Pruning-Friendly RGB-T Semantic Segmentation for Real-Time Processing on Edge Devices
Electronics · 27.08.2025 · 14 (17) · 3408
DOI: 10.3390/electronics14173408 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 27.08.2025. Verfasst von Jun Young Hwang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education, Defense Acquisition Program Administration and Ministry of Trade, Industry and Energy of Korean government.
Abstract (Originalsprache)
RGB-T semantic segmentation using thermal and RGB images simultaneously is actively being researched to robustly recognize the surrounding environment of vehicles regardless of challenging lighting and weather conditions. It is important for them to operate in real time on edge devices. As transformer-based approaches, which most recent RGB-T semantic segmentation studies belong to, are very difficult to perform on edge devices, this paper considers only CNN-based RGB-T semantic segmentation networks that can be performed on edge devices and operated in real time. Although EAEFNet shows the best performance among CNN-based networks on edge devices, its inference speed is too slow for real-time operation. Furthermore, even when channel pruning is applied, the speed improvement is minimal. The analysis of EAEFNet identifies the intermediate fusion of RGB and thermal features and the high complexity of the decoder as the main causes. To address these issues, this paper proposes a network using a ResNet encoder with an early-fused four-channel input and the U-Net decoder structure. To improve the decoder performance, bilinear upsampling is replaced with PixelShuffle. Additionally, mini Atrous Spatial Pyramid Pooling (ASPP) and Progressive Transposed Module (PTM) modules are applied. Since the Proposed Network is primarily composed of convolutional layers, channel pruning is confirmed to be effectively applicable. Consequently, channel pruning significantly improves inference speed, and enables real-time operation on the neural processing unit (NPU) of edge devices. The Proposed Network is evaluated using the MFNet dataset, one of the most widely used public datasets for RGB-T semantic segmentation. It is shown that the proposed method achieves a performance comparable to EAEFNet while operating at over 30 FPS on an embedded board equipped with the Qualcomm QCS6490 SoC.
Förderung
- Ministry of Education
- Defense Acquisition Program Administration and Ministry of Trade, Industry and Energy of Korean government
Zitieren
APA
Hwang, J. Y., Lee, Y. J., Jung, H. G., & Suhr, J. K. (2025). Pruning-Friendly RGB-T Semantic Segmentation for Real-Time Processing on Edge Devices. Electronics, 14(17), 3408. https://doi.org/10.3390/electronics14173408
Vancouver
Hwang JY, Lee YJ, Jung HG, Suhr JK. Pruning-Friendly RGB-T Semantic Segmentation for Real-Time Processing on Edge Devices. Electronics. 2025;14(17):3408. doi:10.3390/electronics14173408
BibTeX
@article{Hwang2025,
author = {Hwang, Jun Young and Lee, Youn Joo and Jung, Ho Gi and Suhr, Jae Kyu},
title = {Pruning-Friendly RGB-T Semantic Segmentation for Real-Time Processing on Edge Devices},
journal = {Electronics},
year = {2025},
volume = {14},
number = {17},
pages = {3408},
doi = {10.3390/electronics14173408}
}
EUVIMED