Rolling Bearing Fault Vibration Signal Denoising Based on Adaptive Morphological Wavelet Perona–Malik Filter Algorithm

This paper proposes an adaptive Perona–Malik filtering algorithm based on the morphological Haar wavelet, which is used for vibration signal denoising in rolling bearing fault diagnosis with strong noise. First, the morphological Haar wavelet operator is utilized to presmooth the noisy signal, and the gradient of the presmooth signal is estimated. Second, considering the uncertainty of gradient at the strong noise point, a strong noise point recognition operator is constructed to adaptively identify the strong noise point. Third, the two-step gradient average value of the strong noise point in the same direction is used to substitute, and the second derivative is introduced into the diffusion coefficient. Finally, diffusion filtering is performed based on the improved Perona–Malik model. The simulation experiment result indicated that not only the algorithm can denoise effectively, but also the average gradient and second derivative in the same direction can effectively suppress the back diffusion of strong noise points to improve the denoising signal-to-noise ratio. The experimental results of rolling bearing show that the algorithm can adaptively filter out strong noise points and keep the information of peak in the signal well, which can improve the accuracy of rolling bearing fault diagnosis.

Outlier Detection of Light Buoy Telemetry and Telecontrol Data Based on Improved Adaptive ε Neighborhood DBSCAN Clustering

In this paper, according to the water area of light buoy, the migration rule of light buoy in main channel is counted, and the frequency of light buoy passing through a certain position point in the process of migration is calculated, and the model is verified by buoy position data. An anomaly detection algorithm based on improved adaptive DBSCAN clustering is designed. The size of the ε neighborhood is adaptive according to the wind speed, wave height, and drift distance span of the water area where the light buoy is located. The experimental results show that the improved adaptive DBSCAN clustering algorithm can solve the problem that the common DBSCAN clustering algorithm takes the “hot” water area of the light buoy position or the most likely area in the light buoy migration process as the noise point.

Pavement 3D Data Denoising Algorithm Based on Cell Meshing Ellipsoid Detection

As a new measuring technique, laser 3D scanning technique has advantages of rapidity, safety, and accuracy. However, the measured result of laser scanning always contains some noise points due to the measuring principle and the scanning environment. These noise points will result in the precision loss during the 3D reconstruction. The commonly used denoising algorithms ignore the strong planarity feature of the pavement, and thus might mistakenly eliminate ground points. This study proposes an ellipsoid detection algorithm to emphasize the planarity feature of the pavement during the 3D scanned data denoising process. By counting neighbors within the ellipsoid neighborhood of each point, the threshold of each point can be calculated to distinguish if it is the ground point or the noise point. Meanwhile, to narrow down the detection space and to reduce the processing time, the proposed algorithm divides the cloud point into cells. The result proves that this denoising algorithm can identify and eliminate the scattered noise points and the foreign body noise points very well, providing precise data for later 3D reconstruction of the scanned pavement.

Continuous-Time Laser Frames Associating and Mapping via Multilayer Optimization

To achieve the ability of associating continuous-time laser frames is of vital importance but challenging for hand-held or backpack simultaneous localization and mapping (SLAM). In this study, the complex associating and mapping problem is investigated and modeled as a multilayer optimization problem to realize low drift localization and point cloud map reconstruction without the assistance of the GNSS/INS navigation systems. 3D point clouds are aligned among consecutive frames, submaps, and closed-loop frames using the normal distributions transform (NDT) algorithm and the iterative closest point (ICP) algorithm. The ground points are extracted automatically, while the non-ground points are automatically segmented to different point clusters with some noise point clusters omitted before 3D point clouds are aligned. Through the three levels of interframe association, submap matching and closed-loop optimization, the continuous-time laser frames can be accurately associated to guarantee the consistency of 3D point cloud map. Finally, the proposed method was evaluated in different scenarios, the experimental results showed that the proposed method could not only achieve accurate mapping even in the complex scenes, but also successfully handle sparse laser frames well, which is critical for the scanners such as the new Velodyne VLP-16 scanner’s performance.

Image Filtering Algorithm of Subway Tunnel Cracks Based on Regional Difference

Aiming at the problems of uneven illumination, low contrast and serious noise interference in subway tunnel images, an adaptive median filtering algorithm based on regional differences is proposed to improve noise detection and noise filtering. The algorithm first used the filter window set in advance by the algorithm to detect and determined the noise point by calculating the gray difference in the window. Then it is only filtered by the effective pixels are median-calculated in the template. The result is output as the gray value in the center of the window. Compared with the traditional median, mean and adaptive median filtering algorithms, the proposed new algorithm can effectively filter out noise while reducing the difficulty of subsequent segment recognition.

SVM Ensemble-based Noise Detection Method for Image Denoising

Background: To preserve sharp edges and image details while removing noise, this paper presents a denoising method based on Support Vector Machine (SVM) ensemble for detecting noise. Methods: The proposed method ISVM can be divided into two stages: noise detection and noise recovery. In the first stage, local binary features and weighted difference features are extracted as input features vector of ISVM, and multiple sub-SVM classifiers are integrated to form the noise classification model of ISVM by iteratively updating the sample weight. The pixels are divided into noise points and signal points. In the noise recovery stage, according to the classification results of the previous stage, only the gray value of the noise point is replaced, and the replacement value is the weighted mean value with the reciprocal of the quadratic square of the distance as the weight. Results: Finally, the replacement value at the noise point and the original pixel value of the signal point are reconstructed to get the denoised image. Conclusion: The experiments demonstrate that ISVM can achieve a noise detection rate of up to 99.68%. ISVM is highly effective in the denoising task, produces a visually pleasing denoised image with clear edge information, and offers remarkable improvement compared to that of the BPDF and DAMF.

Shear measurement bias

We present a study of the dependencies of shear bias on simulation (input) and measured (output) parameters, noise, point-spread function anisotropy, pixel size, and the model bias coming from two different and independent galaxy shape estimators. We used simulated images from GALSIM based on the GREAT3 control-space-constant branch, and we measured shear bias from a model-fitting method (GFIT) and a moment-based method (Kaiser-Squires-Broadhurst). We show the bias dependencies found on input and output parameters for both methods, and we identify the main dependencies and causes. Most of the results are consistent between the two estimators, an interesting result given the differences of the methods. We also find important dependences on orientation and morphology properties such as flux, size, and ellipticity. We show that noise and pixelization play an important role in the bias dependencies on the output properties and galaxy orientation. We show some examples of model bias that produce a bias dependence on the Sérsic index n as well as a different shear bias between galaxies consisting of a single Sérsic profile and galaxies with a disc and a bulge. We also see an important coupling between several properties on the bias dependences. Because of this, we need to study several measured properties simultaneously in order to properly understand the nature of shear bias. This paper serves as a first step towards a companion paper that describes a machine learning approach to modelling shear bias as a complex function of many observed properties.

Quintuple Local Coordinate Images for Local Shape Description

Owing to poor descriptiveness, weak robustness, and high computation complexity of local shape descriptors (<small>LSDs</small>), point-cloud registration in the case of partial overlap and object recognition in a cluttered environment are still challeng- ing tasks. For this purpose, an <small>LSD</small> is developed in this article by proposing a new local reference frame (<small>LRF</small>) method and designing a novel feature representation. In the <small>LRF</small> method, two weighting methods are applied to obtain robustness to noise, point-density variation, and incomplete shape. Additionally, a vector representation is calculated to disambiguate the sign of the x-axis. The feature representation encodes the local information by generating the local coordinate images from five views. Thus, more geometric and spatial information is included in the descriptor. Finally, the performance of the <small>LRF</small> method and the <small>LSD</small> is evaluated on several popular data sets. The experimental results demonstrate well that the <small>LRF</small> is robust to noise, point-density variation, and incomplete shape, and the <small>LSD</small> holds strong robustness, superior descriptiveness, and high computational efficiency.

Small and Dim Ship Target Detection Based on Sea-Sky-Line

In order to solve the problem of small and dim ship target detection under complex sea-sky background, we propose a target detection algorithm based on sea-sky line detection. Firstly, the paper locates the sea-sky-line based on fully convolutional networks, through which target potential area can be determined and disturbance can be excluded. Then the method based on the mean of four detection gradient is adopted to detect the small and dim ship target. The simulation results show that the method of sea-sky-line detection based on fully convolutional networks can overcome the disadvantages of the traditional methods and is suitable for complex background. The detection method proposed can filter the white noise point on the sea surface and thus can reduce false alarm, through which the detection of small and dim ship can be completed well.

Implementation of Fuzzy C-Means and Possibilistic C-Means Clustering Algorithms, Cluster Tendency Analysis and Cluster Validation

In this paper, several two-dimensional clustering scenarios are given. In those scenarios, soft partitioning clustering algorithms (Fuzzy C-means (FCM) and Possibilistic c-means (PCM)) are applied. Afterward, VAT is used to investigate the clustering tendency visually, and then in order of checking cluster validation, three types of indices (e.g., PC, DI, and DBI) were used. After observing the clustering algorithms, it was evident that each of them has its limitations; however, PCM is more robust to noise than FCM as in case of FCM a noise point has to be considered as a member of any of the cluster.