Improved Illumination Independent Moving Object Detection Algorithm

Improved Illumination Independent Moving Object Detection Algorithm

Copyright: © 2014 |Pages: 8
DOI: 10.4018/978-1-4666-4896-8.ch002

Abstract

A real time change detection technique is proposed in order to detect the moving objects in a real image sequence. The described method is independent of the illumination of the analyzed scene. It is based on a comparison of corresponding pixels that belong to different frames and combines time and space analysis, which augments the algorithm’s precision and accuracy. The efficiency of the described technique is illustrated on a real world interior video sequence recorded under significant illumination changes.
Chapter Preview
Top

2. Methodology

Image sequence 978-1-4666-4896-8.ch002.m01consisting of N video frames is observed. The sliding mask 978-1-4666-4896-8.ch002.m02 is applied on every frame.

Skifstad and Jain, (Skifstad, 1989), use the ratio of pixel intensities in mask 978-1-4666-4896-8.ch002.m03 between two a reference and a current frame to estimate the pixel variance 978-1-4666-4896-8.ch002.m04 as follows:

978-1-4666-4896-8.ch002.m05, 978-1-4666-4896-8.ch002.m06. (1)

Here, pixel intensities within mask 978-1-4666-4896-8.ch002.m07 are denoted with 978-1-4666-4896-8.ch002.m08 for a reference, background frame that does not contain changing regions and with 978-1-4666-4896-8.ch002.m09 for a current frame where moving objects are being identified. The mean of the pixel intensity ratio within 978-1-4666-4896-8.ch002.m10 is denoted with978-1-4666-4896-8.ch002.m11. If 978-1-4666-4896-8.ch002.m12 (where 978-1-4666-4896-8.ch002.m13 is a suitable threshold), the center of the mask 978-1-4666-4896-8.ch002.m14 is marked as changing region.

Experiments in (Inigo, 1989), (Mecocci, 1989), (Rourke, 1990), (Fathy, 1995), (Corall, 1991), (Foresti, 1998), (Foresti, 1994) have shown that for significant illumination changes this method fails, i.e. some pixels are falsely assigned to changing regions. A modified technique based on adaptive coefficient for illumination compensation is proposed in this chapter. Pixel variance is estimated as:

978-1-4666-4896-8.ch002.m15
(2)

Complete Chapter List

Search this Book:
Reset