激光与光电子学进展, 2018, 55 (8): 081003, 网络出版: 2018-08-13
一种改进的基于卡尔曼滤波的背景差分算法 下载: 954次
An Improved Background Subtraction Algorithm Based on Kalman Filtering
图像处理 运动检测 卡尔曼滤波 背景差分 分块分类 动态背景 image processing motion detection Kalman filtering background subtraction blocks classification dynamic background
摘要
基于卡尔曼滤波的背景差分算法存在背景更新不自适应,对光照变化、物体移入移出敏感等问题。提出了一种改进的以分类分块为核心的背景差分算法。首先,将前N帧视频序列图像求取均值得到初始背景模型;将第K帧图像与背景图像进行差分得到差分图像,再按照均值和标准差进行两次分类分块,分出前景块和背景块;在单个像素基础上对前景块进行背景细分割,确定运动目标区域;依据相邻两帧之间的灰度信息完成背景自适应更新。实验证明,本文算法能有效克服外界光线缓慢变化和背景中物体的轻微移动等问题。该算法具有较好的稳健性、相对较快的运算速度以及精确的运动目标区域。
Abstract
The background difference method based on Kalman filtering cannot adapt to the background update and it is sensitive to light changes and object moving. A modified background subtraction algorithm based on the idea of classification is proposed. First, the initial background model is gotten by averaging the first N frames of the video sequence images. Then, the difference image is obtained from the difference between the Kth image and the background image. The difference image is split into foreground and background blocks for two times and the classification criteria are the mean value and standard deviation. The foreground blocks are finely segmented based on a single pixel, and the moving targets region is determined. Finally, the adaptive background updating is conducted according to the gray value information between adjacent frames. The experimental results show that the proposed algorithm can effectively solve the problems of slow changes in external light and slight movement of objects in the background, and it has good robustness, relatively higher computing speed, and accurate moving targets area.
施龙超, 安玉磊, 苏秉华, 文博, 董泽华. 一种改进的基于卡尔曼滤波的背景差分算法[J]. 激光与光电子学进展, 2018, 55(8): 081003. Shi Longchao, An Yulei, Su Binghua, Wen Bo, Dong Zehua. An Improved Background Subtraction Algorithm Based on Kalman Filtering[J]. Laser & Optoelectronics Progress, 2018, 55(8): 081003.