Noise Removal and Feature Extraction in Airborne Radar Sounding Data of Ice Sheets

The airborne ice-penetrating radar (IPR) is an effective method used for ice sheet exploration and is widely applied for detecting the internal structures of ice sheets and for understanding the mechanism of ice flow and the characteristics of the bottom of ice sheets. However, because of the ambient influence and the limitations of the instruments, IPR data are frequently overlaid with noise and interference, which further impedes the extraction of layer features and the interpretation of the physical characteristics of the ice sheet. In this paper, we first applied conventional filtering methods to remove the feature noise and interference in IPR data. Furthermore, machine learning methods were introduced in IPR data processing for noise removal and feature extraction. Inspired by a comparison of the filtering methods and machine learning methods, we propose a fusion method combining both filtering methods and machine-learning-based methods to optimize the feature extraction in IPR data. Field data tests indicated that, under different conditions of IPR data, the application of different methods and strategies can improve the layer feature extraction.

Component-scaled signal reconstruction for enhanced noise filtration

This research introduces a procedure for signal denoising based on linear combinations of intrinsic mode functions (IMFs) extracted using empirical mode decomposition (EMD). The method, termed component-scaled signal reconstruction, employs the standard EMD algorithm, with no enhancements to decompose the signal into a set of IMFs. The problem of mode mixing is leveraged for noise removal by constructing an optimal linear combination of the potentially mixed IMFs. The optimal linear combination is determined using an optimization routine with an objective function that maximizes and minimizes the information and noise, respectively, in the denoised signal. The method is demonstrated by applying it to a computer-generated voice sample and the displacement response of a cantilever beam with local stiffness nonlinearity. In the first application, the noise is introduced into the sample manually by adding a Gaussian white-noise signal to the signal. In the second application, the response of the entire beam is filmed using two 1-megapixel cameras, and the three-dimensional displacement field is extracted using digital image correlation. The noise in this application arises entirely from the images captured. The proposed method is compared to existing EMD, ensemble EMD, and LMD based denoising approaches and is found to perform better.

Adaptive Enhancement Algorithm of High-Resolution Satellite Image Based on Feature Fusion

Since the traditional adaptive enhancement algorithm of high-resolution satellite images has the problems of poor enhancement effect and long enhancement time, an adaptive enhancement algorithm of high-resolution satellite images based on feature fusion is proposed. The noise removal and quality enhancement areas of high-resolution satellite images are determined by collecting a priori information. On this basis, the histogram is used to equalize the high-resolution satellite images, and the local texture features of the images are extracted in combination with the local variance theory. According to the extracted features, the illumination components are estimated by Gaussian low-pass filtering. The illumination components are fused to complete the adaptive enhancement of high-resolution satellite images. Simulation results show that the proposed algorithm has a better adaptive enhancement effect, higher image definition, and shorter enhancement time.

Adaptive Image Denoising Method Based on Diffusion Equation and Deep Learning

Effective noise removal has become a hot topic in image denoising research while preserving important details of an image. An adaptive threshold image denoising algorithm based on fitting diffusion is proposed. Firstly, the diffusion coefficient in the diffusion equation is improved, and the fitting diffusion coefficient is established to overcome the defects of texture detail loss and edge degradation caused by excessive diffusion intensity. Then, the threshold function is adaptively designed and improved so that it can automatically control the threshold of the function according to the maximum gray value of the image and the number of iterations, so as to further preserve the important details of the image such as edge and texture. A neural network is used to realize image denoising because of its good learning ability of image statistical characteristics, mainly by the diffusion equation and deep learning (CNN) algorithm as the foundation, focus on the effects of activation function of network optimization, using multiple feature extraction technology in-depth networks to study the characteristics of the input image richer, and how to better use the adaptive algorithm on the depth of diffusion equation and optimization backpropagation learning. The training speed of the model is accelerated and the convergence of the algorithm is improved. Combined with batch standardization and residual learning technology, the image denoising network model based on deep residual learning of the convolutional network is designed with better denoising performance. Finally, the algorithm is compared with other excellent denoising algorithms. From the comparison results, it can be seen that the improved denoising algorithm in this paper can also improve the detail restoration of denoised images without losing the sharpness. Moreover, it has better PSNR than other excellent denoising algorithms at different noise standard deviations. The PSNR of the new algorithm is greatly improved compared with the classical algorithm, which can effectively suppress the noise and protect the image edge and detail information.

Numerical analysis of wave propagating in a periodic layered structure

Controlling sound fields is a key technology for noise removal, acoustic lenses, energy harvesting, etc. This study investigated the control of sound field by a periodic layered structure. At first, we formulated the wave propagation in a periodic layered structure and proved that the wave fields constructed by the periodic boundary conditions are limited to plane wave modes with discretely different propagation directions. Numerical calculations clarified that the desired plane wave mode can be obtained in the transmitted wave through an intermediate thin-plate stacked region in a periodic layered structure, in which Lamb waves travel in each plate at different phase velocities and create phase difference at the exit of the intermediate thin-plate region. Further numerical investigations revealed that tuning frequency and length of the thin-plate region provides wave field more dominantly with a single wanted plane wave mode.

Analysis of Instagram Users’ Movement Pattern by Cluster Analysis and Association Rule Mining

Understanding the characteristics of tourists’ movements is essential for tourism destination management. With advances in information and communication technology, more and more people are willing to upload photos and videos to various social media platforms while traveling. These openly available media data is gaining increasing attention in the field of movement pattern mining as a new data source. In this study, uploaded images and their geographic information within Lake Constance region, Germany were collected and through clustering analysis, a state-of-the-art k-means with noise removal algorithm was compared with the commonly used DBCSCAN on Instagram dataset. Finally, association rules between popular attractions at region-level and city-level were mined respectively. Results show that social media data like Instagram constitute a valuable input to analyse tourists’ movement patterns as input to decision support and destination management.

Framelet transform and fuzzy clustering-based intelligent technique for speckle noise removal in ultrasound images

PurposeSpeckle noise removal in ultrasound images is one of the important tasks in biomedical-imaging applications. Many filtering -based despeckling methods are discussed in many existing works. Two-dimensional (2-D) transforms are also used enormously for the reduction of speckle noise in ultrasound medical images. In recent years, many soft computing-based intelligent techniques have been applied to noise removal and segmentation techniques. However, there is a requirement to improve the accuracy of despeckling using hybrid approaches.Design/methodology/approachThe work focuses on double-bank anatomy with framelet transform combined with Gaussian filter (GF) and also consists of a fuzzy kind of clustering approach for despeckling ultrasound medical images. The presented transform efficiently rejects the speckle noise based on the gray scale relative thresholding where the directional filter group (DFB) preserves the edge information.FindingsThe proposed approach is evaluated by different performance indicators such as the mean square error (MSE), peak signal to noise ratio (PSNR) speckle suppression index (SSI), mean structural similarity and the edge preservation index (EPI) accordingly. It is found that the proposed methodology is superior in terms of all the above performance indicators.Originality/valueFuzzy kind clustering methods have been proved to be better than the conventional threshold methods for noise dismissal. The algorithm gives a reconcilable development as compared to other modern speckle reduction procedures, as it preserves the geometric features even after the noise dismissal.

Application of Image Denoising Method Based on Two-Way Coupling Diffusion Equation in Public Security Forensics

This paper uses the web live broadcast and on-demand platform based on the B/S architecture as the application side and designs a video image forensic system that can meet multiple police types and multiple application scenarios. The system uses mobile phones as the video image capture terminal to solve the problem of rapid response and concealment and uses 5G communication technology as the transmission medium to solve the problem of device mobility and link maintenance. The problem of diversification of the use and application modes of multiple police types is solved; the video image evidence is managed in a centralized storage, audit, and export method, and the security and authenticity of the evidence are solved. While the system realizes a series of functions such as the collection, transmission, storage, and application of video image evidence, it also realizes the application-side video image live broadcast function according to actual work needs and solves the large-scale case command and decision-making problem that has been plagued by public security organs. In order to remove the noise in the public security forensic images and to smooth the noise while retaining the details of the image, this paper proposes a denoising algorithm based on the two-way coupling diffusion equation. By improving the second-order partial differential equation, a new diffusion function with better diffusion effect than the original model is constructed. We combined the adaptive edge threshold and stop criterion to establish a new denoising algorithm model, which can get better denoising results. When the noise level is low, the PSNR value and SSIM value of several denoising methods are relatively ideal, and the result is at a higher level, the denoising picture effect is better, and there is no obvious incomplete noise removal or detail problems. As the noise level increases, the denoising results will gradually decrease, and the effects will also vary to different degrees. When the noise intensity increases, visually, it can be clearly seen that the two-way coupled diffusion equation and DnCNN have better denoising effects. When the noise level is high, the two-way coupled diffusion equation network is used to use the clear image and the denoised image for indistinguishable calculation. The method in this paper almost retains all the texture details in the clear image, and there are almost no artifacts and images. On the other hand, the color of the image after denoising by the method in this paper is more vivid, and it is closer to the target picture in terms of picture definition and tone, the denoising effect is ideal, and the generated image has a higher degree of restoration. Compared with the residual GAN, the two-way coupling diffusion equation network converges faster and the network performance is improved.