ABSTRACT
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.
- Fu, C. W. and Chang, S. A motion estimation algorithm under time varying illumination case. Pattern Recognit. Lett., vol. 10, 1989, 195--199.Google ScholarCross Ref
- Nagel, H. H. Recent advances in motion interpretation based on image sequences. ICASSP, 1982, 1179--1186.Google Scholar
- Radke, R. J., Andra, S. Image Change Detection Algorithm: A Systematic Survey. IEEE Trans. On Image Processing, vol. 14, no. 3, Mar 2005, 294--307. Google ScholarDigital Library
- Jain, R. Difference and accumulative difference pictures in dynamic scene analysis. Image Vision Comput. 2, 1984, 99--107.Google ScholarCross Ref
- Skifstad, K. and Jain, K. Illumination independent change detection from real world image sequences. Comput. Vis., Graph., Image Process., vol. 46, 1989, 387--399. Google ScholarDigital Library
- Liu, S. C. Statistical change detection with moments under time-varying illumination. IEEE Trans. On Image Processing, vol. 7, no. 9, 1998, 1258--1268. Google ScholarDigital Library
- Cavallaro, A. and Ebrahami, T. Change Detection Based on Color Edges. IEEE Trans, 2001, 141--144.Google Scholar
- Wesolkowski, S., Jernigan, M. E. and Dony R. D. Comparison of Color Image Edge Detectors in Multiple Color Spaces. IEEE Trans, 2000, 796--799.Google Scholar
- Shan, Y., Yang, F. and Wang, R. Color Space Selection for Moving Shadow Elimination. Fourth International Conference on Image and Graphics, IEEE Computer Society, 2007, 496--501. Google ScholarDigital Library
Index Terms
- Retrieval of changes in moving objects in multiple and color images
Recommendations
A comparison of color coordinate systems using color classification and image segmentation results of humans
Here we present a comparison of color coordinate systems using two types of image segmentation data created by human subjects. The first type was created based on color classification of pixels using color information alone as perceived by human ...
Contrast Enhancement of RGB Color Images by Histogram Equalization of Color Vectors’ Intensities
Intelligent Computing MethodologiesAbstractThe histogram equalization (HE) is a technique developed for image contrast enhancement of grayscale images. For RGB (Red, Green, Blue) color images, the HE is usually applied in the color channels separately; due to correlation between the color ...
Color recovery of black-and-white halftoned images via categorized color-embedding look-up tables
A new method of recovering the original colors of black-and-white (B&W) halftoned images with homogeneous dot patterns is proposed. The conventional inverse halftoning method, which uses a look-up table (LUT), can establish the relation between the ...
Comments