Improved adaptive mixture of Gaussians model for moving objects detection
| Autor: | Fengqi Gao, Guanglong Wang, Wenjie Zhu, Jie Tian, Zhongtao Qiao |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Pixel
business.industry Computer science Gaussian Process (computing) Pattern recognition 0102 computer and information sciences 02 engineering and technology Mixture model 01 natural sciences Object detection symbols.namesake 010201 computation theory & mathematics 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Algorithm design Artificial intelligence business Spatial analysis Smoothing |
| Zdroj: | ICIA |
| DOI: | 10.1109/icinfa.2017.8079053 |
| Popis: | The spatial information of the video sequence is introduced into the background modeling process to deal with the problems of the traditional single-pixel based mixture of Gaussians moving objects detection method. Gaussian modeling process is improved to adaptively select the number of models, learning rate and other parameters by adjacent neighborhood pixels updating, spatio-temporal smoothing and other methods. The complete algorithm processing flow and steps of the algorithm are discussed in detail. The qualitative and quantitative experimental analysis and comparison results exhibit that the proposed algorithm has superior performances compared with traditional algorithms. The improved adaptive mixture of Gaussians model provides a novel method for solving the problem of moving objects detection in complex background. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|