融合深度和颜色信息的图像物体分割算法-模式识别与人工智能.PDFVIP

第26 卷摇 第2 期摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 模式识别与人工智能摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Vol.26摇 No.2 摇 2013年2月摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 PR AI摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Feb摇 摇 2013 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 融融合深度和颜色信息的图像物体分割算法* 皮志明摇 摇 汪增福 (中国科学技术大学 自动化系摇 合肥230027) 摘摇 要摇 讨论立体图对的图像分割问题,提出一种基于深度和颜色信息的图像物体分割算法.该算法首先利用基 于聚类的Mean鄄shift分割算法对目标图像进行适度的过分割,同时借助双目立体视觉算法获取立体图对的稠密深 度图,并依据深度不连续性从过分割结果中选取用于继续进行“精致冶分割的种子点集,接着对未分配种子标签的 区域用图割算法分配标签,并对彼此之间没有深度不连续边界但具有不同标签的相邻区域进行融合.相比于传统 图像分割算法,该算法可有效克服过分割和欠分割问题,获取具有一定语义的图像分割结果.相关的对比实验结果 验证了该算法的有效性. 关键词摇 图像分割,深度不连续,面向物体分割,图割算法 中图法分类号摇 TP391.41 Image Object Segmentation Algorithm by Combining Depth Discontinuities and Color Information PI Zhi鄄Ming,WANGZeng鄄Fu (Department of Automation,University of Science and Technology of China,Hefei230027) ABSTRACT The image segmentation using stereo image pairs is discussed. An image segmentation algorithm combining depth discontinuities and color information is proposed. Mean鄄shift segmentation algorithm is applied totheover鄄segmentationoftheimage,andmeanwhilethedensedepthmapoftheimagepairscan be calculated by using stereo vision algorithm. Then,through combining color image over鄄segmentation and depth discontinuities,multiple seed regions for accurate segmentation are selected along the depth discontinuities. By using graph cut algorithm,unlabeled regions are assigned with seed regions忆labels. Next,the neighbor regionswith different labels but without discontinuous depth boundary between them are merged together as well. Compared with the traditional feature clustering image segmentation algorithms,theproposedalgorithmo