arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.01357cs.CVcs.LGstat.ML
收藏

一种递归多尺度RBG-D目标识别方法

A recurrent multi-scale approach to RBG-D Object Recognition

Department of Computer, Control, and Management Engineering(计算机、控制与管理工程系);Sapienza University of Rome(罗马第一大学)

Mirco Planamente, Mohammad Reza Loghmani, Barbara Caputo

摘要:

技术发展的目标是生产出能够执行复杂任务的效率越来越高的机器人。这需要科学界付出相当大的努力来找到解决计算机视觉问题的新算法,例如对象识别。RGB-D相机的扩散将研究引向能够利用RGB和深度信息的新架构的研究。在本论文中开发的项目涉及到一个新的端到端的架构的RGB-D对象识别RCFusion的实现。我们的方法通过结合互补RGB和代表不同抽象级别的深度信息来生成紧凑且具有高度区分力的多模态特征。我们在标准对象识别数据集、RGB-D对象数据集和JHUIT-50上评估了我们的方法。实验表明,我们的方法优于现有的方法,并建立了新的国家的最先进的结果,这两个数据集。

英文摘要:

Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks. This requires considerable efforts, from the scientific community, to find new algorithms that solve computer vision problems, such as object recognition. The diffusion of RGB-D cameras directed the study towards the research of new architectures able to exploit the RGB and Depth information. The project that is developed in this thesis concerns the realization of a new end-to-end architecture for the recognition of RGB-D objects called RCFusion. Our method generates compact and highly discriminative multi-modal features by combining complementary RGB and depth information representing different levels of abstraction. We evaluate our method on standard object recognition datasets, RGB-D Object Dataset and JHUIT-50. The experiments performed show that our method outperforms the existing approaches and establishes new state-of-the-art results for both datasets.

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。

↑