Remote sensing image denoising based on improved semi-soft threshold

Meng

et al. 2022

Sensors

In indoor positioning, signal fluctuation is one of the main factors affecting positioning accuracy. To solve this problem, a new method based on an integration of the empirical mode decomposition threshold smoothing method (EMDT) and improved weighted K nearest neighbor (WKNN), named EMDT-WKNN, is proposed in this paper. First, the nonlinear and non-stationary received signal strength indication (RSSI) sequences are constructed. Secondly, intrinsic mode functions (IMF) selection criteria based on energy analysis method and fluctuation coefficients is proposed. Thirdly, the EMDT method is employed to smooth the RSSI fluctuation. Finally, to further avoid the influence of RSSI fluctuation on the positioning accuracy, the deviated matching points are removed, and more precise combined weights are constructed by combining the geometric distance of the matching points and the Euclidean distance of fingerprints in the positioning method-WKNN. The experimental results show that, on an underground parking dataset, the positioning accuracy based on EMDT-WKNN can reach 1.73 m in the 75th percentile positioning error, which is 27.6% better than 2.39 m of the original RSSI positioning method.

where

is the smoothed version of

is the threshold of

, N is the number of data samples of the RSSI sequence

is an empirical constant that makes the

more flexible.…”

Section: The Proposed Methodsmentioning

confidence: 99%

A Wi-Fi Indoor Positioning Method Based on an Integration of EMDT and WKNN

Meng

et al. 2022

Sensors

6th International Conference on Mechatronics and Intelligent Robotics (ICMIR2022)

“…Considering the template effect on the basis of this ( 9), the distance l should be enlarged by /2 times, and M is the Zernike moment template size 7 . Thus the final formula for calculating the subpixel coordinates is (10)…”

Section: Zernike Moment Algorithm To Pinpoint Edge Locationmentioning

confidence: 99%

Improved Canny-Zernike moment-based subpixel edge detection algorithm

Bao

2022

In order to solve the lack of edge precision of traditional Canny algorithm and the defects of Gaussian filtering and gradient calculation, we propose an algorithm based on wavelet transform to realize image denoising, which improves the detection accuracy by replacing the original gradient template algorithm with the Scharr operator in four directions, and then uses the reference threshold, combined with the Zernike moment algorithm to perform sub-pixel pinpointing of all possible edge points thus The edge detection is achieved. It is confirmed by many experimental results that the algorithm improves the image edge positioning accuracy and processing efficiency, and has better anti-noise ability than the traditional Canny algorithm and Zernike moment algorithm.

“…In response to the above defects, this paper introduces a progressive semi-soft threshold function. Compared with the soft threshold function, the progressive semi-soft threshold function not only retains the continuity of the soft threshold function, but also eliminates the distortion caused by the soft threshold [29]. The calculation formula for realizing progressive semi-soft threshold is as follows:…”

Section: Progressive Semi-soft Thresholdmentioning

confidence: 99%

An Intelligent Quadrotor Fault Diagnosis Method Based on Novel Deep Residual Shrinkage Network

Yang

Geng

Wen

et al. 2021

Drones

In this paper, a fault diagnosis algorithm named improved one-dimensional deep residual shrinkage network with a wide convolutional layer (1D-WIDRSN) is proposed for quadrotor propellers with minor damage, which can effectively identify the fault classes of quadrotor under interference information, and without additional denoising procedures. In a word, that fault diagnosis algorithm can locate and diagnose the early minor faults of the quadrotor based on the flight data, so that the quadrotor can be repaired before serious faults occur, so as to prolong the service life of quadrotor. First, the sliding window method is used to expand the number of samples. Then, a novel progressive semi-soft threshold is proposed to replace the soft threshold in the deep residual shrinkage network (DRSN), so the noise of signal features can be eliminated more effectively. Finally, based on the deep residual shrinkage network, the wide convolution layer and DroupBlock method are introduced to further enhance the anti-noise and over-fitting ability of the model, thus the model can effectively extract fault features and classify faults. Experimental results show that 1D-WIDRSN applied to the minimal fault diagnosis model of quadrotor propellers can accurately identify the fault category in the interference information, and the diagnosis accuracy is over 98%.