Real-time segmentation algorithm of unstructured road scenes based on improved BiSeNet

In response to the fuzzy and complex boundaries of unstructured road scenes, as well as the high difficulty of segmentation, this paper uses BiSeNet as the benchmark model to improve the above situation and proposes a real-time segmentation model based on partial convolution. Using FasterNet based o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of real-time image processing Jg. 21; H. 3; S. 91
Hauptverfasser:	Bai, Chunhui, Zhang, Lilian, Gao, Lutao, Peng, Lin, Li, Peishan, Yang, Linnan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2024 Springer Nature B.V
Schlagworte:	Accuracy Algorithms Cameras Computer Graphics Computer Science Context Convolution Deep learning Floating point arithmetic Image Processing and Computer Vision Inference Modules Multimedia Information Systems Pattern Recognition Real time Roads & highways Semantics Sensors Signal,Image and Speech Processing Street signs Task complexity Vehicles More Unstructured roads Semantic segmentation Spatial pyramid pooling MSC code2 Feature fusion MSC code1 Partial convolution
ISSN:	1861-8200, 1861-8219
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!