Local Mean Method Research Articles

Spatial scale applicability of 4-Scale geometrical optics model canopy reflectance simulation.

Accurately clarifying the applicable spatial scale of 4-Scale model is conducive to improving the accuracy of its application in canopy reflectance simulation of different vegetation types, and to further improving the inversion accuracy of leaf area index, canopy density, and other parameters. Two forest plots (one for broad-leaved forest and one for mixed forest) with each area of 100 m×100 m in Maoershan Experimental Forest Farm, Shangzhi, Heilongjiang, were divided into the spatial scales of 10, 20, 30, 40 and 50 m, respectively. The 4-Scale model was used to simulate forest canopy reflectance. Local mean method, the nearest neighbor method, bilinear interpolation method, and cubic convolution method were used to convert Sentinel-2 images with spatial resolution of 10 m to other scales, with the results being evaluated. The simulated canopy reflectance and remote sensing pixel reflectance were compared and analyzed. The spatial scale of mixed forest and broad-leaved forest suitable for high-precision inversion parameters of 4-Scale model was determined. The results showed that the 4-Scale model underestimated the pixel forest canopy reflectance as a whole. The canopy reflectance of mixed forest and broad-leaved forest had the worst simulation effect at the 20 m scale. Both the root mean square error (RMSE) and the mean absolute error from (MAE) of red and near-infrared band were large. When the scale was >20 m, the simulation effect became better. The applicability of the model was the best when the mixed forest was 40 m and the broad-leaved forest was 30 m. The mean and standard deviation of the reflectance difference between the simulated value and the remote sensing pixel were the minimum in the red and near near-infrared bands, with the minimum RMSE and MAE. The simulation results of mixed forest and broad-leaved forest at 10 m scale were not stable, the rule of mean and standard deviation was inconsistent, and the difference between RMSE and MAE was large under the same band.

Infrared and Visible Image Fusion Based on Visual Saliency Map and Image Contrast Enhancement.

The purpose of infrared and visible image fusion is to generate images with prominent targets and rich information which provides the basis for target detection and recognition. Among the existing image fusion methods, the traditional method is easy to produce artifacts, and the information of the visible target and texture details are not fully preserved, especially for the image fusion under dark scenes and smoke conditions. Therefore, an infrared and visible image fusion method is proposed based on visual saliency image and image contrast enhancement processing. Aiming at the problem that low image contrast brings difficulty to fusion, an improved gamma correction and local mean method is used to enhance the input image contrast. To suppress artifacts that are prone to occur in the process of image fusion, a differential rolling guidance filter (DRGF) method is adopted to decompose the input image into the basic layer and the detail layer. Compared with the traditional multi-scale decomposition method, this method can retain specific edge information and reduce the occurrence of artifacts. In order to solve the problem that the salient object of the fused image is not prominent and the texture detail information is not fully preserved, the salient map extraction method is used to extract the infrared image salient map to guide the fusion image target weight, and on the other hand, it is used to control the fusion weight of the basic layer to improve the shortcomings of the traditional ‘average’ fusion method to weaken the contrast information. In addition, a method based on pixel intensity and gradient is proposed to fuse the detail layer and retain the edge and detail information to the greatest extent. Experimental results show that the proposed method is superior to other fusion algorithms in both subjective and objective aspects.

Underlying Topography Inversion Using TomoSAR Based on Non-Local Means for an L-Band Airborne Dataset

The underlying topography is an important part of the three-dimensional structure of forests, and is used for a variety of applications, such as hydrology and water resource management, civil engineering projects, and forest resource surveying. Due to the three-dimensional imaging ability and strong penetration, the tomographic synthetic aperture radar (TomoSAR) with a long wavelength has been shown to be a useful tool to estimate the underlying topography. At present, most of the current methods use the local means method to estimate the sample covariance matrix, in which the vertical backscattering power is estimated. However, these methods cannot easily obtain high-precision underlying topography, and often lose some detailed information. In this paper, to solve this problem, a non-local means method is introduced to estimate the optimal covariance matrix by combining weighted neighborhood pixels. To validate the feasibility and effectiveness of this proposed method, a BioSAR 2008 campaign L-band dataset acquired from the northern forests of Sweden was used to inverse the underlying topography. The results show that the accuracy of the underlying topography retrieved by the proposed method is improved by more than 30% when compared with the traditional method.

SNR enhancement of a Raman distributed temperature sensor using partial window-based non local means method

Raman scattering-based distributed sensor is nowadays the most mature and consolidated technology for distributed temperature sensing at long ranges. Even though the various applied methods in recent decades have made important improvements in performance of Raman sensors, they do not thoroughly exploit the high level of correlation and similitude existing in the acquired data. In the present, we exploit a 2D image processing method called non-local means (NLM) algorithm that takes full advantage of, compared to existing methods, highly redundant texture of the 1D data obtained from distributed Raman sensors. One of the main drawbacks of the original NLM filter in distributed sensors area is to establish complete squared similarity windows for denoising the boundary pixels, corresponding to the data placed at the last row of the data matrices, which constrains the best attainable SNR values. To overcome this issue, we introduce an unprecedented approach called partial window (PW) by which we utilize partial similarity windows for denoising the boundary pixels. The PW-based NLM (PW-NLM) technique not only leads to higher levels of SNR compared with the original one, but also has no detrimental effects on the denoised data. The simulation results demonstrate the SNR improvement of 2.8 dB using the PW-based NLM filter over the original NLM filter corresponding to the 17 dB SNR boost compared with the unprocessed data.

Local means denoising of ECG signal

Electrocardiograph (ECG) signals denoising by Non-Local Means (NLM) method can achieve high signal-to-noise ratio improvements with less waveform distortion. But, computational complexity constraints its potential application in ECG signal real-time denoising. In this paper, firstly we present a simple method to determine standard deviation of additive white Gaussian noise in the ECG signal. Then, a fast ECG signal denoising method, Local Means (LM) method, which is a “local” version of the NLM method is introduced. LM method has about 2 order of magnitude lower computational cost than NLM method due to the “local search.” In a low SNR level condition, the signal-to-noise (SNR) improvement increases via LM method, by 21% compared to NLM method.

Image de-noising with subband replacement and fusion process using bayes estimators,

A hybrid image de-noising framework with an automatic parameter selection scheme is proposed to handle substantially high noise with an unknown variance. The impetus of the framework is to preserve the latent detail information of the noisy image while removing the noise with an appropriate smoothing and feasible sharpening. The proposed method is executed in two steps. First, the sub-band replacement and fusion process based on accelerated version of the Bayesian non local means method are implemented to enhance the weak edges that often result in low gradient magnitude and fade out during the de-noising process. Then, a truncated beta-Bernoulli process is employed to infer an appropriate dictionary of the edge enhanced data to obtain de-noising results precisely. Numerical simulations are performed to substantiate the restoration of the weak edges through sub-band replacement and fusion process. The proposed de-noising scheme is validated through visual and quantitative results using well established metrics.

Design of Blurring Mean-Shift Algorithms for Data Classification

The mean-shift algorithm is an iterative method of mode seeking and data clustering based on the kernel density estimator. The blurring mean-shift is an accelerated version which uses the original data only in the first step, then re-smoothes previous estimates. It converges to local centroids, but may suffer from problems of asymptotic bias, which fundamentally depend on the design of its smoothing components. This paper develops nearest-neighbor implementations and data-driven techniques of bandwidth selection, which enhance the clustering performance of the blurring method. These solutions can be applied to the whole class of mean-shift algorithms, including the iterative local mean method. Extended simulation experiments and applications to well known data-sets show the goodness of the blurring estimator with respect to other algorithms.

An Effective Evolutionary Clustering Algorithm: Hepatitis C Case Study

Clustering analysis plays an important role in scientific research and commercial application. K-means algorithm is a widely used partition method in clustering. However, it is known that the K-means algorithm may get stuck at suboptimal solutions, depending on the choice of the initial cluster centers. In this article, we propose a technique to handle large scale data, which can select initial clustering center purposefully using Genetic algorithms (GAs), reduce the sensitivity to isolated point, avoid dissevering big cluster, and overcome deflexion of data in some degree that caused by the disproportion in data partitioning owing to adoption of multi-sampling.We applied our method to some public datasets these show the advantages of the proposed approach for example Hepatitis C dataset that has been taken from the machine learning warehouse of University of California. Our aim is to evaluate hepatitis dataset. In order to evaluate this dataset we did some preprocessing operation, the reason to preprocessing is to summarize the data in the best and suitable way for our algorithm. Missing values of the instances are adjusted using local mean method.

PCA-ANN for Classification of Hepatitis-C Patients

In this paper, an automatic diagnosis system based on Neural Network for hepatitis virus is introduced. This automatic diagnosis system deals with the mixture of feature extraction and classification. The system has two stages, which are feature extraction – reduction and classification stages. In the feature extraction – diminution stage, the hepatitis features were obtained from UCI Repository of Machine Learning Databases. Missing values of the instances are adjusted using local mean method. Then, the number of these features was reduced to 6 from 19 due to relative significance of fields. In the classification stage, these reduced features are given as inputs Neural Network classifier. The classification accuracy of this ANN diagnosis system for the diagnosis of hepatitis virus was obtained, this accuracy was around 99.1% for training data and 100% for testing data. General Terms Data Mining