摘要
提出一种基于边缘信息及光照方向的阴影检测算法。该算法通过将HSV和RGB彩色空间的阴影特征相结合进行初步检测,从初步检测得到的阴影中估计光照方向,运用基于边缘信息阴影检测算法检测在光照方向角阈值范围内的阴影区域,实现对运动目标阴影的准确检测,为运动目标后续处理排除阴影干扰。实验结果表明,该算法能较好地抑制噪声,阴影检测效果比传统算法好。
This paper proposes a shadow detection algorithm based on edge information and illumination direction.It detects shadow which unifies through the shadow characteristics of HSV and RGB color space,estimates the illumination direction through the shadow which formerly examined,and uses the shadow detection algorithm based on edge information to detect the shadow in the threshold range of illumination direction.It can effectively detect the shadow of a moving object and remove the shadow disturbance for the following processing. Experimental results show that the algorithm is robust to noise and more efficient than traditional algorithms.
出处
《计算机工程》
CAS
CSCD
北大核心
2009年第20期192-193,196,共3页
Computer Engineering
关键词
阴影检测
目标检测
光照方向
shadow detection
object detection
illumination direction
作者简介
林坤杰（1984-），男，硕士研究生，主研方向：计算机自动控制与仿真；E-mail：smallpig_18@163．com
万晓冬，副研究员
