为提高光照变化和背景混淆下的实时跟踪效果,提出了基于Kalman滤波和边缘直方图特征(edge orientationhistogram,EOH)的实时目标跟踪方法。边缘方向直方 .
基于2个网页-相关网页
...doi: 摘要: 为提高光照变化和背景混淆下的实时跟踪效果,提出了基于Kalman滤波和边缘直方图特征(edge orientation histogram, EOH)的实时目标跟踪方法.
基于2个网页-相关网页
滤波和边缘直方图特征 edge orientation histogram ; EOH
研究了利用颜色直方图、颜色边缘幅值和边缘方向直方图特征,基于支撑向量分类器的检测人脸技术。
This paper studies the human face detection by support vector classifier using histograms of color, color edge and its orientation.
提出了一种自适应图像二值化方法,它基于数学形态学理论,求取彩色图像边缘特征,并将它与灰度直方图二值化方法相结合。
A new method of adaptive threshold selection is proposed which combines the edge feature of the color image based on the theory of mathematical morphology.
首先在具有明显边缘特征的图像序列中,提取图像强边缘块的直方图,然后,利用时域多分辨算法,比较不同帧之间的图像差异。
Firstly, the histogram is computed from the strong edge blocks in the image sequences. Then, different images are compared by algorithm of multi-resolution steps.
应用推荐