Towards Robotic Semantic Segmentation of Supporting Surfaces
Towards Robotic Semantic Segmentation of Supporting Surfaces
复制标题
DOI：
10.1109/cict.2015.89
复制
发表时间：
2015-02
期刊：
影响因子：
--
通讯作者：
Sen Wang;X. Zuo;Weiwei Yu;Runxiao Wang;K. Madani
中科院分区：
文献类型：
--
作者：
Sen Wang;X. Zuo;Weiwei Yu;Runxiao Wang;K. Madani
感知周围环境结构的几何形状是机器人自主理解室内环境的重要前提。提出了一种新的支持曲面分割的RGB-D图像解析框架。首先，利用主成分分析和基于3D均值漂移聚类的法线簇从深度信息中提取表面法线。然后利用重力向量估计对地板、墙体等主要平面进行检测。最后利用能量函数图优化方法对支撑面及其对应的对象进行分割。该方法可以为更好地理解室内环境提供机器人语义分割。基于Berkeley 3D对象数据集的实验结果表明，该框架能够很好地处理室内RGB-D杂波场景。
Perceiving the geometry of environmental structures surrounding is a crucial prerequisite for robotic understand the indoor environments autonomously. A new framework for parsing RGB-D images aimed at supporting surfaces segmentation is proposed. First, the surface normal is extracted from depth information using PCA and normal clusters with 3D mean shift clustering. Then the main planes such as floor, wall will be detected with gravity vector estimation. Finally supporting surface and its corresponding objects are segmented using graph optimization with energy functions. The approach can offer a robotic semantic segmentation for better understanding the indoor environment. The experiment results based on Berkeley 3D Object Dataset demonstrate that our framework works well on indoor RGB-D cluttered scenes.