基于非负矩阵分解的阴影检测方法

针对以往的矩阵分解方法不能保证分解结果非负的问题, 根据非负矩阵分解（NMF: Non negative Matrix Factorization）结果非负的特点, 提出了基于NMF的阴影检测方法, 并以此为基础将进一步引入的分块非负矩阵分解（BNMF: Block Non negative Matrix Factorization）应用于阴影检测。通过NMF/BNMF提取训练样本中阴影的亮度特征, 再根据特征识别测试样本中的阴影区域。实验结果表明,与基于奇异值分解方法相比, 该算法的阴影检测细节更清晰, 具有更好的效果。

Method of Shadow Detection Based on Non-Negative Matrix Factorization

Previous matrix factorization algorithms can not guarantee the nonnegativity of results. Inspired by the nonnegative character of NMF (Non-negative Matrix Factorization), NMF is utilized to detect shadow areas. The BNMF (Block Non negative Matrix Factorization) is introduced for shadow detection. The brightness features of shadow points of training samples are extracted by NMF or BNMF method. The shadow areas of testing sample are recognized by features. The results demonstrate that the approach preserves edges clearer than the method based on singular value decomposition.