arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.08464cs.CVcs.AIcs.HCcs.RO
收藏

使用密度函数的低成本场景建模提高了分割性能

Low-Cost Scene Modeling using a Density Function Improves Segmentation Performance

KU Leuven(鲁汶大学);ETH Zürich(苏黎世联邦理工学院);Norwegian University of Science and Technology(挪威科技大学)

Vivek Sharma, Sule Yildirim-Yayilgan, Luc Van Gool

摘要:

我们提出了一种低成本和有效的方法来结合一个免费的仿真软件和免费的CAD模型来建模人与物体的交互,以提高人与物体分割。它旨在用于工业领域中与安全人机协作(SHRC)和交互(SHRI)相关的研究场景。人类和物体建模的任务已被用于检测活动,并用于推断和预测动作,与这些工作不同,我们进行人类和物体建模,以学习RGB-D数据中的交互,以改善分割。为此,我们定义了一个新的密度函数来模拟三维(3D)场景中的虚拟环境(VREP)。这个密度函数考虑了人与物体和物体与物体之间的关系的各种可能的配置,以及由它们的启示所支配的交互。使用这个函数,我们合成了一个大型的,真实的和高度多样化的合成RGB-D数据集,我们使用它来训练。我们训练一个随机森林分类器,并得到的像素级预测集成为一元项的成对条件随机场(CRF)。我们的评估表明,对这些相互作用进行建模可以将分割性能提高约7%,平均精度和召回率超过忽略现实数据中这些相互作用的最先进方法。我们的方法计算效率高,鲁棒性强,可以在消费者硬件上实时运行。

英文摘要:

We propose a low cost and effective way to combine a free simulation software and free CAD models for modeling human-object interaction in order to improve human & object segmentation. It is intended for research scenarios related to safe human-robot collaboration (SHRC) and interaction (SHRI) in the industrial domain. The task of human and object modeling has been used for detecting activity, and for inferring and predicting actions, different from those works, we do human and object modeling in order to learn interactions in RGB-D data for improving segmentation. For this purpose, we define a novel density function to model a three dimensional (3D) scene in a virtual environment (VREP). This density function takes into account various possible configurations of human-object and object-object relationships and interactions governed by their affordances. Using this function, we synthesize a large, realistic and highly varied synthetic RGB-D dataset that we use for training. We train a random forest classifier, and the pixelwise predictions obtained is integrated as a unary term in a pairwise conditional random fields (CRF). Our evaluation shows that modeling these interactions improves segmentation performance by ~7\% in mean average precision and recall over state-of-the-art methods that ignore these interactions in real-world data. Our approach is computationally efficient, robust and can run real-time on consumer hardware.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑