scholarly journals Autonomous Identification and Positioning of Trucks during Collaborative Forage Harvesting

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1166
Author(s):  
Wei Zhang ◽  
Liang Gong ◽  
Suyue Chen ◽  
Wenjie Wang ◽  
Zhonghua Miao ◽  
...  
Keyword(s):  
Field Experiments ◽  
Absolute Error ◽  
Identification Accuracy ◽  
Depth Image ◽  
Dynamic Identification ◽  
Random Sample Consensus ◽  
Harvesting Efficiency ◽  
Value Decomposition ◽  
Forage Harvester ◽  
Ransac Algorithm

In the process of collaborative operation, the unloading automation of the forage harvester is of great significance to improve harvesting efficiency and reduce labor intensity. However, non-standard transport trucks and unstructured field environments make it extremely difficult to identify and properly position loading containers. In this paper, a global model with three coordinate systems is established to describe a collaborative harvesting system. Then, a method based on depth perception is proposed to dynamically identify and position the truck container, including data preprocessing, point cloud pose transformation based on the singular value decomposition (SVD) algorithm, segmentation and projection of the upper edge, edge lines extraction and corner points positioning based on the Random Sample Consensus (RANSAC) algorithm, and fusion and visualization of results on the depth image. Finally, the effectiveness of the proposed method has been verified by field experiments with different trucks. The results demonstrated that the identification accuracy of the container region is about 90%, and the absolute error of center point positioning is less than 100 mm. The proposed method is robust to containers with different appearances and provided a methodological reference for dynamic identification and positioning of containers in forage harvesting.

scholarly journals Fast Image Registration for Spacecraft Autonomous Navigation Using Natural Landmarks

2018 ◽  
Vol 2018 ◽  
pp. 1-12
Author(s):  
Yun-Hua Wu ◽  
Lin-Lin Ge ◽  
Feng Wang ◽  
Bing Hua ◽  
Zhi-Ming Chen ◽  
...  
Keyword(s):  
Image Registration ◽  
Autonomous Navigation ◽  
Computational Cost ◽  
Segmentation Algorithm ◽  
Speeded Up Robust Features ◽  
Speed Up ◽  
Random Sample Consensus ◽  
Invariant Properties ◽  
Low Computational Cost ◽  
Ransac Algorithm

In order to satisfy the real-time requirement of spacecraft autonomous navigation using natural landmarks, a novel algorithm called CSA-SURF (chessboard segmentation algorithm and speeded up robust features) is proposed to improve the speed without loss of repeatability performance of image registration progress. It is a combination of chessboard segmentation algorithm and SURF. Here, SURF is used to extract the features from satellite images because of its scale- and rotation-invariant properties and low computational cost. CSA is based on image segmentation technology, aiming to find representative blocks, which will be allocated to different tasks to speed up the image registration progress. To illustrate the advantages of the proposed algorithm, PCA-SURF, which is the combination of principle component analysis and SURF, is also analyzed in this paper for comparison. Furthermore, random sample consensus (RANSAC) algorithm is applied to eliminate the false matches for further accuracy improvement. The simulation results show that the proposed strategy obtains good results, especially in scaling and rotation variation. Besides, CSA-SURF decreased 50% of the time in extraction and 90% of the time in matching without losing the repeatability performance by comparing with SURF algorithm. The proposed method has been demonstrated as an alternative way for image registration of spacecraft autonomous navigation using natural landmarks.

scholarly journals Research on Dynamic Identification of Servo Motor Load Inertia Based on the Error Gain Factor Model

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6664
Author(s):  
Fang Xie ◽  
Fei Yu ◽  
Chaochen An
Keyword(s):  
Factor Model ◽  
Slow Motion ◽  
Gain Factor ◽  
Moment Of Inertia ◽  
Identification Accuracy ◽  
Identification Algorithm ◽  
Servo Motor ◽  
Dynamic Identification ◽  
Identification Method ◽  
The Moment

Aiming at solving the problems of slow motion and positioning deviation caused by the change of the moment of inertia of the servo motor due to different loads, an identification method for the moment of inertia on the basis of the error gain factor model is introduced into the controller, so that the moment of inertia can be obtained accurately and quickly under dynamic conditions. First, the electromagnetic and motion equation of the permanent magnet synchronous motor is built, and the logical relationship between the moment of inertia, torque, speed and other physical quantities is derived, so that the moment of inertia can be dynamically acquired. Second, in order to increase the identification accuracy, an adaptive function is introduced in the inertia identification model to replace the fixed parameters as an error gain factor (EGF). Third, the accuracy parameter is defined, and the identification algorithm on the basis of the EGF model is compared with the accuracy parameters of the existing identification method, which verifies that the improved algorithm has a better accuracy and speed. Finally, on the experimental platform, the working condition of unsteady speed is simulated. It is further verified that the proposed method has a high anti-interference capability.

scholarly journals Toward efficacy of piecewise polynomial truncated singular value decomposition algorithm in moving force identification

2019 ◽  
Vol 22 (12) ◽  
pp. 2687-2698 ◽  
Author(s):  
Zhen Chen ◽  
Lifeng Qin ◽  
Shunbo Zhao ◽  
Tommy HT Chan ◽  
Andy Nguyen
Keyword(s):  
Singular Value Decomposition ◽  
Singular Values ◽  
Singular Value ◽  
Decomposition Algorithm ◽  
Identification Accuracy ◽  
Piecewise Polynomial ◽  
Truncated Singular Value Decomposition ◽  
Force Identification ◽  
Moving Force ◽  
Value Decomposition

This article introduces and evaluates the piecewise polynomial truncated singular value decomposition algorithm toward an effective use for moving force identification. Suffering from numerical non-uniqueness and noise disturbance, the moving force identification is known to be associated with ill-posedness. An important method for solving this problem is the truncated singular value decomposition algorithm, but the truncated small singular values removed by truncated singular value decomposition may contain some useful information. The piecewise polynomial truncated singular value decomposition algorithm extracts the useful responses from truncated small singular values and superposes it into the solution of truncated singular value decomposition, which can be useful in moving force identification. In this article, a comprehensive numerical simulation is set up to evaluate piecewise polynomial truncated singular value decomposition, and compare this technique against truncated singular value decomposition and singular value decomposition. Numerically simulated data are processed to validate the novel method, which show that regularization matrix [Formula: see text] and truncating point [Formula: see text] are the two most important governing factors affecting identification accuracy and ill-posedness immunity of piecewise polynomial truncated singular value decomposition.

scholarly journals User Embedding for Rating Prediction in SVD++-Based Collaborative Filtering

Symmetry ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 121 ◽  
Author(s):  
Wenchuan Shi ◽  
Liejun Wang ◽  
Jiwei Qin
Keyword(s):  
Collaborative Filtering ◽  
Absolute Error ◽  
Rating Data ◽  
Latent Features ◽  
Collaborative Filtering Algorithm ◽  
Rating Prediction ◽  
Value Decomposition ◽  
Linear Interactions ◽  
Information Values ◽  
Explicit Feedback

The collaborative filtering algorithm based on the singular value decomposition plus plus (SVD++) model employs the linear interactions between the latent features of users and items to predict the rating in the recommendation systems. Aiming to further enrich the user model with explicit feedback, this paper proposes a user embedding model for rating prediction in SVD++-based collaborative filtering, named UE-SVD++. We exploit the user potential explicit feedback from the rating data and construct the user embedding matrix by the proposed user-wise mutual information values. In addition, the user embedding matrix is added to the existing user bias and implicit parameters in the SVD++ to increase the accuracy of the user modeling. Through extensive studies on four different datasets, we found that the rating prediction performance of the UE-SVD++ model is improved compared with other models, and the proposed model’s evaluation indicators root-mean-square error (RMSE) and mean absolute error (MAE) are decreased by 1.002–2.110% and 1.182–1.742%, respectively.

scholarly journals P-RANSAC: An Integrity Monitoring Approach for GNSS Signal Degraded Scenario

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Gaetano Castaldo ◽  
Antonio Angrisano ◽  
Salvatore Gaglione ◽  
Salvatore Troisi
Keyword(s):  
Computer Vision ◽  
Random Sample ◽  
Simultaneous Presence ◽  
Static Test ◽  
Navigation Solution ◽  
Processing Data ◽  
Urban Scenario ◽  
Random Sample Consensus ◽  
Quality Check ◽  
Ransac Algorithm

Satellite navigation is critical in signal-degraded environments where signals are corrupted and GNSS systems do not guarantee an accurate and continuous positioning. In particular measurements in urban scenario are strongly affected by gross errors, degrading navigation solution; hence a quality check on the measurements, defined as RAIM, is important. Classical RAIM techniques work properly in case of single outlier but have to be modified to take into account the simultaneous presence of multiple outliers. This work is focused on the implementation of random sample consensus (RANSAC) algorithm, developed for computer vision tasks, in the GNSS context. This method is capable of detecting multiple satellite failures; it calculates position solutions based on subsets of four satellites and compares them with the pseudoranges of all the satellites not contributing to the solution. In this work, a modification to the original RANSAC method is proposed and an analysis of its performance is conducted, processing data collected in a static test.

Pipeline Leakage Recognition Based on the Projection Singular Value Features and Support Vector Machine

2010 ◽  
Author(s):  
Mingda Wang ◽  
Laibin Zhang ◽  
Wei Liang ◽  
Jinqiu Hu
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Field Experiments ◽  
Small Sample ◽  
Singular Value ◽  
Support Vector ◽  
Leakage Detection ◽  
Feature Extraction Method ◽  
Standard Bases ◽  
Value Decomposition

Identification of negative pressure waveform is the key of pipeline leakage detection. The feature extraction and the choice of the classifier are two main contents to solve the recognition problem. In this paper, a new feature extraction method based on the Projection Singular Value is presented. First of all, the two orthogonal singular value decomposition matrixes of the typical leakage waveform are extracted as the standard bases. Then the projection singular value features of the other pressure wave matrixes are extracted by being projected to the two standard bases. As the pipeline leakage is a small probability event, it is difficult to obtain the leakage samples. A multi-classification Support Vector Machine, which has the advantage of small sample learning, is constructed to classify these features in this paper. The field experiments indicate that the leakage detection based on this feature extraction and recognition model has a higher accuracy of leakage recognition.

scholarly journals Separation of diffracted waves via SVD filter

2020 ◽  
Vol 17 (5) ◽  
pp. 1259-1271
Author(s):  
Hong-Yan Shen ◽  
Qin Li ◽  
Yue-Ying Yan ◽  
Xin-Xin Li ◽  
Jing Zhao
Keyword(s):  
Seismic Waves ◽  
Original Data ◽  
Identification Accuracy ◽  
Reflected Waves ◽  
Wave Separation ◽  
Imaging Results ◽  
Diffracted Waves ◽  
Fast Processing ◽  
The Difference ◽  
Value Decomposition

Abstract Diffracted seismic waves may be used to help identify and track geologically heterogeneous bodies or zones. However, the energy of diffracted waves is weaker than that of reflections. Therefore, the extraction of diffracted waves is the basis for the effective utilization of diffracted waves. Based on the difference in travel times between diffracted and reflected waves, we developed a method for separating the diffracted waves via singular value decomposition filters and presented an effective processing flowchart for diffracted wave separation and imaging. The research results show that the horizontally coherent difference between the reflected and diffracted waves can be further improved using normal move-out (NMO) correction. Then, a band-rank or high-rank approximation is used to suppress the reflected waves with better transverse coherence. Following, separation of reflected and diffracted waves is achieved after the filtered data are transformed into the original data domain by inverse NMO. Synthetic and field examples show that our proposed method has the advantages of fewer constraints, fast processing speed and complete extraction of diffracted waves. And the diffracted wave imaging results can effectively improve the identification accuracy of geological heterogeneous bodies or zones.

scholarly journals Measuring and Modeling the Polarized Upwelling Radiance Distribution in Clear and Coastal Waters

2018 ◽  
Vol 8 (12) ◽  
pp. 2683 ◽  
Author(s):  
Arthur Gleason ◽  
Kenneth Voss ◽  
Howard Gordon ◽  
Michael Twardowski ◽  
Jean-François Berthon
Keyword(s):  
Optical Properties ◽  
Absorption Coefficient ◽  
Field Experiments ◽  
Absolute Error ◽  
Mueller Matrix ◽  
Spectral Radiance ◽  
Remote Measurement ◽  
Inherent Optical Properties ◽  
Satellite Sensors ◽  
Radiance Distribution

The upwelling spectral radiance distribution is polarized, and this polarization varies with the optical properties of the water body. Knowledge of the polarized, upwelling, bidirectional radiance distribution function (BRDF) is important for generating consistent, long-term data records for ocean color because the satellite sensors from which the data are derived are sensitive to polarization. In addition, various studies have indicated that measurement of the polarization of the radiance leaving the ocean can used to determine particle characteristics (Tonizzo et al., 2007; Ibrahim et al., 2016; Chami et al., 2001). Models for the unpolarized BRDF (Morel et al., 2002; Lee et al., 2011) have been validated (Voss et al., 2007; Gleason et al., 2012), but variations in the polarization of the upwelling radiance due to the sun angle, viewing geometry, dissolved material, and suspended particles have not been systematically documented. In this work, we simulated the upwelling radiance distribution using a Monte Carlo-based radiative transfer code and measured it using a set of fish-eye cameras with linear polarizing filters. The results of model-data comparisons from three field experiments in clear and turbid coastal conditions showed that the degree of linear polarization (DOLP) of the upwelling light field could be determined by the model with an absolute error of ±0.05 (or 5% when the DOLP was expressed in %). This agreement was achieved even with a fixed scattering Mueller matrix, but did require in situ measurements of the other inherent optical properties, e.g., scattering coefficient, absorption coefficient, etc. This underscores the difficulty that is likely to be encountered using the particle scattering Mueller matrix (as indicated through the remote measurement of the polarized radiance) to provide a signature relating to the properties of marine particles beyond the attenuation/absorption coefficient.

Restoration Simulation of Image Quality Degradation of Nanosensors Based on Virtual Reality

2021 ◽  
Vol 17 (11) ◽  
pp. 2265-2270
Author(s):  
Jiajie Wang ◽  
Junmei Zeng
Keyword(s):  
Virtual Reality ◽  
Image Quality ◽  
Complexity Analysis ◽  
Absolute Error ◽  
Channel Calculation ◽  
Recovery Method ◽  
Noise Characteristics ◽  
Quality Degradation ◽  
Texture Complexity ◽  
Value Decomposition

The texture complexity of traditional sensor image degradation restoration methods is high and the restoration effect is reduced. For this reason, a virtual reality-based image quality degradation recovery method for nanosensors is designed in this paper. First, the image quality degradation model of nanometer sensor is constructed based on virtual reality technology. Then, the noise characteristics of the degraded image are analyzed. On the premise of retaining the original image information, the diffusion coefficients in the vertical and horizontal directions are calculated to obtain the expression of adaptive filter (ADF) in the image with noise, so as to complete the image denoising process. On the basis of texture complexity analysis, singular value decomposition detection and alpha channel calculation are completed, and image quality degradation recovery of nanosensor is achieved through synthesis operation. The experimental results show that the texture complexity of the recovered images is lower than 0.54, the average absolute error percentage of the recovered images is only 10%, and the P-R value is high, which fully demonstrates the effectiveness of the offered procedure.

Ellipse Detection-Based Bin-Picking Visual Servoing System

2013 ◽  
pp. 114-121
Author(s):  
Kai Liu ◽  
Hongbo Li ◽  
Zengqi Sun
Keyword(s):  
Visual Servoing ◽  
Geometric Model ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Time Performance ◽  
Ellipse Detection ◽  
Bin Picking ◽  
Random Sample Consensus ◽  
Hole Model ◽  
Ransac Algorithm

In this chapter, the authors tackle the task of picking parts from a bin (bin-picking task), employing a 6-DOF manipulator on which a single hand-eye camera is mounted. The parts are some cylinders randomly stacked in the bin. A Quasi-Random Sample Consensus (Quasi-RANSAC) ellipse detection algorithm is developed to recognize the target objects. Then the detected targets’ position and posture are estimated utilizing camera’s pin-hole model in conjunction with target’s geometric model. After that, the target, which is the easiest one to pick for the manipulator, is selected from multi-detected results and tracked while the manipulator approaches it along a collision-free path, which is calculated in work space. At last, the detection accuracy and run-time performance of the Quasi-RANSAC algorithm is presented, and the final position of the end-effecter is measured to describe the accuracy of the proposed bin-picking visual servoing system.

Sign in / Sign up

Export Citation Format

Share Document