A Monte-Carlo-based algorithm for background generation./
By: Abu, Patricia Angela R.
Contributor(s): Chu, Varian Sherwin | Fernandez, Proceso.
Description: vol. 6, 8 tables, 7 figs, refs.ISSN: 2012-0761 .Other title: Philippine Information Technology Journal.Subject(s): IMAGE PROCESSING AND COMPUTER VISION-SCENE ANALYSIS | PROBABILITY AND STATISTICS-PROBABILISTIC ALGORITHMSDDC classification: 050/Ab91 Summary: In this study, a Monte-Carlo-based algorithm, named CRF, was developed for generating background images from a video sequence. This algorithm is a variant of the Teknomo-Fernandez (TF) algorithm, an efficient background generation algorithm that also incorporates the Monte-Carlo concept and applies simple logical bit operations. Two different configurations of CRF were implemented, i.e. CRF .2 and CRF 81.1. A brute force algorithm that generates the ground truth using modal pixel bit values was also developed in order to analyze the empirical performances of the TF algorithm and the 2 CRF configurations. Experiments on some colored video tests show that the CRF configurations outperform the TF algorithm in terms of accuracy. However, the TF algorithm remains more efficient in terms of processing time.| Item type | Current location | Collection | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|---|
Periodicals Journal Bound
|
College Library Periodical Section | GC | AI 050/Ab91 (Browse shelf) | Available |
Browsing College Library Shelves , Shelving location: Periodical Section , Collection code: GC Close shelf browser
In this study, a Monte-Carlo-based algorithm, named CRF, was developed for generating background images from a video sequence. This algorithm is a variant of the Teknomo-Fernandez (TF) algorithm, an efficient background generation algorithm that also incorporates the Monte-Carlo concept and applies simple logical bit operations. Two different configurations of CRF were implemented, i.e. CRF .2 and CRF 81.1. A brute force algorithm that generates the ground truth using modal pixel bit values was also developed in order to analyze the empirical performances of the TF algorithm and the 2 CRF configurations. Experiments on some colored video tests show that the CRF configurations outperform the TF algorithm in terms of accuracy. However, the TF algorithm remains more efficient in terms of processing time.
There are no comments for this item.