An improved graph cut algorithm in stereo matching

Lu, Baoli; Sun, Liang; Yu, Lina; Dong, Xianlin

doi:10.1016/j.displa.2021.102052

Cited by 24 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is paper implements intelligent control on dance teaching using BPNN algorithm [3] and artificial intelligence technology [4][5][6], which can control multiple parameters without repeatability and with a wide change range in response to changes in the external environment and resolve challenging nonlinear control issues [7,8].…”

Section: Introductionmentioning

confidence: 99%

[Retracted] An Adaptive Dance Motion Smart Detection Method Using BP Neural Network Model under Dance Health Teaching Scene

Liu

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

As a body movement art, dance has its special form of expression. In terms of dance vocabulary, it can be roughly divided into two parts: external body movement and internal modality. In the process of body movement, it conveys information through silent language and the audience directly feels the information given by the dance image through vision. This is the special way of expressing emotion and meaning in dance art. This paper combines artificial intelligence technology and BP neural network (BPNN) algorithm to intelligently control dance teaching and solve complex nonlinear control problems. This paper studies dance teaching based on artificial intelligence technology. In this paper, BPNN algorithm and PCA-BPNN algorithm are used to test the dance teaching training of dance language, dance music, and stage art. The average accuracy of the BPNN evaluation model is 85.35% when the time reaches 80, while the average accuracy of the PCA-BPNN evaluation model is 65.64%. This shows that the accuracy of the BPNN evaluation model is higher than that of the PCA-BPNN evaluation model. Under the artificial intelligence technology, the dance using BPNN algorithm brings more intense sensory stimulation to the viewer because of the accompaniment of music, so as to achieve the infection and enjoyment of beauty and achieve the harmonious unity of sports and art.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] An Adaptive Dance Motion Smart Detection Method Using BP Neural Network Model under Dance Health Teaching Scene

Liu

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

show abstract

“…(1)SADWinSize (SWS): The size of the SAD window in the cost calculation step, SW, should be an odd number, generally in the range (3,11).…”

Section: Experimental Parameters Selectionmentioning

confidence: 99%

“…The global stereo matching algorithms use global optimization algorithms for parallax estimation, mainly DP [10], GC [11], and BP [12] algorithms. This class of algorithms converts the stereo matching problem into solving the energy function minimization problem in the energy function framework.…”

Section: Introductionmentioning

confidence: 99%

Binocular Stereo Matching Based on SGM and Flood Filling Algorithm

Song

Shu

et al. 2022

Preprint

View full text Add to dashboard Cite

The SGM algorithm was weak in matching the occluded area and parallax discontinuity area in stereo matching, and it was easy to produce more voids. To address this question, the paper proposes a parallax optimizati-on algorithm based on SGM algorithm combined with flood filling and median smoothing. The algorithm fills the missing parallax values based on the parallax values at the edges of the voids and achieves the repair of the missing parallax in the parallax map without raising a large computational effort. The proposed algorithm has also been qua-ntitatively analyzed on the Middlebury stereo matching dataset using three evaluation metrics: root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity (MSSIM). The experimental results show that the improvement and optimization of the SGM algorithm can effectively fill the voids in the parallax map and reduce the noise of the image, and the matching accuracy of parallax maps is improved by an average of 9%.

show abstract

“…At present, there are endless reports on the use of digital image processing to extract infrared image targets and boundaries. For example, LU B [10] proposed an improved graph cut extraction algorithm based on the Census transform. This algorithm introduces the Census transform into the data items of the energy function to achieve good extraction results in weak or repeated texture target areas.…”

Section: Introductionmentioning

confidence: 99%

Research on infrared image target extraction method based on constrained Otsu method

Wu,

Lv,

Tan

2023

Third International Computing Imaging Conference (CITA 2023)

View full text Add to dashboard Cite

Infrared images have advantages such as strong anti-interference ability and working day and night, and have been widely used in important places monitoring, traffic management, and other fields. However, infrared images also have problems such as poor contrast and low signal-to-noise ratio, which result in the feature extraction of targets in infrared images not being visible and bright and cannot meet the needs of target recognition in complex backgrounds. Based on this, a fusion method combining interactive strokes-based Otsu method with morphological operations is proposed. This method is based on the principle of maximum inter class variance, maximum flow/minimum cut, and digital morphology to establish an image object extraction model, which takes into account the accuracy and noise resistance of image extraction.

show abstract

An improved graph cut algorithm in stereo matching

Cited by 24 publications

References 35 publications

[Retracted] An Adaptive Dance Motion Smart Detection Method Using BP Neural Network Model under Dance Health Teaching Scene

[Retracted] An Adaptive Dance Motion Smart Detection Method Using BP Neural Network Model under Dance Health Teaching Scene

Binocular Stereo Matching Based on SGM and Flood Filling Algorithm

Research on infrared image target extraction method based on constrained Otsu method

Contact Info

Product

Resources

About