A dual attention mechanism semantic segmentation method for autonomous driving

The paper introduces a refined dual attention mechanism designed to mitigate attention deficiency challenges encountered during the segmentation of diminutive objects within the domain of autonomous driving. In this context, multifaceted factors such as lighting, weather, and road conditions create...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Yannian, RUAN Pei, LIAN Jihong, ZHENG Fangliang
Format: Article
Language:zho
Published: Editorial Office of Journal of XPU 2023-12-01
Series:Xi'an Gongcheng Daxue xuebao
Subjects:
Online Access:http://journal.xpu.edu.cn/en/#/digest?ArticleID=1414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850275247021883392
author WANG Yannian
RUAN Pei
LIAN Jihong
ZHENG Fangliang
author_facet WANG Yannian
RUAN Pei
LIAN Jihong
ZHENG Fangliang
author_sort WANG Yannian
collection DOAJ
description The paper introduces a refined dual attention mechanism designed to mitigate attention deficiency challenges encountered during the segmentation of diminutive objects within the domain of autonomous driving. In this context, multifaceted factors such as lighting, weather, and road conditions create intricate challenges. The primary objective of this approach is to augment the capacity for feature representation by incorporating position and channel attention mechanisms to derive weights. Initially, the position attention mechanism discerns the significance of each pixel within the spatial domain, generating position-related weights. Subsequently, the channel attention mechanism assesses the importance of each channel in feature representation, resulting in channel-related weights. These derived position and channel attention weights are multiplicatively applied to the input features on an element-wise basis, thereby enhancing their representation capabilities. The resultant features from the two attention modules are amalgamated. Experimental findings substantiate that this enhanced network model significantly elevates the accuracy of semantic segmentation. It achieves an average intersection over union (mIoU) of 80.4% on the Cityscapes dataset, marking a substantial improvement of 10.4% in comparison to the baseline fully convolutional network (FCN) method.
format Article
id doaj-art-cdc3ee433e844ab9a54e333d29ac226a
institution OA Journals
issn 1674-649X
language zho
publishDate 2023-12-01
publisher Editorial Office of Journal of XPU
record_format Article
series Xi'an Gongcheng Daxue xuebao
spelling doaj-art-cdc3ee433e844ab9a54e333d29ac226a2025-08-20T01:50:49ZzhoEditorial Office of Journal of XPUXi'an Gongcheng Daxue xuebao1674-649X2023-12-0137611412010.13338/j.issn.1674-649x.2023.06.014A dual attention mechanism semantic segmentation method for autonomous drivingWANG Yannian0RUAN Pei1LIAN Jihong2ZHENG Fangliang3School of Electronics and Information, Xi'an Polytechnic University, Xi'an 710048, ChinaSchool of Electronics and Information, Xi'an Polytechnic University, Xi'an 710048, ChinaSchool of Electronics and Information, Xi'an Polytechnic University, Xi'an 710048, ChinaSchool of Electronics and Information, Xi'an Polytechnic University, Xi'an 710048, ChinaThe paper introduces a refined dual attention mechanism designed to mitigate attention deficiency challenges encountered during the segmentation of diminutive objects within the domain of autonomous driving. In this context, multifaceted factors such as lighting, weather, and road conditions create intricate challenges. The primary objective of this approach is to augment the capacity for feature representation by incorporating position and channel attention mechanisms to derive weights. Initially, the position attention mechanism discerns the significance of each pixel within the spatial domain, generating position-related weights. Subsequently, the channel attention mechanism assesses the importance of each channel in feature representation, resulting in channel-related weights. These derived position and channel attention weights are multiplicatively applied to the input features on an element-wise basis, thereby enhancing their representation capabilities. The resultant features from the two attention modules are amalgamated. Experimental findings substantiate that this enhanced network model significantly elevates the accuracy of semantic segmentation. It achieves an average intersection over union (mIoU) of 80.4% on the Cityscapes dataset, marking a substantial improvement of 10.4% in comparison to the baseline fully convolutional network (FCN) method.http://journal.xpu.edu.cn/en/#/digest?ArticleID=1414autonomous drivingsemantic segmentationattention mechanismchannel attentionposition attention
spellingShingle WANG Yannian
RUAN Pei
LIAN Jihong
ZHENG Fangliang
A dual attention mechanism semantic segmentation method for autonomous driving
Xi'an Gongcheng Daxue xuebao
autonomous driving
semantic segmentation
attention mechanism
channel attention
position attention
title A dual attention mechanism semantic segmentation method for autonomous driving
title_full A dual attention mechanism semantic segmentation method for autonomous driving
title_fullStr A dual attention mechanism semantic segmentation method for autonomous driving
title_full_unstemmed A dual attention mechanism semantic segmentation method for autonomous driving
title_short A dual attention mechanism semantic segmentation method for autonomous driving
title_sort dual attention mechanism semantic segmentation method for autonomous driving
topic autonomous driving
semantic segmentation
attention mechanism
channel attention
position attention
url http://journal.xpu.edu.cn/en/#/digest?ArticleID=1414
work_keys_str_mv AT wangyannian adualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT ruanpei adualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT lianjihong adualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT zhengfangliang adualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT wangyannian dualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT ruanpei dualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT lianjihong dualattentionmechanismsemanticsegmentationmethodforautonomousdriving
AT zhengfangliang dualattentionmechanismsemanticsegmentationmethodforautonomousdriving