3D Selective Search for obtaining object candidates
3D Selective Search for obtaining object candidates
复制标题
DOI：
10.1109/iros.2015.7353358
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Asako Kanezaki;T. Harada
中科院分区：
文献类型：
--
作者：
Asako Kanezaki;T. Harada
我们提出了一种在 3D 空间中获取候选对象的新方法。我们的方法不需要学习，对对象属性（例如紧凑性或对称性）没有限制，因此使用完全通用的方法生成对象候选。该方法是选择性搜索（一种适用于 2D 图像的非学习型物体检测器）和超体素分割方法（适用于 3D 点云）的简单组合。我们对超体素分割做了一个小但重要的修改；它为超体素带来了更好的“播种”，从而产生了更合适的候选对象。我们使用几个公开可用的 RGB-D 数据集进行的实验表明，我们的方法优于在 2D 图像中生成对象建议的最先进方法。
We propose a new method for obtaining object candidates in 3D space. Our method requires no learning, has no limitation of object properties such as compactness or symmetry, and therefore produces object candidates using a completely general approach. This method is a simple combination of Selective Search, which is a non-learning-based objectness detector working in 2D images, and a supervoxel segmentation method, which works with 3D point clouds. We made a small but non-trivial modification to supervoxel segmentation; it brings better “seeding” for supervoxels, which produces more proper object candidates as a result. Our experiments using a couple of publicly available RGB-D datasets demonstrated that our method outperformed state-of-the-art methods of generating object proposals in 2D images.