摘要
运动目标轮廓的有效提取对于目标识别、跟踪和行为的理解等后期的处理是非常重要的。受背景复杂性的影响,当背景灰度和运动目标的灰度相近时,提取的运动目标易产生空洞,某些部位无法完全恢复。根据帧差法的基本原理,提出了一种针对复杂背景的运动目标检测、轮廓提取方法。首先,对图像进行滤波处理,采用最大方差比阈值法消除了剩余部分噪声和背景,然后在三帧时间差分法基础上,利用序列中多帧图像融合运动信息,并确定参考区域,通过对原图像进行回扫描,最终提取出完整的运动目标轮廓。实验结果验证了算法的稳健性和有效性。
Effective extraction of the moving object silhouette is essential for the subsequent processing, including target identification, tracking, behavior comprehension, and so on, In some cases, especially when there is low contrast in gray between the background and moving object, the recovered-object is often made up of holes and distorted parts. To improve the performance of extraction in such situation, a modified method based on the principle of frames subtraction was presented. Firstly pre-filtering was needed to alleviate the Gauss noise. Secondly, a maximum variance ratio threshold value was used to remove the remaining noise and background. Then some frames were fused to obtain more information about the moving object, and an area for reference was defined at the same time. After scanning the original image, the moving object silhouette was recovered. Experiment results prove that the modified method is more robust, and superior to other traditional ones.
出处
《计算机应用》
CSCD
北大核心
2006年第1期123-126,共4页
journal of Computer Applications
关键词
运动目标
复杂背景
帧差法
多帧图像融合
低对比度
moving object
complicated background
frame subtraction
frames fusion
low-contrast