一种基于改进卷积神经网络的RGB-D室内场景分类方法

An RGB-D Indoor Scene Classification Method Based on Improved Convolutional Neural Network

RGB-D室内场景分类是一项极具挑战性的工作,卷积神经网络在场景分类方面已经取得了非常好的效果,但是由于室内场景存在多种目标且布局复杂,另外不同类别的场景之间存在相似性,因此传统卷积神经网络直接应用于室内场景分类存在着很多问题。针对这些问题,本文提出一种改进的基于卷积神经网络的RGB-D室内场景分类方法,包括2个分支,一个是基于ResNet-18的全局特征提取分支,另一个是深度与语义信息的融合分支。将2个分支得到的特征进行融合,达到室内场景分类的目的。在SUN RGB-D数据集上的实验结果表明,所提出的方法优于现有的对比方法。

RGB-D indoor scene classification is a challenging task.In this field,convolutional neural network has yielded excellent outcomes in terms of scene classification.However,many problems arise in the immediate application of traditional convolutional neural networks to indoor scene classification due to the multiple objectives,complex layout of indoor scenes,and the similarity existed between different categories of scenes.Aiming at these problems,an improved RGB-D indoor scene classification method based on convolutional neural networks is proposed,including two branches,one of which is a global feature extraction branch based on ResNet-18 and the other is a fusion branch of depth and semantic information.The features obtained from the two branches are fused for the purpose of indoor scene classification.Experimental results based on the SUN RGB-D dataset have proven the superiority of the proposed method in contrast to existing comparison methods.