We propose a novel feature, local histogram of figure/ground segmentations, for robust and efficient background subtraction (BGS) in dynamic scenes (e.g., waving trees, ripples in water, illumination changes, camera jitters, etc.). We represent each pixel as a local histogram of figure/ground segmentations, which aims at combining several candidate solutions that are produced by simple BGS algorithms to get a more reliable and robust feature for BGS. The background model of each pixel is constructed as a group of weighted adaptive local histograms of figure/ground segmentations, which describe the structure properties of the surrounding region. This is a natural fusion because multiple complementary BGS algorithms can be used to build background models for scenes. Moreover, the correlation of image variations at neighboring pixels is explicitly utilized to achieve robust detection performance since neighboring pixels tend to be similarly affected by environmental effects (e.g., dynamic scenes). Experimental results demonstrate the robustness and effectiveness of the proposed method by comparing with four representatives of the state of the art in BGS.