@article{ART003198684},
author={Kimsay Pov and Tara Kit and TAEKYUNG KIM and Youngsun Han},
title={MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation},
journal={Journal of Internet of Things and Convergence},
issn={2466-0078},
year={2025},
volume={11},
number={2},
pages={63-75}
TY - JOUR
AU - Kimsay Pov
AU - Tara Kit
AU - TAEKYUNG KIM
AU - Youngsun Han
TI - MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation
JO - Journal of Internet of Things and Convergence
PY - 2025
VL - 11
IS - 2
PB - The Korea Internet of Things Society
SP - 63
EP - 75
SN - 2466-0078
AB - Efficient real-time water body segmentation is crucial for applications such as flood detection, but balancing accuracy and inference efficiency remains challenging. In this paper, we propose MoTUNet (MobileNetV2-Transformer U-Net), designed to optimize both accuracy and inference speed for water body segmentation. Its performance is evaluated against several popular segmentation models such as U-Net, DeepLabV3+, PSPNet, PAN, and LinkNet. All models use MobileNetV2 as an encoder to reduce computational complexity while preserving feature extraction, and the Kaggle RIWA dataset is used for training and evaluation. The key metrics include Intersection over Union (IoU), precision, recall, F1-score, frames per second (FPS), and the average inference latency. Our results show that U-Net and DeepLabV3+ achieve the highest accuracy, while PSPNet is the most efficient in terms of FPS. MoTUNet provides an optimal balance by being 97.20% and 64.49% faster than U-Net and DeepLabV3+ at a 512×512 input size, and 81.71% and 58.18% faster at a 256×256 input size, while maintaining competitive segmentation accuracy
KW - Water body segmentation;Flood monitoring;Deep learning;Convolutional neural network;Transformer-based decoder.
DO -
UR -
ER -
Kimsay Pov, Tara Kit, TAEKYUNG KIM and Youngsun Han. (2025). MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation. Journal of Internet of Things and Convergence, 11(2), 63-75.
Kimsay Pov, Tara Kit, TAEKYUNG KIM and Youngsun Han. 2025, "MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation", Journal of Internet of Things and Convergence, vol.11, no.2 pp.63-75.
Kimsay Pov, Tara Kit, TAEKYUNG KIM, Youngsun Han "MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation" Journal of Internet of Things and Convergence 11.2 pp.63-75 (2025) : 63.
Kimsay Pov, Tara Kit, TAEKYUNG KIM, Youngsun Han. MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation. 2025; 11(2), 63-75.
Kimsay Pov, Tara Kit, TAEKYUNG KIM and Youngsun Han. "MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation" Journal of Internet of Things and Convergence 11, no.2 (2025) : 63-75.
Kimsay Pov; Tara Kit; TAEKYUNG KIM; Youngsun Han. MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation. Journal of Internet of Things and Convergence, 11(2), 63-75.
Kimsay Pov; Tara Kit; TAEKYUNG KIM; Youngsun Han. MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation. Journal of Internet of Things and Convergence. 2025; 11(2) 63-75.
Kimsay Pov, Tara Kit, TAEKYUNG KIM, Youngsun Han. MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation. 2025; 11(2), 63-75.
Kimsay Pov, Tara Kit, TAEKYUNG KIM and Youngsun Han. "MoTUNet: A MobileNetV2-Transformer U-Net for Water Body Segmentation" Journal of Internet of Things and Convergence 11, no.2 (2025) : 63-75.
