Pose Estimation of Similar Shape Objects using Convolutional Neural Network trained by Synthetic data
Pose Estimation of Similar Shape Objects using Convolutional Neural Network trained by Synthetic data
复制标题
使用由合成数据训练的卷积神经网络对相似形状物体进行姿势估计
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
F. Seyfert
中科院分区：
文献类型：
--
作者：
S. Bila;R. Cameron;P. Lenoir;V. Lunot;F. Seyfert
本文的目的是准确的6D姿态估计从2.5D点云的对象类具有高的形状变化，如蔬菜和水果。一般的位姿估计方法通常侧重于计算已知模型与目标场景之间的刚性变换，而没有显式地考虑形状变化。我们采用深度卷积神经网络（CNN），它在2D图像域显示出强大的最先进的性能。相比之下，通常从点云进行姿态估计的性能较弱，因为很难准备足够大的带注释的训练数据。为了克服这个问题，我们提出了一个自主生成过程的合成2.5D点云覆盖不同形状的变化的对象。合成数据用于训练深度CNN模型，以估计对象姿态。我们提出了一种新的损失函数，以指导估计有较大的特征距离不同的姿态，并直接估计正确的对象姿态。我们使用真实的对象进行评估，其中使用从公共网络资源下载的人工CAD模型进行训练。结果表明，我们的方法是适合于真实的世界的机器人应用。
The objective of this paper is accurate 6D pose estimation from 2.5D point clouds for object classes with a high shape variation, such as vegetables and fruit. General pose estimation methods usually focus on calculating rigid transformations between known models and the target scene, and do not explicitly consider shape variations. We employ deep convolutional neural networks (CNN), which show robust and state of the art performance for the 2D image domain. In contrast, normally the performance of pose estimation from point clouds is weak, because it is hard to prepare large enough annotated training data. To overcome this issue, we propose an autonomous generation process of synthetic 2.5D point clouds covering different shape variations of the objects. The synthetic data is used to train the deep CNN model in order to estimate the object poses. We propose a novel loss function to guide the estimator to have larger feature distances for different poses, and to directly estimate the correct object pose. We performed an evaluation using real objects, where the training was conducted with artificial CAD models downloaded from a public web resource. The results indicate that our approach is suitable for real world robotic applications.