Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes
Remote Sensing · 19.05.2023 · 15 (10) · 2649
DOI: 10.3390/rs15102649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.05.2023. Verfasst von Yingpeng Dai und 4 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese Academy of Agricultural Sciences Science and Technology Innovation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Vision is an important way for unmanned mobile platforms to understand surrounding environmental information. For an unmanned mobile platform, quickly and accurately obtaining environmental information is a basic requirement for its subsequent visual tasks. Based on this, a unique convolution module called Multi-Scale Depthwise Separable Convolution module is proposed for real-time semantic segmentation. This module mainly consists of concatenation pointwise convolution and multi-scale depthwise convolution. Not only does the concatenation pointwise convolution change the number of channels, but it also combines the spatial features from the multi-scale depthwise convolution operations to produce additional features. The Multi-Scale Depthwise Separable Convolution module can strengthen the non-linear relationship between input and output. Specifically, the multi-scale depthwise convolution module extracts multi-scale spatial features while remaining lightweight. This fully uses multi-scale information to describe objects despite their different sizes. Here, Mean Intersection over Union (MIoU), parameters, and inference speed were used to describe the performance of the proposed network. On the Camvid, KITTI, and Cityscapes datasets, the proposed algorithm compromised between accuracy and memory in comparison to widely used and cutting-edge algorithms. In particular, the proposed algorithm acquired 61.02 MIoU with 2.68 M parameters on the Camvid test dataset.
Förderung
- Chinese Academy of Agricultural Sciences Science and Technology Innovation
- National Natural Science Foundation of China
Zitieren
APA
Dai, Y., Li, C., Su, X., Liu, H., & Li, J. (2023). Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes. Remote Sensing, 15(10), 2649. https://doi.org/10.3390/rs15102649
Vancouver
Dai Y, Li C, Su X, Liu H, Li J. Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes. Remote Sensing. 2023;15(10):2649. doi:10.3390/rs15102649
BibTeX
@article{Dai2023,
author = {Dai, Yingpeng and Li, Chenglin and Su, Xiaohang and Liu, Hongxian and Li, Jiehao},
title = {Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {10},
pages = {2649},
doi = {10.3390/rs15102649}
}
EUVIMED