摘要
将对图像处理有效的e指数定义的信息熵用于目标检测问题中,该信息熵克服了log对数信息熵的不足.仿真结果表明,两种不同信息熵的定义对目标的不确定性描述具有近乎相同的效果,但是指数定义与对数定义下的信息增量相比,避免了信息中无定义值和零值的产生.*
The exponential behavior is very efficient in image processing, when used in target detection in this paper, it is efficient too, and it also overcomes the shortage of logarithmic behavior. Simulation results show that the two different definitions of entropy have approximately the same effect on the uncertainty of targets, but compared with the logarithmic behavior of Shannons entropy, this new definition of entropy avoids the undefined and zero values of information.
出处
《信息与控制》
CSCD
北大核心
2005年第1期119-122,共4页
Information and Control
基金
国家自然科学基金资助项目(60272024)
河南省高校杰出科研人才创新工程资助项目(2003KYCX003)
关键词
目标检测
信息熵
信息增量
传感器管理
target detection
information entropy
information gain
sensor management
