| Journal of Computer Science | |
| A Block-Based Multi-Scale Background Extraction Algorithm | Science Publications | |
| Fatimah Khalid1  Maryam Golchin1  Seyed H. Davarpanah1  | |
| 关键词: Background extraction; background modeling; multistate modeling; block-based modeling; foreground; | |
| DOI : 10.3844/jcssp.2010.1450.1456 | |
| 学科分类:计算机科学(综合) | |
| 来源: Science Publications | |
PDF
|
|
【 摘 要 】
Problem statement: To extract the moving objects, vision-based surveillance systemssubtract the current image from a predefined background image. The efficiency of these systemsmainly depends on accuracy of the extracted background image. It should be able to adapt to thechanges continuously. In addition, especially in real-time applications the time complexity of thisadaptation is a critical matter. Approach: In this study, to extract an adaptive background, acombination of blocking and multi-scale methods is presented. Because of being less sensitive to localmovements, block-based techniques are proper to control the non-stationary objects
【 授权许可】
Unknown
【 预 览 】
| Files | Size | Format | View |
|---|---|---|---|
| RO201911300585318ZK.pdf | 292KB |
PDF