| 1. |
- Xu, Zhifei, et al.
(författare)
-
An Eigenbackground Subtraction Method using Recursive Error Compensation
- 2006
-
Ingår i: to appear in "Advances in Multimedia Information Processing - PCM 2006", LNCS (Springer) Vol. 4261, 2006. ; 4261
-
Konferensbidrag (refereegranskat)abstract
- Eigenbackground subtraction is a common method for movingobject detection. The method uses the difference between input image and the reconstructed background image to detect foreground objects based on eigenvalue decomposition. In the method, foreground regions are represented in the reconstructed image using eigenbackground. This results in errors that are spread out over the entire reconstructed reference image. This will also result in degradation of quality of reconstructed background leading to inaccurate moving object detection. In order to compensate these regions, an efficient recursive error compensation method is proposed. The experimental results show that a better approximation of the background is constructed by the proposed method and more accurate foreground objects can be detected based on the reconstructed background.
|
|
| 2. |
- Xu, Zhifei, et al.
(författare)
-
Recursive Error-Compensated Dynamic Eigenbackground Learning and Adptive Background Subtraction in Video
- 2008
-
Ingår i: Optical Engineering. - : SPIE-Intl Soc Optical Eng. - 1560-2303 .- 0091-3286. ; 47:5, s. 11 pages (article No. 057001)-
-
Tidskriftsartikel (refereegranskat)abstract
- We address the problem of foreground object detection through background subtraction. Although eigenbackground models are successful in many computer vision applications, background subtraction methods based on a conventional eigenbackground method may suffer from high false-alarm rates in the foreground detection due to possible absorption of foreground changes into the eigenbackgroundmodel. This paper introduces an improved eigenbackground modeling method for videos by recursively applying an error compensation process to reduce the influence of foreground moving objects on the eigenbackground model. An adaptive threshold method is also introduced for background subtraction, where the threshold is determined by combininga fixed global threshold and a variable local threshold. A fast algorithm is then given as an approximation to the proposed method by imposing and exploiting a constraint on motion consistency, leading to about 50% reduction in computations. Experiments have been performed on a rangeof videos with satisfactory results. Performance is evaluated using an objective criterion. Comparisons are made with two existing methods.
|
|
