改进的双模型的运动目标检测方法

Enhanced Dual Model Moving Target Detection Method

在动态背景下,由于双模型算法对运动目标检测时会出现误检、目标检测不完整和出现鬼影的现象,提出一种改进的双模型的运动目标检测算法。该算法首先对双模型背景的判断方式改进,将新来像素点图像值与背景模型对应位置样本值之间的距离和阈值进行比较,可以全面地区分前景和背景。然后对自适应阈值更新方式改进,通过对前景背景的判断情况把自模型和邻域模型结合起来,作为阈值增加或减少的条件,能够更精确地检测出前景。最后,结合帧间差分技术,通过比较对应位置像素值的时域变化来判断鬼影像素,以达到快速消除鬼影的目的。实验结果表明,改进算法的检测结果比原来的双模型更加精确、全面。

An improved dual model moving target detection method was presented as the result of the misjudge rate of the existing dual model algorithms, incompleted object detection and appearance of ghost in dynamic scenes. Firstly, the way of background judgement is improved to distinguish foreground comprehensively. The distance between the new pixel value and the sample value of background model is compared with the threshold. Secondly, the improved adaptive threshold is used for determining the foreground correctly. The combination of self model and neighborhood model by judging of foreground and background, which becomes the conditions of threshold＇ s increasing or reducing. Finally, by comparing the corresponding change of position pixel value to determine the ghost pixel, the inter frame difference technique was combined with in order to achieve the purpose of eliminating ghost rapidly. The experimental results demonstrate that the proposed method detects comprehensively the movement targets and its precision is improved as compared with that of the original dual model algorithm.