Segmentation of visual images under complex outdoor conditions

Abstract

Motion detection and segmentation of traffic vehicles in an outdoor environment, particularly under non ideal weather conditions, in the presence of camera noise and with variable or unfavorable luminance conditions is still an area of active research. Gaussian based background modeling is commonly used to detect moving objects in computer vision systems. However, it has some limitations it cannot effectively deal with sudden change in illumination, snowfall, fog, and repetitive motions such as swaying leaves. These nonideal outdoor conditions result in false motion detection. An alternative technique propose to detect and segment the moving vehicles by making use of dynamically adaptive threshold using the full-search sum of absolute difference (FSSAD) algorithm. Motion energy is obtained using sequence of frames that can be effectively be used to differentiate between moving vehicles and a dynamic background. Adaptive-motion threshold is used. It not only reduces the false motion but improves the computational efficiency as well.