arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.12805cs.CVcs.RO
收藏

基于核方法的机器人快速目标分割学习

Fast Object Segmentation Learning with Kernel-based Methods for Robotics

Istituto Italiano di Tecnologia(意大利技术研究院);University of Genoa(热那亚大学);Massachusetts Institute of Technology(麻省理工学院)

Federico Ceola, Elisa Maiettini, Giulia Pasquale, Lorenzo Rosasco, Lorenzo Natale

摘要:

物体分割是机器人视觉系统中的一个关键组成部分,它执行抓取和物体操作等任务,特别是在存在遮挡的情况下。与许多其他计算机视觉任务一样,深度架构的采用使得执行此任务的算法具有出色的性能。然而,在机器人技术中采用这样的算法受到这样一个事实的阻碍,即训练需要大量的计算时间,并且不能在线执行。在这项工作中,我们提出了一种新的体系结构的对象分割,克服了这个问题,并提供了相当的性能在一小部分的国家的最先进的方法所需的时间。我们的方法基于预训练的Mask R-CNN,其中各个层已被一组分类器和回归器所取代,这些分类器和回归器已针对新任务进行了重新训练。我们采用了一种高效的基于内核的方法,可以在大规模问题上进行快速训练。我们的方法在计算机视觉和机器人社区广泛采用的YCB-Video数据集上进行了验证,证明我们可以实现甚至超越最先进的性能,同时显著减少(${\sim}6\times$)训练时间。重现实验的代码在GitHub上公开。

英文摘要:

Object segmentation is a key component in the visual system of a robot that performs tasks like grasping and object manipulation, especially in presence of occlusions. Like many other computer vision tasks, the adoption of deep architectures has made available algorithms that perform this task with remarkable performance. However, adoption of such algorithms in robotics is hampered by the fact that training requires large amount of computing time and it cannot be performed on-line. In this work, we propose a novel architecture for object segmentation, that overcomes this problem and provides comparable performance in a fraction of the time required by the state-of-the-art methods. Our approach is based on a pre-trained Mask R-CNN, in which various layers have been replaced with a set of classifiers and regressors that are re-trained for a new task. We employ an efficient Kernel-based method that allows for fast training on large scale problems. Our approach is validated on the YCB-Video dataset which is widely adopted in the computer vision and robotics community, demonstrating that we can achieve and even surpass performance of the state-of-the-art, with a significant reduction (${\sim}6\times$) of the training time. The code to reproduce the experiments is publicly available on GitHub.

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。

↑