Loading...
Please wait, while we are loading the content...
Similar Documents
Foreground Background Segmentation using Temporal and Spatial Markov Processes (2000)
| Content Provider | CiteSeerX |
|---|---|
| Author | Kumar, Pankaj Sengupta, Kuntal |
| Description | In this paper, we present a novel approach in extracting interesting foreground regions from a complex and largely stationary background scene. The method is a substantial extension to the existing background subtraction techniques. The advantage of the proposed technique are the following: it removes false detection due to shadow, due to illumination changes caused by Automatic Exposure Correction (AEC), and ensures temporal and spatial contiguity in the results. A background pixel is first statistically modelled by two Gaussian distributions. These statistical estimates are used next as important parameters in test for spatial and temporal contiguity in the foreground regions. Temporal contiguity of pixels are ensured by modelling the pixel value as a Markov Random Sequence and the Bayes smoothing is applied on the result of the foreground/background hypothesis test. Spatial contiguity is ensured by using Markov Random Fields. We make an analogy of a pixel process in a neighborhood of pixels and a lattice site in a lattice structure. The spatial constraints are applied by applying the Gibb's energy distribution function. The segmentation results are quite fast (about 3 frames a second on a desktop PC with a 500 MHz Pentium III processor) and comparative analysis shows that it is more accurate than most existing background-foreground segmentation algorithms. |
| File Format | |
| Language | English |
| Publisher Date | 2000-01-01 |
| Publisher Institution | DRAA FOR IEEE TRANSACTIONS ON IMAGE PROCESSING |
| Access Restriction | Open |
| Subject Keyword | Hypothesis Test Interesting Foreground Region Novel Approach Background-foreground Segmentation Algorithm Illumination Change Lattice Structure Background Pixel Temporal Contiguity Statistical Estimate Desktop Pc Stationary Background Scene Pixel Process Spatial Constraint False Detection Important Parameter Energy Distribution Function Markov Random Field Gaussian Distribution Lattice Site Segmentation Result Automatic Exposure Correction Spatial Markov Process Background Subtraction Technique Pixel Value Comparative Analysis Foreground Background Segmentation Bayes Smoothing Substantial Extension Foreground Region Markov Random Sequence Mhz Pentium Iii Processor Spatial Contiguity |
| Content Type | Text |
| Resource Type | Article |
