摘要
针对静态水面的特性,提出了一种水上物体检测分割算法。该算法主要包括3个环节:饱和度检测水面区域、区域一致性的GOA检测边缘和目标物体标记定位。以水面具有较低饱和度的特征对水面区域进行提取,在此基础上运用浮雕处理凸显水面区域的边缘灰度,利用区域一致性进行边缘检测分割出水面和水上物体,最后提取出目标物体的中心位置。仿真结果证明了该图像分割算法的有效性。
According to the characteristics of the static water object, this article introduced a detection segmentation algorithm which includes three steps： the surface region extraction with saturation, GOA edge detection with regional coherence, marking and fixing position of the object. Firstly, extracting the surface with a lower degree of saturation of the characteristics of the surface region extraction, dealing with the edge of gray area highlights the surface of the water, then using regional coherence edge detection to segment the water and the water objects, finally extracting the center of the object. The simulation results show the effectivity of the segmentation algorithm for image.
出处
《实验室研究与探索》
CAS
北大核心
2010年第6期30-32,共3页
Research and Exploration In Laboratory
关键词
图像分割
饱和度
浮雕
区域一致性
image segmentation
saturation
relief
region homogeneity
