Application of Improved Illumination Invariance Algorithm in Building Detection

Application of Improved Illumination Invariance Algorithm in Building Detection

Copyright: © 2014 |Pages: 10
DOI: 10.4018/978-1-4666-4896-8.ch003
OnDemand PDF Download:
No Current Special Offers


The problem of edge-based classification of natural video sequences containing buildings and captured under changing lighting conditions is addressed. The introduced approach is derived from two empiric observations: In static regions the likelihood of finding features that match the patterns of “buildings” is high because buildings are rigid static objects, and misclassification can be reduced by filtering out image regions changing or deforming in time. These regions may contain objects semantically different to buildings but with a highly similar edge distribution (e.g., high frequency of vertical and horizontal edges). Using these observations, a strategy is devised in which a fuzzy rule-based classification technique is combined with a method for changing region detection in outdoor scenes. The efficiency of the described techniques is implemented and tested with sequences showing changes in the lighting conditions.
Chapter Preview

2. Illumination Invariant Detection Of Changing Image Areas

The approach proposed in this section requires a preprocessing phase to filter out image areas changing in time. The results of this initial filtering are fed into the classifier to improve the detection rate and reduce the probability of misclassification. Most existing algorithms for detection of changing regions in video sequences do not consider illumination changes inherent to exterior conditions (Fathy, 1995), (Skifstad, 1989), (Zeljkovic, 2003). For this reason the algorithms frequently fail when applied to natural outdoor scenes. The model presented in this section initially assumes that the background is static. However, this limitation has been released in the actual implementation by assuming that global motion parameters of background objects are known. Motion compensation is applied using conventional approaches. Under this assumption the outcome of the preprocessing technique described below is the same if global motion parameters are used to compensate global changes of rigid background objects.

Complete Chapter List

Search this Book: