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

TL;DR

This paper introduces RCFusion, a new end-to-end architecture that effectively combines RGB and depth data to improve object recognition accuracy, achieving state-of-the-art results on standard datasets.

Contribution

The paper presents a novel multi-scale fusion architecture for RGB-D object recognition that outperforms existing methods and sets new benchmarks.

Findings

Outperforms existing approaches on RGB-D datasets

Achieves state-of-the-art results on RGB-D Object Dataset and JHUIT-50

Demonstrates the effectiveness of multi-scale feature fusion

Abstract

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.