通过研究视频序列图像的灰度直方图,提出了一种新的基于灰度直方图的叠加原理算法,并构造了相应的近似叠加公式,该算法能够较好地描述背景和移动目标所形成的各种组合场景的灰度直方图,为进一步检测动态背景下的移动目标提供了一个良好基础。实验表明,在背景布局较为均匀的条件下,基于灰度直方图的叠加原理可以很好地描述背景与多目标所构成的各种组合场景。这种方法对于进一步分析动态视频中的移动目标具有重要意义。
Based on the study of gray histograms of video sequences, a new algorithm named the superposition principle of gray histograms and a corresponding approximate superposition formula is introduced, which can well describe the gray histogram of many video scenes formed by background and moving objects and afford an effective method of detecting moving objects in a dynamic background in the future. Experiments show that the superposition principle formula works well in such scenes as uniform background, and the principle can describe various combinations of scenes formed by the background and multiple objects, and detect moving objects in a dynamic background in future video analysis. It is helpful in video analysis.