基于多颜色空间信息融合的运动船舶检测算法  被引量:2

A moving ship detection algorithm based on information fusion of multiple color spaces

在线阅读下载全文

作  者:李晶晶[1] 吴学文[1] 

机构地区:[1]河海大学计算机与信息学院,南京211100

出  处:《信息技术》2013年第4期128-131,共4页Information Technology

摘  要:传统的目标检测方法是将图像灰度化,导致很多重要信息丢失,而帧差法与背景减法相结合的检测方法虽然能很好克服单独使用一种方法所产生的问题,但仍存在目标内部不充实现象。针对以上问题,提出一种基于多颜色空间信息融合的三帧差分法与背景减法相结合的运动船舶检测算法。该算法首先利用帧差法和背景减法原理对选取的最佳颜色分量进行差分处理,然后将两种差分结果的颜色分量对应进行"与"运算,最后采用"或"运算实现颜色分量融合,获取内部充实、轮廓清晰的运动目标。The detection of moving objects is commonly realized by important information will inevitably be missed. The combination of graying the images, where many frame difference and background difference can well overcome the drawbacks of using these two methods separately in objects detection, however, resulting in the problem of holes inside objects. For the above reasons, a moving ship detection algorithm which combines the three frame difference with the background difference on the basis of the information fusion of multiple color spaces is proposed in this paper. The selected optimized color components are firstly differentiated by using both the frame difference and background difference. Then AND operation is applied to the resultant color components from these two methods, respectively. Finally, the components are fused together by applying OR operation on them to gain the moving objects with substantial internals and clear edges.

关 键 词:目标检测 帧差法 背景减法 多颜色空间 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象