A method for detecting artificial objects in natural environments
A method for detecting artificial objects in natural environments
复制标题
一种检测自然环境中人造物体的方法
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
N. Vincent
中科院分区：
文献类型：
--
作者：
Yves Caron;P. Makris;N. Vincent
本文提出了一种自动检测自然环境数字图像中人造物体的方法。该方法是基于纹理模式在图像中的统计分布。这个分布是用齐夫定律计算的。将图像划分为子帧，计算每个子帧的Zipf分布。然后比较不同子帧的Zipf图下的曲面，以确定哪个子帧包含对象。研究了该检测方法对图像分辨率的灵敏度。
In this paper we present a method for automatic detection of man-made objects in digital images representing natural environments. This method is based on statistical distribution of texture patterns in the image. This distribution is computed using Zipf's law. The image is divided into sub-frames and Zipf's distribution is computed for each sub-frame. Then the surfaces under Zipf's plots of the different sub-frames are compared in order to determine which sub-frame contains an object. The sensitivity of this detection method to image resolution is also examined.