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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of real-time image processing Ročník 21; číslo 3; s. 91
Hlavní autoři:	Bai, Chunhui, Zhang, Lilian, Gao, Lutao, Peng, Lin, Li, Peishan, Yang, Linnan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2024 Springer Nature B.V
Témata:	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
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!