A Lightweight CNN-Transformer Network with Laplacian Loss for Low-Altitude UAV Imagery Semantic Segmentation

Simple item page
aut.relation.endpage1
aut.relation.issue99
aut.relation.journalIEEE Transactions on Geoscience and Remote Sensing
aut.relation.startpage1
aut.relation.volumePP
dc.contributor.authorLu, Wen
dc.contributor.authorZhang, Zhiqi
dc.contributor.authorNguyen, Minh
dc.date.accessioned2024-05-21T03:52:10Z
dc.date.available2024-05-21T03:52:10Z
dc.date.issued2024-04-04
dc.description.abstractSemantic segmentation is crucial for enabling autonomous flight and landing of low-altitude unmanned aerial vehicles (UAVs) and is indispensable for various intelligent applications. However, real-time semantic segmentation is a computationally intensive task because it involves pixel-wise classification, which renders conventional semantic segmentation networks impractical for deployment on embedded systems of limited hardware resources. Moreover, variations in flight height and object appearance increase the likelihood of misjudgment in segmentation results. To address these challenges, we propose an efficient approach consisting of a convolutional neural network (CNN)–Transformer network and an auxiliary loss. The encoder of the network integrates a newly designed module, which equally handles objects with varying scales. The decoder is composed of the innovative query–value squeeze axial transformer attention (QVSATA), which reduces computational complexity from quadratic in terms of image size to O(2C(H2+W2)) , linear in terms of image size. By incorporating Laplacian operator convolution, the novel network-agnostic loss effectively captures intricate patterns, boundaries, and small objects. This enables extra penalization of misjudgments in these areas and compels the network to focus on objects that are challenging to distinguish. Our approach attains impressive accuracy when processing 4K resolution images in real time (15 FPS) on a mobile GPU. It demonstrates over 2× faster speed compared to representative lightweight networks, underscoring its suitability for onboard deployment.
dc.identifier.citationIEEE Transactions on Geoscience and Remote Sensing, ISSN: 0196-2892 (Print); 1558-0644 (Online), Institute of Electrical and Electronics Engineers (IEEE), PP(99), 1-1. doi: 10.1109/tgrs.2024.3385318
dc.identifier.doi10.1109/tgrs.2024.3385318
dc.identifier.issn0196-2892
dc.identifier.issn1558-0644
dc.identifier.urihttp://hdl.handle.net/10292/17573
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urihttps://ieeexplore.ieee.org/document/10491345
dc.rights© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.rights.accessrightsOpenAccess
dc.subject40 Engineering
dc.subject0404 Geophysics
dc.subject0906 Electrical and Electronic Engineering
dc.subject0909 Geomatic Engineering
dc.subjectGeological & Geomatics Engineering
dc.subject37 Earth sciences
dc.subject40 Engineering
dc.titleA Lightweight CNN-Transformer Network with Laplacian Loss for Low-Altitude UAV Imagery Semantic Segmentation
dc.typeJournal Article
pubs.elements-id544428
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A_Lightweight_CNN-Transformer_Network_with_Laplacian_Loss_for_Low-altitude_UAV_Imagery_Semantic_Segmentation.pdf
Size:
24.52 MB
Format:
Adobe Portable Document Format
Description:
Journal article
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau