RGB-D Indoor Object Recognition Algorithm Based on Fusion Convolutional Neural Network

Aiming at the problems of insufficient network fusion and low detection efficiency in current object recognition using RGB-D images, a recognition algorithm based on the medium-level layer-by-layer fusion of dual-channel networks is proposed. First of all, the RGB and Depth networks are trained with...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series Jg. 1267; H. 1; S. 12022 - 12028
Hauptverfasser: Wang, Decheng, Yi, Hui, Zhao, Feng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bristol IOP Publishing 01.07.2019
Schlagworte:
Accuracy
Algorithms
Artificial neural networks
Object recognition
Physics
ISSN:1742-6588, 1742-6596
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Aiming at the problems of insufficient network fusion and low detection efficiency in current object recognition using RGB-D images, a recognition algorithm based on the medium-level layer-by-layer fusion of dual-channel networks is proposed. First of all, the RGB and Depth networks are trained with ten labelled RGB-D indoor objects respectively, and then determine the fusion coefficients according to the identify accuracy of two types networks. Finally, two kinds of features are merged in convolutional layers step by step to obtain the final weights. By testing on the challenging NYU Depth v2 dataset, we found that the recognition accuracy of our method is 92.85%, and average detection time is 61.03ms per image. Through comparison experiments, we got the conclusion that average accuracy of the RGB-D layer-by-layer fusion network is 5.22% higher than that of the RGB network.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1267/1/012022