Efficient block matching using improved particle swarm optimization with application to displacement measurement for nano motion systems

Lu, Guoliang; Zhu, Yanjun; Su, Gaozhao; Zhang, Zhiming; Yan, Peng

doi:10.1016/j.optlaseng.2018.08.011

Cited by 10 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pinhole imaging is a physics phenomenon where a light source passes through a pinhole and its inverted image will be formed on a screen (Long et al, 2021). Inspired by the related literature (Long et al, 2021;Lu et al, 2018), this paper introduces the pinhole imaging theory into the search strategy of potential cluster centers, which can help the TMsDP to expand the range of center exploration. Assume that the point S i x s i ; y s i À Á is a potential cluster center in Sample and The whole process of constructing pointdomains by utilizing the pinhole imaging strategy DTA other potential cluster centers, like the point S k x s k ; y s k À Á and the point S j x s j ; y s j À Á , may also exist in the same point-domain.…”

Section: The Proposed Clustering Methods 31 Point-domain Strategy Bas...mentioning

confidence: 99%

TMsDP: two-stage density peak clustering based on multi-strategy optimization

Hao

2022

DTA

View full text Add to dashboard Cite

PurposeThe density peak clustering algorithm (DP) is proposed to identify cluster centers by two parameters, i.e. ρ value (local density) and δ value (the distance between a point and another point with a higher ρ value). According to the center-identifying principle of the DP, the potential cluster centers should have a higher ρ value and a higher δ value than other points. However, this principle may limit the DP from identifying some categories with multi-centers or the centers in lower-density regions. In addition, the improper assignment strategy of the DP could cause a wrong assignment result for the non-center points. This paper aims to address the aforementioned issues and improve the clustering performance of the DP.Design/methodology/approachFirst, to identify as many potential cluster centers as possible, the authors construct a point-domain by introducing the pinhole imaging strategy to extend the searching range of the potential cluster centers. Second, they design different novel calculation methods for calculating the domain distance, point-domain density and domain similarity. Third, they adopt domain similarity to achieve the domain merging process and optimize the final clustering results.FindingsThe experimental results on analyzing 12 synthetic data sets and 12 real-world data sets show that two-stage density peak clustering based on multi-strategy optimization (TMsDP) outperforms the DP and other state-of-the-art algorithms.Originality/valueThe authors propose a novel DP-based clustering method, i.e. TMsDP, and transform the relationship between points into that between domains to ultimately further optimize the clustering performance of the DP.

show abstract

Section: The Proposed Clustering Methods 31 Point-domain Strategy Bas...mentioning

confidence: 99%

TMsDP: two-stage density peak clustering based on multi-strategy optimization

Hao

2022

DTA

View full text Add to dashboard Cite

show abstract

“…1) Template matching: Template matching is a technique for finding small parts of a new image which match the predefined templates in the reference image, thereby motion measurement can be achieved by tracking the templates in the image sequences. Since the template is usually a rectangle area and the matching process is on searching image intensities, this technique has been given different names in literature, such as block matching [72], area-based matching [73], and image correlation [74]. Nevertheless, in this review, this technique is called template matching due to the intuitive concept and the popularity in the majority of published literature.…”

Section: Image Processing Algorithms For Precision Motion Measurementmentioning

confidence: 99%

“…Only a limited number of works for 1-DOF visual measurement are proposed, which mainly exploring high-frequency rate in one dimension [170]. 2-DOF measurement, on the other hand, has been widely studied [72], [77], [113], [171], where in-plane position information is sufficient for the task requirement. All the tracking techniques mentioned in Section II-C are able to easily perform motion measurement for in-plane displacement by locating the target in the image sequence.…”

Section: B Multi-dof Capabilitymentioning

confidence: 99%

“…One can also adapt the coarse-to-fine procedure to find out the potential regions where the template might be [182]. Notably, heuristic approaches such as particle swarm optimization [72] and artificial neural networks [185] have been developed rapidly in recent years and employed in the coarse search, which shows a promising performance to reduce the searching time. For the iterative searching method, Gauss-Newton and Levenberg-Marquardt algorithms outperform other gradient descent approximations in convergence speed and accuracy [186].…”

Section: Efficiencymentioning

confidence: 99%

See 1 more Smart Citation

A Review of Computer Microvision-Based Precision Motion Measurement: Principles, Characteristics, and Applications

Sheng

Pang

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Micro/nano engineering is an emerging field which enables engineering and scientific discoveries in the microworld. As an effective and powerful tool for automation and manipulation at small scales, precision motion measurement by computer micro-vision is now broadly accepted and widely used in micro/nano engineering. Unlike other measurement methods, the vision-based techniques can intuitively visualize the measuring process with high interactivity, expansibility, and flexibility. This review paper aims to comprehensively present a survey of micro-vision-based motion measurement from the collective experience. Working principles of micro-vision systems are firstly introduced and described, where the hardware configuration, model calibration, and motion measurement algorithms are systematically summarized. The characteristics and performances of different micro-vision-based methods are then analyzed and discussed in terms of measurement resolution, range, degree of freedom, efficiency, and error sources. Recent advances of applications empowered by the developed computer micro-visionbased methods are also presented. The review can be helpful to researchers who engage in the development of micro-vision-based techniques, as well as provide the recent state and tendency for the research community of vision-based measurement, manipulation, and automation at micro/nano scales.

show abstract

FPGA implementation of EFSME for high efficient video coding standard

Chatterjee

Vittapu

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Efficient block matching using improved particle swarm optimization with application to displacement measurement for nano motion systems

Cited by 10 publications

References 27 publications

TMsDP: two-stage density peak clustering based on multi-strategy optimization

TMsDP: two-stage density peak clustering based on multi-strategy optimization

A Review of Computer Microvision-Based Precision Motion Measurement: Principles, Characteristics, and Applications

FPGA implementation of EFSME for high efficient video coding standard

Contact Info

Product

Resources

About