| 基于噪声与阴影抑制多模态背景模型的运动物体检测 |
| |
| 引用本文： | 毛燕芬,施鹏飞.基于噪声与阴影抑制多模态背景模型的运动物体检测[J].东南大学学报,2004,20(4):423-426. |
| |
| 作者姓名： | 毛燕芬 施鹏飞 |
| |
| 作者单位： | 上海交通大学电子信息与电气工程学院，上海200030 |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划) |
| |
| 摘 要： | 针对场景照明变化、模型初始化以及阴影等问题, 提出了一种用于视频监视系统运动物体检测的统计多模态背景模型. 通过相隔固定的帧差值阈值化得到背景样本值, 并采用高斯核密度估计方法计算背景灰度的概率密度函数. 利用像素的邻域信息来去除由于摄像机抖动和场景小运动产生的噪声. HMMD色彩信息用来检测和抑制运动投射阴影. 实验结果验证了算法在交通监控前景物体分割中的有效性.
|
| 关 键 词： | 视频监视 背景模型 核密度估计 阴影抑制 HMMD色彩空间 |
Multimodal background model with noise and shadow suppression for moving object detection |
| |
| Mao Yanfen Shi Pengfei.Multimodal background model with noise and shadow suppression for moving object detection[J].Journal of Southeast University(English Edition),2004,20(4):423-426. |
| |
| Authors: | Mao Yanfen Shi Pengfei |
| |
| Abstract: | A statistical multimodal background model is described for moving object detection in video surveillance. The solution to some of the problems such as illumination changes, initialization of model with moving objects, and shadows suppression is provided. The background samples are chosen by thresholding inter-frame differences, and the Gaussian kernel density estimation is used to estimate the probability density function of background intensity. Pixel's neighbor information is considered to remove noise due to camera jitter and small motion in the scene. The hue-max-min-diff color information is used to detect and suppress moving cast shadows. The effectiveness of the proposed method in the foreground segmentation is demonstrated in the traffic surveillance application. |
| |
| Keywords: | video surveillance background model kernel density estimation shadow suppression hue-max-min-diff (HMMD) color space |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
