Instituto de Investigación en Informática, University of Alicante, P.O. Box 99, E-03080 Alicante, Spain.
Neural Netw. 2012 Aug;32:138-46. doi: 10.1016/j.neunet.2012.02.014. Epub 2012 Feb 16.
Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.
近年来，已有多项研究致力于解决移动机器人领域中的 3D 数据问题，例如地图绘制或自身运动。数据来源于各种传感器，如立体视觉系统、飞行时间相机或 3D 激光雷达，提供了大量未组织的 3D 数据。在本文中，我们描述了一种从生长神经网络（GNG）构建完整 3D 模型的有效方法。GNG 应用于 3D 原始数据，它可以减少底层误差和点数，同时保持 3D 数据的拓扑结构。然后，GNG 的输出被用于 3D 特征提取方法。我们进行了深入的研究，定量表明 GNG 的使用可以提高 3D 特征提取方法的性能。我们还表明，我们的方法可以应用于任何类型的 3D 数据。所获得的 3D 特征被用作输入，应用于迭代最近点（ICP）类似的方法，以计算移动机器人执行的 6DoF 运动。我们还与标准 ICP 进行了比较，结果表明 GNG 的使用可以提高结果的准确性。最后还展示了从计算得出的自身运动中进行 3D 映射的结果。
