Real-Time Video Processing System based on Field Programmable Gate Array

Havrilov, Dmytro; Baraban, Serhii; Volovyk, Andrii; Zviahin, O.S.; Семенов, А. А.; Savytskyi, Anton

doi:10.1109/stc-csit.2019.8929758

Cited by 6 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with these traditional algorithms, the spectral clustering algorithm [13] has gained popularity because of its simple implementation and good performance for sample spaces of arbitrary shapes, particularly for nonconvex shapes. Spectral clustering has broad applications, including image segmentation [14,15], pattern recognition [16], video processing [17], and bioinformatics [18,19].…”

Section: Introductionmentioning

confidence: 99%

Spectral clustering based on the local similarity measure of shared neighbors

Chen

Cao

2022

ETRI Journal

View full text Add to dashboard Cite

Spectral clustering has become a typical and efficient clustering method used in a variety of applications. The critical step of spectral clustering is the similarity measurement, which largely determines the performance of the spectral clustering method. In this paper, we propose a novel spectral clustering algorithm based on the local similarity measure of shared neighbors. This similarity measurement exploits the local density information between data points based on the weight of the shared neighbors in a directed k-nearest neighbor graph with only one parameter k, that is, the number of nearest neighbors.Numerical experiments on synthetic and real-world datasets demonstrate that our proposed algorithm outperforms other existing spectral clustering algorithms in terms of the clustering performance measured via the normalized mutual information, clustering accuracy, and F-measure. As an example, the proposed method can provide an improvement of 15.82% in the clustering performance for the Soybean dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Spectral clustering based on the local similarity measure of shared neighbors

Chen

Cao

2022

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, promising in this direction is the development of inexpensive portable sensors with integrated computational cores, based on new algorithms for information transformations of the FID signal in the transmit and receive path and the visualization of NQR spectra [ 13 , 14 , 15 ]. At the same time, considerable attention should be paid to increasing the signal-to-noise ratio value provided by the sensor to the required level for error-free detection of the NQR signal in the investigated substances of small volumes with masses from tenths to several grams, and to the development of highly efficient methods for the formation of special multi-pulse sequences of nanosecond time intervals for the stochastic NQR technique [ 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Implementation of the Configuration Structure of an Integrated Computational Core of a Pulsed NQR Sensor Based on FPGA

Samila

Hotra

Majewski

2021

Sensors

View full text Add to dashboard Cite

This paper presents a method for implementing the configuration structure of an integrated computational core of a pulsed nuclear quadrupole resonance (NQR) sensor based on a field-programmable gate array (FPGA), which comprises the following modules: a three-channel direct digital synthesizer (DDS), a pulse sequence shaper and a software-defined radio. Experimental studies carried out using the in-circuit analyzer SignalTap Logic Analyzer have confirmed the reliability of the correct and stable operation of the functional modules of the configuration structure at all stages of signal transformations, starting from the formation of the envelope of the excitation pulses and ending with the obtainment of low-frequency quadrature signals at the outlet of the compensating filters. The time and frequency dependences of the amplitude of the output signals generated using the DDS based on a 48 bit phase accumulator are investigated. This development can be used when creating pulsed coherent NQR sensors in the frequency range of 1 MHz–50 MHz.

show abstract

“…Thus it is widely used for data clustering. Nowadays, in the fields of image segmentation [18], video processing [19], speech recognition [20], and pattern recognition [21], the algorithm has been successfully used.…”

Section: Introductionmentioning

confidence: 99%

Spectral Clustering Algorithm Based on Fast Search of Natural Neighbors

Yuan

Zhu

2020

IEEE Access

View full text Add to dashboard Cite

The spectral clustering is a typical and efficient clustering algorithm. However, the performance of spectral algorithm depends on the determination of the appropriate similarity matrix and the number of clusters. We propose a new spectral clustering algorithm based on fast search of natural neighbors (FSNN-SC) in this paper. In the algorithm, we design a fast search algorithm to obtain the natural characteristic value sup k of natural neighbor algorithm in order to improve the efficiency of searching neighbors and to construct a high-quality similarity matrix. At the same time, we design a deep traversal algorithm to adaptively determine the cluster number C. The experimental results verify that our methods are able to improve the search efficiency and find correct number of clusters. The compared experiments show that the accuracy and efficiency of the proposed algorithm are better than others. INDEX TERMS Deep traversal, fast search, natural neighbour, spectral clustering.

show abstract

Real-Time Video Processing System based on Field Programmable Gate Array

Cited by 6 publications

References 3 publications

Spectral clustering based on the local similarity measure of shared neighbors

Spectral clustering based on the local similarity measure of shared neighbors

Implementation of the Configuration Structure of an Integrated Computational Core of a Pulsed NQR Sensor Based on FPGA

Spectral Clustering Algorithm Based on Fast Search of Natural Neighbors

Contact Info

Product

Resources

About