EVALUATION OF DEPTH MODALITY IN CONVOLUTIONAL NEURAL NETWORK CLASSIFICATION OF RGB-D IMAGES

Acta Electrotechnica et Informatica

Michal VARGA¹  Ján JADLOVSKݹ 

[1] Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Kosice, Letna 9, 042 00 Kosice, Slovak Republic;

关键词: 3D imaging;    computer vision;    convolutional neural network;    deep learning;   

DOI  :  10.15546/aeei-2018-0029

来源: DOAJ

【 摘 要 】

This paper investigates the value of depth modality in object classification in RGB-D images. We use a simple model based on a multi-layered convolutional neural network which we train on a dataset of segmented RGB-D images of household and office objects. We evaluate and quantify the benefit of additional depth modality and its effect on classification accuracy on this dataset. Also, we compare the benefit of depth channel against the addition of color to grayscale image. Our experimental results support a conclusion, that for these categories of objects the depth modality provides a significant benefit to classification, which also outweighs the benefit of color information. Similar supporting evidence found in recent research is shown in comparison along with the resulting quantified benefit of depth modality.

【 授权许可】

Unknown