Abstract: Object detection plays very important role in image processing. In which detection of pedestrian gains lot of interest due to it’s direct application in security system, visual surveillance etc. Occlusion means hiding of an object by another object during multiple human tracking. Different methods are implemented for pedestrian detection but that methods suffer from performance degradation due to occlusions, deformations and illuminations. In this paper problem of occlusion is addressed and this system uses two-stage classifier with circulant structure with kernel, named Integrated Circulant Structure Kernels (ICSK). The first stage is applied for transition estimation and the second is used for scale estimation. The circulant structure makes our algorithm realize fast learning and detection. Then, the ICSK is used to detect the target without occlusion and build a classifier pool to save these classifiers with noisy updates. When the target is in heavy occlusion or after long-term occlusion, redetect it using an optimal classifier selected from the classifier-pool according to an entropy minimization criterion.

Keywords: Pedestrian Detection; Visual Surveillance; Occlusion; Integrated Circulant Structure Kernels (ICSK), Object detection

| DOI: 10.17148/IJIREEICE.2018.675