基于多尺度超像素融合的RGB-D单幅图像阴影检测算法

Shadow Detection Algorithm Based on Multi-scaleSuper-pixel Fusion for Single RGB-D Images

针对单幅复杂环境图像阴影检测问题,提出一种基于多尺度超像素融合的自动阴影检测快速算法.首先利用深度图像计算各点的法向量及空间坐标,同时利用简单线性迭代聚类算法对彩色图像进行多个尺度的超像素分割;然后使用阴影置信度算法结合图像的色度、法线和空间位置信息分别估计各尺度下的超像素阴影置信度;最后采用Adaboost训练的分类器对各尺度下的超像素阴影置信度进行融合,得到最终的判决结果.实验结果表明,该算法的准确度明显高于原阴影置信度算法,运行时间约为原阴影置信度算法的10%,对于小块阴影、大面积阴影及边缘不清晰的软阴影检测表现较突出,适合对光线复杂环境下的图像进行前期预处理.

Aiming at the shadow detection problem of single image in complex environment,we proposed a fast automatic shadow detection algorithm based on multi-scale su per-pixel fusion.Firstly,the depth image was used to calculate the normal vector and spatial coordinates of every point,and the simple linear iterative clus tering algorithm was used to complete multi-scale super-pixels segment for the color image.Secondly,the shadow confidence algorithm was used to estimate the shadow confidence of the super-pixels in each scale combined with the chromaticity,the normal and the spatial position information of the image.Finally,the trained Adaboost classifier was used to fuse the super-pixels shadow confidence in each scale,and the final judgment result was obtained.The ex perimental results show that the accuracy of the proposed algorithm is significantly higher than the original shadow confidence algorithm,and the running time is about 10%of th e original shadow confidence algorithm.It performs more prominently in the detection of small shadows,large shadows,a nd soft shadows with unclear edges,which is suitable for pre-processing of the images in complex light environment.