DeepLabV3+-Based Semantic Annotation Refinement for SLAM in Indoor Environments

Visual SLAM systems frequently encounter challenges in accurately reconstructing three-dimensional scenes from monocular imagery in semantically deficient environments, which significantly compromises robotic operational efficiency. While conventional manual annotation approaches can provide supplem...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel, Switzerland) Jg. 25; H. 11; S. 3344
Hauptverfasser: Wei, Shuangfeng, Tang, Hongrui, Liu, Changchang, Yang, Tong, Zhou, Xiaohang, Zlatanova, Sisi, Fan, Junlin, Tu, Liping, Mao, Yaqin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland MDPI AG 26.05.2025
MDPI
Schlagworte:
Accuracy
Algorithms
Annotations
Clustering
Data processing
Efficiency
image semantic segmentation
Localization
Mapping
Neural networks
Optimization
point cloud semantic annotation
Research methodology
scene understanding
Semantics
Sensors
Telecommunication systems
visual SLAM
China
image semantic segmentation
clustering
scene understanding
visual SLAM
point cloud semantic annotation
ISSN:1424-8220, 1424-8220
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Visual SLAM systems frequently encounter challenges in accurately reconstructing three-dimensional scenes from monocular imagery in semantically deficient environments, which significantly compromises robotic operational efficiency. While conventional manual annotation approaches can provide supplemental semantic information, they are inherently inefficient, procedurally complex, and labor-intensive. This paper presents an optimized DeepLabV3+-based framework for visual SLAM that integrates image semantic segmentation with automated point cloud semantic annotation. The proposed method utilizes MobileNetV3 as the backbone network for DeepLabV3+ to maintain segmentation accuracy while reducing computational demands. In this paper, we introduce a parameter-adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm incorporating K-nearest neighbors and accelerated by KD-tree structures, effectively addressing the limitations of manual parameter tuning and erroneous annotations in conventional methods. Furthermore, a novel point cloud processing strategy featuring dynamic radius thresholding is developed to enhance annotation completeness and boundary precision. Experimental results demonstrate that our approach achieves significant improvements in annotation efficiency while preserving high accuracy, thereby providing reliable technical support for enhanced environmental understanding and navigation capabilities in indoor robotic applications.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s25113344