Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street-Road Scenes
文献类型： 外文期刊
作者： Dai, Yingpeng 1 ; Li, Chenglin 2 ; Su, Xiaohang 3 ; Liu, Hongxian 2 ; Li, Jiehao 2 ;
作者机构： 1.Chinese Acad Agr Sci, Tobacco Res Inst, Qingdao 266101, Peoples R China
2.South China Agr Univ, Coll Engn, Key Lab Key Technol Agr Machine & Equipment, Minist Educ, Guangzhou 510642, Peoples R China
3.South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510641, Peoples R China
关键词： semantic segmentation; Depthwise Separable Convolution; multi-scale feature; fully neural networks
期刊名称：REMOTE SENSING （ 影响因子：5.0； 五年影响因子：5.6 ）
ISSN：
年卷期： 2023 年 15 卷 10 期
页码：
收录情况： SCI
摘要： 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.
- 相关文献
作者其他论文 更多>>
-
A multiple resolution branch attention neural network for scene understanding of intelligent autonomous platform
作者：Dai, Yingpeng;Meng, Lingfeng;Ren, Jie;Wang, Yutan
关键词：Information exchange; Lightweight neural network; Multiple resolution branch attention; Semantic segmentation; Unmanned platform
-
An ensemble multi-dimensional randomization network for intelligent recognition of tobacco baking stage
作者：Zhao, Panzhen;Wang, Songfeng;Ren, Jie;Dai, Yingpeng;Zhao, Panzhen;Hao, Xianwei;Wang, Zhisheng;Zou, Jun
关键词：Image processing; Randomization network; Crop baking; Agricultural intelligent platform; Classification
-
The Bayesian mixture expert recognition model for tobacco leaf curing stages based on feature fusion
作者：Zhao, Panzhen;Wang, Songfeng;Wang, Aihua;Meng, Lingfeng;Wang, Zhicheng;Dai, Yingpeng;Duan, Shijiang;Zhao, Panzhen;Wang, Zhicheng
关键词：Curing stage; Feature fusion; Bayesian optimization; Image classification; Ensemble learning
-
Lightweight multi-scale feature dense cascade neural network for scene understanding of intelligent autonomous platform
作者：Dai, Yingpeng;Meng, Lingfeng;Sun, Fushan;Wang, Songfeng
关键词：Lightweight neural network; Semantic segmentation; Classification; Autonomous platform
-
Maturity discrimination of tobacco leaves for tobacco harvesting robots based on a Multi-Scale branch attention neural network
作者：Dai, Yingpeng;Zhao, Panzhen;Wang, Yutan;Zhao, Panzhen
关键词：Maturity discrimination; Tobacco harvesting robots; Neural network; Branch attention mechanism
-
Lightweight Network Ensemble Architecture for Environmental Perception on the Autonomous System
作者：Dai, Yingpeng;Wang, Junzheng;Li, Jing;Meng, Lingfeng;Wang, Songfeng
关键词：Neural network ensemble; real-time application; classification; semantic segmentation
-
Multiscale Feature Extraction Network for Real-time Semantic Segmentation of Road Scenes On the Autonomous Robot
作者：Xue, Junrui;Wang, Yutan;Qu, Aili;Dai, Yingpeng
关键词：Automation; autonomous robot; deep convolutional neural networks; real-time semantic segmentation
