Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network
To solve problems of noise points and high segmentation error for image shadow brought by traditional Vibe+ algorithm, a novel background segmentation method (Vibe++) based on the improved Vibe+ was proposed.Firstly, binarization image was acquired by using traditional Vibe+ algorithm from surveilla...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2021-03-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021046/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529113086525440 |
|---|---|
| author | Zihao LIU Xiaojun JIA Sulan ZHANG Zhiling XU Jun ZHANG |
| author_facet | Zihao LIU Xiaojun JIA Sulan ZHANG Zhiling XU Jun ZHANG |
| author_sort | Zihao LIU |
| collection | DOAJ |
| description | To solve problems of noise points and high segmentation error for image shadow brought by traditional Vibe+ algorithm, a novel background segmentation method (Vibe++) based on the improved Vibe+ was proposed.Firstly, binarization image was acquired by using traditional Vibe+ algorithm from surveillance video.The connected regions were marked based on the region-growing domain marker method.The area threshold was obtained with difference characteristics of boundary area, the connected regions below threshold were treated as disturbing points.Secondly, five different kernel functions were introduced to improve the traditional MeanShift clustering algorithm.After improving, this algorithm was fused effectively with partitioned convolutional neural network.Finally, program of classification of trailing area, non-trailing area and trailing edge area in the resulting image was performed.Position coordinates of the trailing area were calculated and confirmed, and the trailing area was quickly deleted to obtain the final segmentation result.This segmentation accuracy was greatly improved by using the proposed method.The experimental results show that the proposed algorithm can achieve segmentation accuracy of more than 98% and has good application effect and high practical value. |
| format | Article |
| id | doaj-art-a2cce4204ff54dde845e33e984ff1afb |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2021-03-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-a2cce4204ff54dde845e33e984ff1afb2025-01-15T03:26:01ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012021-03-013713314559807328Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural networkZihao LIUXiaojun JIASulan ZHANGZhiling XUJun ZHANGTo solve problems of noise points and high segmentation error for image shadow brought by traditional Vibe+ algorithm, a novel background segmentation method (Vibe++) based on the improved Vibe+ was proposed.Firstly, binarization image was acquired by using traditional Vibe+ algorithm from surveillance video.The connected regions were marked based on the region-growing domain marker method.The area threshold was obtained with difference characteristics of boundary area, the connected regions below threshold were treated as disturbing points.Secondly, five different kernel functions were introduced to improve the traditional MeanShift clustering algorithm.After improving, this algorithm was fused effectively with partitioned convolutional neural network.Finally, program of classification of trailing area, non-trailing area and trailing edge area in the resulting image was performed.Position coordinates of the trailing area were calculated and confirmed, and the trailing area was quickly deleted to obtain the final segmentation result.This segmentation accuracy was greatly improved by using the proposed method.The experimental results show that the proposed algorithm can achieve segmentation accuracy of more than 98% and has good application effect and high practical value.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021046/background segmentationclustering analysissegmentation accuracyconvolutional neural network |
| spellingShingle | Zihao LIU Xiaojun JIA Sulan ZHANG Zhiling XU Jun ZHANG Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network Dianxin kexue background segmentation clustering analysis segmentation accuracy convolutional neural network |
| title | Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network |
| title_full | Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network |
| title_fullStr | Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network |
| title_full_unstemmed | Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network |
| title_short | Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network |
| title_sort | vibe background segmentation method combining meanshift clustering analysis and convolutional neural network |
| topic | background segmentation clustering analysis segmentation accuracy convolutional neural network |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021046/ |
| work_keys_str_mv | AT zihaoliu vibebackgroundsegmentationmethodcombiningmeanshiftclusteringanalysisandconvolutionalneuralnetwork AT xiaojunjia vibebackgroundsegmentationmethodcombiningmeanshiftclusteringanalysisandconvolutionalneuralnetwork AT sulanzhang vibebackgroundsegmentationmethodcombiningmeanshiftclusteringanalysisandconvolutionalneuralnetwork AT zhilingxu vibebackgroundsegmentationmethodcombiningmeanshiftclusteringanalysisandconvolutionalneuralnetwork AT junzhang vibebackgroundsegmentationmethodcombiningmeanshiftclusteringanalysisandconvolutionalneuralnetwork |