التفاصيل البيبلوغرافية
| العنوان: |
基于改进混合高斯模型的运动物体检测研究. (Chinese) |
| Alternate Title: |
Modified Gaussian mixture background model for moving object detection. (English) |
| المؤلفون: |
黄东军, 杨颖华 |
| المصدر: |
Application Research of Computers / Jisuanji Yingyong Yanjiu; Jun2017, Vol. 34 Issue 6, p1862-1866, 5p |
| Abstract (English): |
For initialization of the traditional Gaussian model and the calculation of the parameters' values depends on all previous frames as well as scattered noise, this paper proposed a modified Gaussian mixture model. The method firstly applied the strategy of combining median filtering with the characteristics of neighborhood pixels so that to get closer to the actual initial background. It also proposed a time reset policy on the basis of the original background of the sort, so that the newly added pixels could be quickly matched. And it modified the learning rate of specific region as well. Through the re-set learning rate and the spatial pixel distribution characteristics, some noise and scattered empty could be eliminated. Compared with the traditional Gaussian mixture model, experimental results show that this algorithm can accurately detect moving objects and eliminate shadows and noise to some extent. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
针对传统高斯建模的初始化问题、参数值的计算依赖于先前所有帧和零散噪点较多等问题，提出了一种改进混合高斯模型的方法，即在初始化每个像素点时采用邻域特性与中值滤波相结合的方法，用来获取更接近实际的初始背景。同时对背景模型的更新提出了改进方法，在原有的背景排序基础上增加定时清零策略，使新加入的像素点能快速匹配。最后对特定区域的学习速率进行重新设定，再结合像素点的空间分布特性，达到消除零散噪点和部分空洞的目的。实验结果表明，与传统的混合高斯模型相比，该算法能准确地检测出运动物体，并对阴影和噪声有一定的抑制作用。 [ABSTRACT FROM AUTHOR] |
|
Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
