Shadow Detection Using Multi-Features in SVM Classifier
Shadow Detection Using Multi-Features in SVM Classifier
复制标题
DOI：
10.4028/www.scientific.net/amm.602-605.1680
复制
发表时间：
2014-08
期刊：
影响因子：
--
通讯作者：
Z. Wang;Jiandong Tian;Yandong Tang;Yan Zhu Zhang;Yong Xia;Ling Wang
中科院分区：
文献类型：
--
作者：
Z. Wang;Jiandong Tian;Yandong Tang;Yan Zhu Zhang;Yong Xia;Ling Wang
阴影会给计算机视觉带来很多问题，如目标识别、图像分割和视频监控等。本文提出了一种新的方法来检测投阴影在一个单一的室外图像。我们建立了一个光照模型来解释阴影的形成过程，并通过这个模型引入了一些有用的特征。经过一系列的形态学运算后，利用Canny边缘检测器得到待提取特征的区域。然后，我们使用支持向量机分类器与多核模型来训练这些特征的阴影区域分类。实验结果表明，该方法可以有效地检测阴影图像的边缘。
Shadows may cause many problems in computer vision, such as object recognition, image segmentation and video surveillance. In this paper, we present a new method to detect cast shadow in a single outdoor image. We build up an illumination model to explain the process of shadow formed, and through this model we introduce some useful features. The regions for extract features are acquired through canny edge detector, after a series of morphological operations. Then we use SVM classifier with a multi-kernel model to train these features for shadow region classification. Our results show that edges of shadow images can be detected effectively with our methods.