Pixel values may be obtained for a scene at two or more exposure levels, each exposure level corresponding to at least one of an exposure time interval different from that of another exposure level or an applied gain different from that of another exposure level. The pixel values may be aggregated into superpixel values, wherein each of the superpixel values includes a plurality of pixel values. A background model corresponding to each exposure level may be obtained. The superpixel values corresponding to each exposure level may be compared with the background model corresponding to each exposure level, to obtain an image change detection result for each exposure level. The image change detection results for each exposure level may be aggregated to obtain a combined image change detection result. A region of interest and/or a background region for the scene may be determined according to the combined image change detection result.