Real Time Motion and Color Detection

Abstract

When using HD video cameras in stores a large storage space is needed. The required
 storage space can be decreased using motion and a color detection algorithm that
 makes the camera records only when a motion or a lighting change occur. So, in this
 work a real time motion and color detection is presented based on the difference of
 two successive frames of images after dividing the image into blocks, different block
 sizes are tested (2×2, 4×4 , and 8×8).YCbCr color system is used for each case with
 different thresholds for Cb, Cr, and Y. Good results for the motion detection can be
 obtained using Cb, and Cr other than Y, since the coloring components of an image are
 exist in Cr, and Cb, which are important for motion detection. Additionally the
 components that produce or reflect bright light can be obtained from Y. Consequently
 the result of lightening change detection at different illumination conditions is better
 using Y more than Cb, and Cr. This means that the best result for both motion, and
 lighting change detection is obtained by combining the chrominance (Cb, Cr) and
 luminance (Y) components of a video. The data used in this work are collected in an
 indoor environment using a laptop webcam under different illumination conditions.

Applying color recognition techniques to achieve low-cost portable digital board functionalities

“…However, we first needed to ensure that these cameras can fulfill our needs. There are successful research projects using cameras for color-based object detection [17], including real-time moving objects [13] and images with similar colors [26]. This leaves which is the minimum resolution that the camera needs to fulfill our purposes as the only question to be answered.…”