摘要
针对图像边坡表面状态发生的变化检测,提出了一种新的智能检测方法。人工设置两个目标体,一个作为参考标识点,一个作为监测点,标识点具有特殊的颜色(红色)与形状(圆形),以两者之间的相对位移来表征边坡的状态变化。该方法由以下4个环节构成:选取特定目标体,设置目标体;将图像转换到HIS空间,提取特定的颜色---红色,确定感兴趣区域(ROI);进行图像二值化,确定感兴趣区域的中心坐标;通过位移判定准则判定边坡表面状态是否发生变化。实验证明,该方法具有鲁棒性好、检测准确率高等特点。
This paper presents an intelligent method based on image processing for the detection of slope surface state.Two objects were set by artificial body,one is a reference point,another is a monitoring point.The relative displacement between the two points was used to characterize the change of the state of the slope surface.The signature points have special color（red） and shape（round）.This method is mainly carried out in four steps.Firstly,select a specific target body and set the target body.Secondly,convert RGB color space to HIS color space,and extract pixels with red color,and determine the region of interest.Then,convert the image to binary image and measure center coordinates of the ROI.And finally we detect the state of the slope surface by using the some Criteria.The experimental result reveals the good robustness,accurate detection rate of the presented method.
出处
《农业网络信息》
2011年第8期8-10,共3页
Agriculture Network Information
关键词
图像处理
目标体特征
感兴趣区域
相对位移
image processing
characteristics of target
regions of interest（ROI）
relative displacement
