A linear approximation based method for noise-robust and illumination-invariant image change detection | |
Gao, B ; Liu, TY ; Cheng, QS ; Ma, WY | |
2004 | |
关键词 | video surveillance change detection linear algebra SEQUENCES |
英文摘要 | Image change detection plays a very important role in real-time video surveillance systems. To deal with the illumination, a category of linear algebra based algorithms were designed in the literature. They have been proved to be effective for surveillance environment with lighting and shadowing. In practice. other than illumination, the detecting process is also influenced by the noises of cameras and reflections. In this paper, analysis is made systemically on the existing linear algebra detectors, showing their intrinsic weakness in case of noises. In order to get less sensitive to noises, a novel method is proposed based on the technique of linear approximation. Theoretical and experimental analysis both show its robustness and high performance for noisy image change detection.; Computer Science, Information Systems; Computer Science, Theory & Methods; SCI(E); CPCI-S(ISTP); 0 |
语种 | 英语 |
出处 | SCI |
内容类型 | 其他 |
源URL | [http://hdl.handle.net/20.500.11897/400238] ![]() |
专题 | 数学科学学院 |
推荐引用方式 GB/T 7714 | Gao, B,Liu, TY,Cheng, QS,et al. A linear approximation based method for noise-robust and illumination-invariant image change detection. 2004-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论