Fast Object Segmentation Learning with Kernel-based Methods for Robotics
Fast Object Segmentation Learning with Kernel-based Methods for Robotics
复制标题
DOI：
10.1109/icra48506.2021.9561758
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Federico Ceola;Elisa Maiettini;Giulia Pasquale;L. Rosasco;L. Natale
中科院分区：
文献类型：
--
作者：
Federico Ceola;Elisa Maiettini;Giulia Pasquale;L. Rosasco;L. Natale
物体分割是机器人视觉系统的关键组成部分，用于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该任务的算法具有出色的性能。然而，由于训练需要大量的计算时间，并且不能在线进行，因此在机器人技术中采用这种算法受到了阻碍。在这项工作中，我们提出了一种新的对象分割架构，克服了这个问题，并在最先进的方法所需的一小部分时间内提供了相当的性能。我们的方法是基于预训练的掩码R-CNN，其中各种层已经被一组分类器和回归器所取代，这些分类器和回归器是为新任务重新训练的。我们采用了一种高效的基于核的方法，允许在大规模问题上快速训练。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，表明我们可以实现甚至超越最先进的性能，显著减少（~6倍）的训练时间。重现实验的代码可以在GitHub1上公开获得。
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 retrained 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 (~6×) of the training time.The code to reproduce the experiments is publicly available on GitHub1.