Name
Title | ||
|---|---|---|
Real-Time Statistical Background Learning for Foreground Detection under Unstable Illuminations |
Abstract | ||
|---|---|---|
This work proposes a fast background learning algorithm for foreground detection under changing illumination. Gaussian Mixture Model (GMM) is an effective statistical model in background learning. We first focus on Titterington's online EM algorithm that can be used for real-time unsupervised GMM learning, and then advocate a deterministic data assignment strategy to avoid Bayesian computation. The color of the foreground is apt to be influenced by the environmental illumination that usually produce undesirable effect for GMM updating, however, a collinear feature of pixel intensity under changing light is discovered in RGB color space. This feature is afterward used as a reliable clue to decide which part of mixture to update under changing light. A foreground detection step proposed in early version of this work is employed to extract foreground objects by comparing the estimated background model with the current video frame. Experiments have shown the proposed method is able to achieve satisfactory static background images of scenes as well as is also superior to some mainstream methods in detection performance under both indoor and outdoor scenes. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/ICMLA.2012.85 | ICMLA (1) |
Keywords | Field | DocType |
real-time statistical background learning,video signal processing,detection performance,unsupervised gmm learning,satisfactory static background image,unstable illuminations,bayesian computation,foreground detection step,foreground object,lighting,bayes methods,statistical analysis,learning (artificial intelligence),estimated background model,titterington online em algorithm,real-time unsupervised gmm learning,pixel intensity,collinear feature,fast background,satisfactory static background images,rgb color space,online em algorithm,gaussian processes,object detection,foreground detection,background learning,environmental illumination,gaussian mixture model,video frame,image colour analysis,learning artificial intelligence | Background subtraction,Computer science,RGB color space,Foreground detection,Artificial intelligence,Object detection,Computer vision,Pattern recognition,Expectation–maximization algorithm,Pixel,Statistical model,Mixture model,Machine learning | Conference |
Volume | ISBN | Citations |
1 | 978-1-4673-4651-1 | 1 |
PageRank | References | Authors |
0.40 | 3 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dawei Li | 1 | 53 | 3.77 |
| Lihong Xu | 2 | 18 | 1.75 |
| Erik Goodman | 3 | 145 | 15.19 |