Name
Abstract | ||
|---|---|---|
Illumination changes cause challenging problems for video surveillance algorithms, as objects of interest become masked by changes in background appearance. It is desired for such algorithms to maintain a consistent perception of a scene regardless of illumination variation. This work introduces a concept we call Big Background, which is a model for representing large, persistent scene features based on chromatic self-similarity. This model is found to comprise 50% to 90% of surveillance scenes. The large, stable regions represented by the model are used as reference points for performing illumination compensation. The presented compensation technique is demonstrated to decrease improper false-positive classification of background pixels by an average of 83% compared to the uncompensated case and by 25% to 43% compared to compensation techniques from the literature. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1155/2011/171363 | EURASIP J. Image and Video Processing |
Keywords | Field | DocType |
bigbackground-based illumination compensation,illumination compensation,surveillance scene,big background,illumination change,background appearance,video surveillance algorithm,surveillance video,illumination variation,background pixel,compensation technique,persistent scene | Computer vision,Pattern recognition,Chromatic scale,Computer science,Pixel,Artificial intelligence,Biometrics,Perception | Journal |
Volume | Issue | ISSN |
2011, | 1 | 1687-5281 |
Citations | PageRank | References |
5 | 0.59 | 19 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. Ryan Bales | 1 | 8 | 1.11 |
| Dana Forsthoefel | 2 | 11 | 2.18 |
| Brian Valentine | 3 | 13 | 1.77 |
| D. ScottWills | 4 | 5 | 0.59 |
| Linda M Wills | 5 | 293 | 40.95 |