Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background
Advancing the background-subtraction method in dynamic scenes is an ongoing timely goal for many researchers. Recently, background subtraction methods have been developed with deep convolutional features, which have improved their performance. However, most of these deep methods are supervised, only...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/12/7/128 |
| _version_ | 1817984766371168256 |
|---|---|
| author | Tianming Yu Jianhua Yang Wei Lu |
| author_facet | Tianming Yu Jianhua Yang Wei Lu |
| author_sort | Tianming Yu |
| collection | DOAJ |
| description | Advancing the background-subtraction method in dynamic scenes is an ongoing timely goal for many researchers. Recently, background subtraction methods have been developed with deep convolutional features, which have improved their performance. However, most of these deep methods are supervised, only available for a certain scene, and have high computational cost. In contrast, the traditional background subtraction methods have low computational costs and can be applied to general scenes. Therefore, in this paper, we propose an unsupervised and concise method based on the features learned from a deep convolutional neural network to refine the traditional background subtraction methods. For the proposed method, the low-level features of an input image are extracted from the lower layer of a pretrained convolutional neural network, and the main features are retained to further establish the dynamic background model. The evaluation of the experiments on dynamic scenes demonstrates that the proposed method significantly improves the performance of traditional background subtraction methods. |
| first_indexed | 2024-04-13T23:49:04Z |
| format | Article |
| id | doaj.art-7a942054f7f04557a969d66cbd1eeecc |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-04-13T23:49:04Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-7a942054f7f04557a969d66cbd1eeecc2022-12-22T02:24:11ZengMDPI AGAlgorithms1999-48932019-06-0112712810.3390/a12070128a12070128Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic BackgroundTianming Yu0Jianhua Yang1Wei Lu2School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, ChinaSchool of Control Science and Engineering, Dalian University of Technology, Dalian 116024, ChinaSchool of Control Science and Engineering, Dalian University of Technology, Dalian 116024, ChinaAdvancing the background-subtraction method in dynamic scenes is an ongoing timely goal for many researchers. Recently, background subtraction methods have been developed with deep convolutional features, which have improved their performance. However, most of these deep methods are supervised, only available for a certain scene, and have high computational cost. In contrast, the traditional background subtraction methods have low computational costs and can be applied to general scenes. Therefore, in this paper, we propose an unsupervised and concise method based on the features learned from a deep convolutional neural network to refine the traditional background subtraction methods. For the proposed method, the low-level features of an input image are extracted from the lower layer of a pretrained convolutional neural network, and the main features are retained to further establish the dynamic background model. The evaluation of the experiments on dynamic scenes demonstrates that the proposed method significantly improves the performance of traditional background subtraction methods.https://www.mdpi.com/1999-4893/12/7/128background-subtractionconvolutional neural networkconvolutional features |
| spellingShingle | Tianming Yu Jianhua Yang Wei Lu Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background Algorithms background-subtraction convolutional neural network convolutional features |
| title | Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background |
| title_full | Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background |
| title_fullStr | Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background |
| title_full_unstemmed | Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background |
| title_short | Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background |
| title_sort | refinement of background subtraction methods based on convolutional neural network features for dynamic background |
| topic | background-subtraction convolutional neural network convolutional features |
| url | https://www.mdpi.com/1999-4893/12/7/128 |
| work_keys_str_mv | AT tianmingyu refinementofbackgroundsubtractionmethodsbasedonconvolutionalneuralnetworkfeaturesfordynamicbackground AT jianhuayang refinementofbackgroundsubtractionmethodsbasedonconvolutionalneuralnetworkfeaturesfordynamicbackground AT weilu refinementofbackgroundsubtractionmethodsbasedonconvolutionalneuralnetworkfeaturesfordynamicbackground |