Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Combining dual attention mechanism and efficient feature aggregation for road and vehicle segmentation from UAV imagery

Bulletin of Electrical Engineering and Informatics · Vol. 13 No. 3 (2024) · pp. 1779–1787

DOI
10.11591/eei.v13i3.6742
ISSN
2089-3191, 2302-9285
Published
2024-04-05
Publisher
Institute of Advanced Engineering and Science (IAES)
Language
en
License
creativecommons.org/licenses/by-sa/4.0/

Abstract

Unmanned aerial vehicles (UAVs) have gained significant popularity in recent years due to their ability to capture high-resolution aerial imagery for various applications, including traffic monitoring, urban planning, and disaster management. Accurate road and vehicle segmentation from UAV imagery plays a crucial role in these applications. In this paper, we propose a novel approach combining dual attention mechanisms and efficient multi-layer feature aggregation to enhance the performance of road and vehicle segmentation from UAV imagery. Our approach integrates a spatial attention mechanism and a channel-wise attention mechanism to enable the model to selectively focus on relevant features for segmentation tasks. In conjunction with these attention mechanisms, we introduce an efficient multi-layer feature aggregation method that synthesizes and integrates multi-scale features at different levels of the network, resulting in a more robust and informative feature representation. Our proposed method is evaluated on the UAVid semantic segmentation dataset, showcasing its exceptional performance in comparison to renowned approaches such as U-Net, DeepLabv3+, and SegNet. The experimental results affirm that our approach surpasses these state-of-the-art methods in terms of segmentation accuracy.

Keywords

Collaboration network of the authors

28 authors · 70 co-authorship links · 3 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Industrial University of Ho Chi Minh City
  • Ton Duc Thang University
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Tuan Anh NguyenAffiliation unknown3
Thuan Thanh NguyenIndustrial University of Ho Chi Minh City3
Minh Binh LamIndustrial University of Ho Chi Minh City2
Tong Tan Hoa LeIndustrial University of Ho Chi Minh City2
Thanh Hai TranIndustrial University of Ho Chi Minh City2
Hoang Thi Tu UyenIndustrial University of Ho Chi Minh City2
Thanh Long DuongIndustrial University of Ho Chi Minh City1
Ngoc Anh NguyenIndustrial University of Ho Chi Minh City1
Thanhquy BachIndustrial University of Ho Chi Minh City1
Trung Kien PhamIndustrial University of Ho Chi Minh City1
Nguyen Duc ToanAffiliation unknown1
Chi Cuong NguyenAffiliation unknown1
Bui Hong PhongAffiliation unknown1
Thanh Quyen NgoAffiliation unknown1
Phan Minh ThanIndustrial University of Ho Chi Minh City1
Van Tho NguyenAffiliation unknown1
Tien Đoan DuongIndustrial University of Ho Chi Minh City1
Van Sy NguyenAffiliation unknown1
Ngoc Hoi LeIndustrial University of Ho Chi Minh City1
Trung Nhan NguyenIndustrial University of Ho Chi Minh City1
Thang Trung NguyenTon Duc Thang University1
Ngoc Thiem NguyenIndustrial University of Ho Chi Minh City1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, first harvested 19 Nov 2026, last seen 19 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Combining dual attention mechanism and efficient feature aggregation for road and vehicle segmentation from UAV imagery</dc:title><dc:creator>Trung Dung Nguyen</dc:creator><dc:creator>Trung Kien Pham</dc:creator><dc:creator>Chi Kien Ha</dc:creator><dc:creator>Long Ho Le</dc:creator><dc:creator>Thanh Quyen Ngo</dc:creator><dc:creator>Hoanh Nguyen</dc:creator><dc:subject>road segmentation</dc:subject><dc:subject>vehicle segmentation</dc:subject><dc:subject>UAV imagery</dc:subject><dc:subject>semantic segmentation</dc:subject><dc:subject>dual attention mechanism</dc:subject><dc:subject>spatial attention</dc:subject><dc:subject>channel attention</dc:subject><dc:subject>multi-scale feature fusion</dc:subject><dc:description xml:lang="en">Unmanned aerial vehicles (UAVs) have gained significant popularity in recent years due to their ability to capture high-resolution aerial imagery for various applications, including traffic monitoring, urban planning, and disaster management. Accurate road and vehicle segmentation from UAV imagery plays a crucial role in these applications. In this paper, we propose a novel approach combining dual attention mechanisms and efficient multi-layer feature aggregation to enhance the performance of road and vehicle segmentation from UAV imagery. Our approach integrates a spatial attention mechanism and a channel-wise attention mechanism to enable the model to selectively focus on relevant features for segmentation tasks. In conjunction with these attention mechanisms, we introduce an efficient multi-layer feature aggregation method that synthesizes and integrates multi-scale features at different levels of the network, resulting in a more robust and informative feature representation. Our proposed method is evaluated on the UAVid semantic segmentation dataset, showcasing its exceptional performance in comparison to renowned approaches such as U-Net, DeepLabv3+, and SegNet. The experimental results affirm that our approach surpasses these state-of-the-art methods in terms of segmentation accuracy.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2024-04-05</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v13i3.6742</dc:identifier><dc:identifier>10.11591/eei.v13i3.6742</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 13 No 3 (2024); 1779-1787</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/6742/3713</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>