technology, and found the spatiotemporal response law of the geoelectric field in the process of regional rupture and damage of engineering rock masses under a complex stress field environment. The results show that (1) the time series response characteristics and spatial distribution of the geoelectric field signal are closely related to the stress distribution and damage evolution of the surrounding rock mass; (2) the rupture and damage degree of the goaf floor significantly increased when the working face was pushed through the monitoring area for 20–40 m. During this process, the excitation current dropped by 4–12 mA, and the self-potential pulse fluctuation amplitude was greater than 400 mV; (3) from the beginning of the monitoring process to the end of the monitoring, the self-potential in the damaged area decreased by 250 mV, and the self-potential in the mudstone layer below the damaged area increased by 140 mV. The electrons released into the environment around the damaged rock mass during the severe impact phase of mining did not flow back to the damaged area, and the positive charge in the damaged rock mass gradually accumulated in the complete rock mass in units of rock strata; (4) when superimposed and supported by anchor rod and cables, the bearing capacity of the shallow bearing circle of the roadway was enhanced, and the excitation current presented a step-like overall increase during mining of the working face with a small drop after every significant increase. This result is of significance in monitoring the evolutionary process of real-time failure of rock masses under complex stress environments using geoelectric field information and in improving the quality of geoelectric field monitoring technology testing applications in the future.

Dynamic walking characteristics and control of four-wheel mobile robot on ultra-high voltage multi-split transmission line

High-voltage lines are an important channel for power transmission, and multi-split transmission lines are the main strength of power transmission. Compared with double-wheel single-wire maintenance robots, ultra-high-voltage multi-split transmission lines and four-wheel mobile robots have a wider application range and greater demand. The maintenance of multi-split transmission lines relies on the stable walking and control of four-wheel mobile robots on heterogeneous multi-split transmission lines. However, uncertain disturbance factors such as wind load in the complex field environment cause vibration of double-split and quad-split lines. The slight change in the line spacing causes the line contact to the edge of the robot’s walking wheel, which increases the friction during the robot’s walking. It also directly hinder the movement of the robot on the multi-split transmission line, thus restricting the completion of the robot’s maintenance operation. Based on the analysis, this paper establishes a mathematical model of the external force disturbance influence on the spacing of the double-split lines. At the same time, the robot walking mechanics characteristics model under the change of the line space has been established. Three different forms of the robot walking online have been obtained through abstraction processing. A method of side friction identification based on fuzzy control has been proposed, through the online monitoring of the friction between line and edge of the walking wheel, the robot walking wheel motor walking force can be intelligently controlled in real time, and effectively avoids the “wheel-line” jam phenomenon under the external uncertain factors in the field environment. Finally, the feasibility and engineering practicability of the method have been verified through MATLAB/ADAMS simulation and field operation experiments. Therefore, the automation and intelligence level of the operation and the transmission system maintenance management has been improved.

Accurate Wheat Lodging Extraction from Multi-Channel UAV Images Using a Lightweight Network Model.

The extraction of wheat lodging is of great significance to post-disaster agricultural production management, disaster assessment and insurance subsidies. At present, the recognition of lodging wheat in the actual complex field environment still has low accuracy and poor real-time performance. To overcome this gap, first, four-channel fusion images, including RGB and DSM (digital surface model), as well as RGB and ExG (excess green), were constructed based on the RGB image acquired from unmanned aerial vehicle (UAV). Second, a Mobile U-Net model that combined a lightweight neural network with a depthwise separable convolution and U-Net model was proposed. Finally, three data sets (RGB, RGB + DSM and RGB + ExG) were used to train, verify, test and evaluate the proposed model. The results of the experiment showed that the overall accuracy of lodging recognition based on RGB + DSM reached 88.99%, which is 11.8% higher than that of original RGB and 6.2% higher than that of RGB + ExG. In addition, our proposed model was superior to typical deep learning frameworks in terms of model parameters, processing speed and segmentation accuracy. The optimized Mobile U-Net model reached 9.49 million parameters, which was 27.3% and 33.3% faster than the FCN and U-Net models, respectively. Furthermore, for RGB + DSM wheat lodging extraction, the overall accuracy of Mobile U-Net was improved by 24.3% and 15.3% compared with FCN and U-Net, respectively. Therefore, the Mobile U-Net model using RGB + DSM could extract wheat lodging with higher accuracy, fewer parameters and stronger robustness.

Target Positioning Optimization Method in Power System

This thesis presents a method that a position measurement method for moving targets is proposed based on the positioning method based on the time difference of arrival (TDOA) which is based on the research on the positioning problem of station inspection operators and equipment in complex working conditions. The probability error method is introduced to optimize the traditional positioning method that realizes the target node positioning by optimizing the distance difference between the target node to be located in the network domain environment and different base stations, which can effectively improve the positioning accuracy of staff and equipment in the station. Through experiments in a complex power frequency electric field environment, the test results show that the results calculated by the optimization method are better than the existing traditional positioning methods, and can effectively improve the positioning accuracy under the condition of line-of-sight, and realize the substation space Mobile target positioning to ensure the safety of operators.

Statistical distribution modelling and parameter identification of the dynamic stress spectrum of a tractor front driven axle

The reliability data from the front driven axle of a four-wheel drive tractor exhibits a multi-peak distribution because of the complex field environment. The aim of this study was to establish an accurate statistical model for the dynamic stress spectrum with mixed distributions. Using rain-flow counting, the stress-time history of the tractor was transformed into the rain-flow matrix with two parameters. The mean and range of the stress data in the rain-flow domain was modelled with the mixed Gaussian and Weibull distributions, respectively. The identification of unknown parameters is an important and here a novel parameter identification method that adopts a genetic algorithm (GA) for rapid searching was proposed with the generalised reduced gradient (GRG) method was applied for accurate identification. The results of finite element analysis (FEA) provide reference for the selection of the measured points. To obtain the dynamic strain signal, a real-time test system was built and a field experiment was carried out. The calculation and evaluation results confirmed that this approach precisely estimated parameters and established a highly accurate mixed model. For the mixed Gaussian and Weibull distributions, the determination coefficients R 2 exceed 0.98 and the maximum KS test values were not more than 0.2. Furthermore, this study provided accurate model parameters to determine the stress spectrum for the full-life cycle for use in future research. • Statistical modelling of axle data by mixed Gaussian and Weibull distributions. • Unknown model parameters estimated by combining intelligent algorithm. • Goodness of fit test can be adopted to evaluate parameter identification results. • Accurate statistical model for study of agricultural machinery fatigue reliability.

Research on Spatial Positioning System of Fruits to be Picked in Field Based on Binocular Vision and SSD Model

The accurate fruit recognition in the field was one of the key technologies of fruit picking agricultural robots. An improved Single Shot Multi-Box Detector (SSD) model based on the color and morphological characteristics of fruit was proposed in this paper when aimed at the large collection workload and low secondary transfer efficiency of fruit such as palm fruit, durian, pineapple and other fruits grown in a complex field environment. A binocular depth camera RealSense D435i was used to collect images of the fruit to be picked in the field. Meanwhile, the MobileNet was replaced with the VGG16 basic network based on the Tensor-flow deep learning framework to reduce the amount of convolution operations for extracting image features in the SSD model, and a spatial positioning system for pineapple fruit was designed. Furtherly, experiments showed that the improved SSD depth detection model had a smaller size and it was more convenient to be deployed on the mobile end of agricultural robots, which the model had a high accuracy in the effective recognition of the fruits to be picked under the weed occlusion and overlapping scenes. The frame rate of the video reading and detection for the binocular depth camera reached 16.74 Frames Per Second (FPS), which had good robustness and real-time, and a good solution for the automatic picking of agricultural picking robots could be provided in the field.

Application Research on BIM+AR Technology in Construction Safety Management

Safety management is an important work in the field of construction. Traditional safety management methods cannot simulate the complex field environment. At the same time, it can’t allow real-time interaction between safety managers and field workers. Combined with BIM and AR technology, it is great of practical significance for the application on construction safety management. We discuss the safety management problem from the whole process of the project life cycle, which will have certain reference value for improving the construction safety management level of the whole industry. This paper first analyzes the current situation of building safety management. This paper first analyzes the current situation of building safety management. Then, this paper makes clear the development and advantages of Building Information Modeling(hereinafter referred to as BIM ) and Augmented Reality (hereinafter referred to as AR ) technology. Finally, this paper analyzes the application of BIM+AR technology in building safety management.

Metabolomic study of volatile compounds emitted by lavender grown under open-field conditions: a potential approach to investigate the yellow decline disease.

Fine lavender and lavandin are perfume and medicinal plants originate from the South of France and are widely cultivated for their essential oils. Recently, cultivated plants suffered from a severe decline in France, due to the propagation of the yellow decline disease. This disease is caused by the stolbur phytoplasma, a bacterium transmitted by a sap-sucking insect, the planthopper. In order to understand the complex relationships between host plant, pest, pathogen and environment responsible for the yellow decline of lavender, we use a metabolomic approach to highlight changes in chemical emissions from asymptomatic ("healthy") and symptomatic ("infected") plants. Volatile compounds produced by fine lavender and lavandin were collected in the field using a dynamic headspace extraction approach. Afterwards, compounds trapped on Tenax adsorbent were thermodesorbed and analysed using an automated thermal desorption-gas chromatography-mass spectrometry (ATD-GC-MS). Multivariate statistical analyses was performed using principal component analysis and partial least square discriminant analyses. The untargeted screening of volatiles allowed the separation of asymptomatic and symptomatic plants according to their emissions. The approach was sufficiently accurate so as to separate the emissions according to the different stages of infection. Twelve compounds were found to be deregulated metabolites of yellow disease infection, common to fine lavender (variety 7713) and lavandin (variety abrial). The metabolomic approach allowed for the effective identification of chemical variations between infected and healthy plants in a complex field environment.

Northern Maize Leaf Blight Detection Under Complex Field Environment Based on Deep Learning

Northern maize leaf blight is one of the major diseases that endanger the health of maize. The complex background of the field and different light intensity make the detection of diseases more difficult. A multi-scale feature fusion instance detection method, based on convolutional neural network, is proposed to detect maize leaf blight. The proposed technique incorporates three major steps of data set preprocessing part, fine-tuning network and detection module. In the first step, the improved retinex is used to process data sets, which successfully solves the problem of poor detection effects caused by high-intensity light. In the second step, the improved RPN is utilized to adjust the anchor box of diseased leaves. The improved RPN network identifies and deletes negative anchors, which reduces the search space of the classifier and provides better initial information for the detection network. In this paper, a transmission module is designed to connect the fine-tuning network with the detection module. On the one hand, the transmission module fuses the features of the low-level and high-level to improve the detection accuracy of small target diseases. On the other hand, the transmission module converts the feature map associated with the fine-tuning network to the detection module, thus realizing the feature sharing between the detection module and the fine-tuning network. In the third step, the detection module takes the optimized anchor as input, focuses on detecting the diseased leaves. By sharing the features of the transmission module, the time-consuming process of using candidate regions layer by layer to detect is eliminated. Therefore, the efficiency of the whole model has reached the efficiency of the one-stage model. In order to further optimize the detection effect of the model, we replace the loss function with generalized intersection over union (GIoU). After 60000 iterations, the highest mean average precision (mAP) reaches 91.83%. The experimental results indicate that the improved model outperforms several existing methods in terms of greater precision and frames per second (FPS).

Navigation Algorithm Based on the Boundary Line of Tillage Soil Combined with Guided Filtering and Improved Anti-Noise Morphology.

An improved anti-noise morphology vision navigation algorithm is proposed for intelligent tractor tillage in a complex agricultural field environment. At first, the two key steps of guided filtering and improved anti-noise morphology navigation line extraction were addressed in detail. Then, the experiments were carried out in order to verify the effectiveness and advancement of the presented algorithm. Finally, the optimal template and its application condition were studied for improving the image-processing speed. The comparison experiment results show that the YCbCr color space has minimum time consumption of in comparison with HSV, HIS, and 2R-G-B color spaces. The guided filtering method can effectively distinguish the boundary between the tillage soil compared to other competing vanilla methods such as Tarel, multi-scale retinex, wavelet-based retinex, and homomorphic filtering in spite of having the fastest processing speed of . The extracted soil boundary line of the improved anti-noise morphology algorithm has the best precision and speed compared to other operators such as Sobel, Roberts, Prewitt, and Log. After comparing different sizes of image templates, the optimal template with the size of pixels could achieve high-precision vision navigation while the course deviation angle was not more than . The maximum tractor speed of the optimal template and global template were and , respectively, which can meet the real-time vision navigation requirement of the smart tractor tillage operation in the field. The experimental vision navigation results demonstrated the feasibility of the autonomous vision navigation for tractor tillage operation in the field using the tillage soil boundary line extracted by the proposed improved anti-noise morphology algorithm, which has broad application prospect.