Background Subtraction under Multiple Varying Illuminations in Different Background Luminance
Ming Yang Yang, Bo Yang, Men Ai Dong, Guo Yun Long · 2010
Background subtraction is widely used in detecting moving objects in a static scene, which requires a fixed camera, and a static background. Most background subtract algorithms require the illumination changing slowly, so can be tracked and updated. If the illumination changes fast and non-monotony, many algorithms fail. Here we research one scene in changing illumination: multiple continuous varying illuminations. This scene can be seen indoor or in the dark or underground architecture and can be expanded to some daytime scenes. We advance a new algorithm based on different background luminance through calculating the illumination factors. Its theory is similar to the single varying illumination we advanced before; it can relative precisely obtain the moving objects in this scene.