基于正交分解的室外光照阴影检测 | |
段志刚![]() ![]() ![]() ![]() | |
刊名 | 光学学报
![]() |
2016 | |
卷号 | 36期号:8页码:209-217 |
关键词 | 机器视觉 阴影检测 正交分解 期望最大化算法 高斯混合模型 |
ISSN号 | 0253-2239 |
其他题名 | Outdoor Illumination Shadow Detection based on Pixel-wise Orthogonal Decomposition |
通讯作者 | 唐延东 |
产权排序 | 1 |
中文摘要 | 针对室外光照条件下阴影的快速高效检测问题,提出了一种基于正交分解的阴影检测方法。利用室外场景图像中阴影区域内外的线性模型建立线性方程组,对该线性方程组的解空间进行正交分解,得到一幅彩色光照不变图像和一幅光照变化图像。通过K-means算法将彩色光照不变图像分类为几个区域,每个区域具有一致的反照率。根据分类结果,对光照变化图像采用EM算法进行高斯混合建模,提取阴影区域。最后采用形态学算子对提取的阴影区域进行优化。本方法不需要复杂的特征算子学习过程,大大降低了算法的时间复杂度,而且不需要任何先验知识,可以直接应用到实时场景处理中。 |
英文摘要 | For detecting the shadow in outdoor illumination conditions rapidly and efficiently, a shadow detection approach based on pixel-wise orthogonal decomposition is proposed in this paper. Based on linear model in and out of shadows in an outdoor scene image, a linear equation set is built for each pixel value vector and is orthogonally decomposed. By the decomposition of the linear equation solution space, a color illumination invariant image and an illumination variation image are obtained. By K-means algorithm, the color illumination invariant image is classified into some regions, each of which has the same spectral albedo. According to the classification results, a Gaussian mixture model with expectation maximization algorithm is proposed for modeling the illumination variation image, and then the shadow areas are extracted. The extracted shadow areas are optimized with morphological operator. The proposed method does not need complex learning process of feature operators and greatly reduces the time complexity of computation. It also does not require any prior knowledge and can be directly applied to the real-time scene processing. |
收录类别 | EI ; CSCD |
语种 | 中文 |
CSCD记录号 | CSCD:5777812 |
内容类型 | 期刊论文 |
源URL | [http://ir.sia.cn/handle/173321/18810] ![]() |
专题 | 沈阳自动化研究所_机器人学研究室 |
推荐引用方式 GB/T 7714 | 段志刚,屈靓琼,田建东,等. 基于正交分解的室外光照阴影检测[J]. 光学学报,2016,36(8):209-217. |
APA | 段志刚,屈靓琼,田建东,&唐延东.(2016).基于正交分解的室外光照阴影检测.光学学报,36(8),209-217. |
MLA | 段志刚,et al."基于正交分解的室外光照阴影检测".光学学报 36.8(2016):209-217. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论