动态阈值的Vibe运动目标检测

发布时间：2018-03-03 19:36

本文选题：光照变化　切入点：运动目标　出处：《计算机工程与应用》2017年11期 　论文类型：期刊论文

【摘要】：Vibe算法是一种高效的像素级背景建模算法,但是它同混合高斯模型一样,不能适应光线突变的问题,在对Vibe算法的基础上提出了一种在静态场景下对光照变化鲁棒的运动目标检测方法。该方法首先利用Vibe模型建立背景样本集,并利用Vibe模型对判别为背景的像素对背景帧进行更新。其次视频当前图像帧与背景帧差分,并采用Otsu算法计算图像的分割阈值来检测运动目标。实验结果表明,改进的方法能够很好地消除由于环境光照变化引起的"曝光"现象,提高了运动目标检测的精确度,并且改进的算法对室内场景下的阴影也有较好的抑制作用。
[Abstract]:The Vibe algorithm is an efficient pixel level background modeling algorithm, but like the mixed Gao Si model, it can not adapt to the sudden change of light. Based on the Vibe algorithm, this paper proposes a robust method for detecting moving objects in a static scene. Firstly, a background sample set is established by using the Vibe model. The background frame is updated by using Vibe model. Secondly, the difference between the current image frame and the background frame is obtained, and the segmentation threshold of the image is calculated by using the Otsu algorithm. The experimental results show that, The improved method can eliminate the "exposure" phenomenon caused by the change of ambient illumination, improve the accuracy of moving target detection, and the improved algorithm can restrain the shadow in the indoor scene.
【作者单位】：辽宁科技大学软件学院;
【基金】：鞍山市科技项目(鞍科发【2014】29号)
【分类号】：TP391.41

【相似文献】