Large-Scale Semantic Scene Understanding with Cross-Correction Representation

Real-time large-scale point cloud segmentation is an important but challenging task for practical applications such as remote sensing and robotics. Existing real-time methods have achieved acceptable performance by aggregating local information. However, most of them only exploit local spatial geome...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Remote sensing (Basel, Switzerland) Jg. 14; H. 23; S. 6022
Hauptverfasser: Zhao, Yuehua, Zhang, Jiguang, Ma, Jie, Xu, Shibiao
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.12.2022
Schlagworte:
Accuracy
Alliances
Autonomous vehicles
Coders
Complementarity
cross-correction
Deep learning
Efficiency
Image segmentation
large-scale semantic segmentation
Modules
Neighborhoods
Neural networks
point cloud
Real time
Remote sensing
Robotics
Scene analysis
semantic context
Semantic segmentation
Semantics
Sensors
spatial geometric
Teaching methods
ISSN:2072-4292, 2072-4292
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Real-time large-scale point cloud segmentation is an important but challenging task for practical applications such as remote sensing and robotics. Existing real-time methods have achieved acceptable performance by aggregating local information. However, most of them only exploit local spatial geometric or semantic information dependently, few considering the complementarity of both. In this paper, we propose a model named Spatial–Semantic Incorporation Network (SSI-Net) for real-time large-scale point cloud segmentation. A Spatial-Semantic Cross-correction (SSC) module is introduced in SSI-Net as a basic unit. High-quality contextual features can be learned through SSC by correcting and updating high-level semantic information using spatial geometric cues and vice versa. Adopting the plug-and-play SSC module, we design SSI-Net as an encoder–decoder architecture. To ensure efficiency, it also adopts a random sample-based hierarchical network structure. Extensive experiments on several prevalent indoor and outdoor datasets for point cloud semantic segmentation demonstrate that the proposed approach can achieve state-of-the-art performance.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14236022