Illumination independent change detection for real world image sequences
Computer Vision, Graphics, and Image Processing
Color Space Selection for Moving Shadow Elimination
ICIG '07 Proceedings of the Fourth International Conference on Image and Graphics
Statistical change detection with moments under time-varying illumination
IEEE Transactions on Image Processing
Image change detection algorithms: a systematic survey
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
In this paper a new application of information retrieval techniques for detecting moving objects in multiple & color images is presented. We have used circular shift moments extraction from gray scale images. For color images color edges were used as features. This technique makes use of a color edge detection scheme, applied to the difference between current and reference frame. The edges are filled using morphological filtering of dilations and erosions. The images used were taken from a stationary camera. In this work, a statistical decision rule is proposed to cope with the effects of noise. Moreover the computation time is compared with shading model method. All the techniques are tested under constant illumination, varying illumination, Gaussian noise, and speckle noise. The performance is compared on the basis of parameters such as detection rate, false rate, misses rate, and percentage correct classification. Simulation results show that, circular shift moments and color edges retrieve changes in moving objects accurately under time varying illumination case.