Implicit Progressive-Iterative                         Algorithm of Curves and Surfaces with Compactly Supported Radial Basis                         Functions

Wang, Haibo; Liu, Tao; Liu, Bo; Wei, Wenqing; Liu, Xinru; Liu, Pingbo; Bai, Yanyu; Chen, Yue

doi:10.3724/sp.j.1089.2021.18807

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A particular form of neural network known as an ANN learns and self-trains the network parameters to achieve the best desirable output outcomes given the input circumstances. The basic BP algorithm includes two processes: forward signal transmission and reverse error transmission [20]. In the process of backpropagating the error layer by layer, each layer shares the error and adjusts the weight so that the error decreases along the gradient direction.…”

Section: Mtd Algorithm For Dynamic Image Sequences On the Basis Of Annmentioning

confidence: 99%

See 1 more Smart Citation

Moving Target Detection Algorithm for Dynamic Image Sequences on The Basis of Artificial Neural Network

Jia-Min Zhang,

Jia-Min Zhang

2023

Journal of Computers

View full text Add to dashboard Cite

<p>Due to the large changes in dynamic image sequence frames and the complex detection scene, it is difficult to accurately detect moving objects. Therefore, the study proposes a moving target detection algorithm based on artificial neural network. First, the algorithm performs standardized grayscale processing and gamma correction processing on the dynamic image to eliminate the noise interference of the dynamic image. After that, the model calculates the gradient of the dynamic image in order to complete the feature extraction of the dynamic image. Then, according to the result of hog feature extraction, the study adopts the inter-frame calculation method to update the background of the dynamic image. Finally, the principle and structure of the neural network are analyzed experimentally, and a channel attention mechanism is introduced to train dynamic image sequences to obtain MTD results. Experimental results show that the proposed algorithm achieves higher accuracy in MTD than conventional detection algorithms. The calculation efficiency of the algorithm in this paper has significant advantages, and the average detection time is 3.69515ms, which can meet the real-time requirements of MTD.</p> <p> </p>

show abstract

Section: Mtd Algorithm For Dynamic Image Sequences On the Basis Of Annmentioning

confidence: 99%

“…In the formula (20), the kernel parameters γ reflect the distribution characteristics of the data samples. Sparrow search algorithm is an optimization algorithm that transforms the foraging and anti-predation behavior rules of sparrows in nature.…”

Section: Featuresmentioning

confidence: 99%

Moving Target Detection Algorithm for Dynamic Image Sequences on The Basis of Artificial Neural Network

Jia-Min Zhang,

Jia-Min Zhang

2023

Journal of Computers

View full text Add to dashboard Cite

show abstract

“…For large datasets, the convergence of I-PIA may be relatively slow, affecting the reconstruction algorithm's computational efficiency. Therefore, some work has been done to accelerate the convergence rate of I-PIA or improve the computational efficiency of the I-PIA; see the relaxed implicit randomized algebraic reconstruction technique [13]; randomized implicit progressive-iterative approximation [14]; I-PIA with acceleration factor [15]; accelerated I-PIA based on conjugate gradient method [16]; and so on.…”

Section: Introductionmentioning

confidence: 99%

Fast Surface Reconstruction Technique Based on Anderson Accelerated I-PIA Method

Dai,

Yi,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

For curve and surface reconstruction, the implicit progressive-iterative approximation (I-PIA) is widely used in many applications because it is efficient in data fitting and handling noise and missing data. By introducing Anderson extrapolation to the I-PIA, in this paper we exploit an accelerated method, namely AA-I-PIA, for the I-PIA of the B-spline function. For noisy point cloud data, we have exploited the regularized I-PIA and its accelerated version. We have shown that the AA-I-PIA method converges for appropriate parameters. Numerical results show that regardless of missing or noisy data, the (regularized) AA-I-PIA outperforms the classical I-PIA method regarding the number of iterations and elapsed CPU time.

show abstract

Implicit Uniform Rational Spline Reconstruction Method With Regularization Term

Huang

2024

IEEE Access

View full text Add to dashboard Cite

Implicit Progressive-Iterative Algorithm of Curves and Surfaces with Compactly Supported Radial Basis Functions

Cited by 4 publications

References 12 publications

Moving Target Detection Algorithm for Dynamic Image Sequences on The Basis of Artificial Neural Network

Moving Target Detection Algorithm for Dynamic Image Sequences on The Basis of Artificial Neural Network

Fast Surface Reconstruction Technique Based on Anderson Accelerated I-PIA Method

Implicit Uniform Rational Spline Reconstruction Method With Regularization Term

Contact Info

Product

Resources

About