No abstract

No abstract

Detection algorithm for pedestrians is proposed for the real surveillance system based on color similarity for dynamic color images under low illumination, where the proposed color similarity is defined by color change vectors in the L*a*b* color metric space and the time taken by pedestrians to pass between surveillance camera. It provides continuous detection results through surveillance cameras under lower luminance conditions in real surveillance system. Experimental results for dynamic image taken under low illumination in streets show that detected frames with the proposed algorithm increased by 20% compared to detection results without geographic information. The proposed algorithm is being considered for use in poor security areas in downtown Japan.

No abstract

Color restoration algorithm using color instance-based reasoning is proposed. The proposed system does not employ a physical model but color instance. The color instance, Color Change Vector, is defined based on distribution of color values for 175 color scheme cards taken under low and standard illuminations. Modification of CCV is proposed based on color value and linguistic expression. The given image is restored by adding the appropriate color instances for a given color value. A prototype system for color restoration is constructed. An experiment is done with dynamic images of an outdoor walking person, to evaluate the performance of the proposed system in terms of color-difference and processing time. The proposed method presents a foundation for identifying a person captured by a practical security system using a low cost CCD camera.