SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing

Shadows in remote sensing images often introduce challenges in accurate segmentation due to their variability in shape, size, and texture. To address these issues, this study proposes the Supervised Dynamic Kernel U-Net (SDKU-Net), a novel architecture designed to enhance shadow detection in complex...

Full description

Saved in:
Bibliographic Details
Main Authors: Gilberto Alvarado-Robles, Isac Andres Espinosa-Vizcaino, Carlos Gustavo Manriquez-Padilla, Juan Jose Saucedo-Dorantes
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Computers
Subjects:
Online Access:https://www.mdpi.com/2073-431X/14/3/80
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204358263701504
author Gilberto Alvarado-Robles
Isac Andres Espinosa-Vizcaino
Carlos Gustavo Manriquez-Padilla
Juan Jose Saucedo-Dorantes
author_facet Gilberto Alvarado-Robles
Isac Andres Espinosa-Vizcaino
Carlos Gustavo Manriquez-Padilla
Juan Jose Saucedo-Dorantes
author_sort Gilberto Alvarado-Robles
collection DOAJ
description Shadows in remote sensing images often introduce challenges in accurate segmentation due to their variability in shape, size, and texture. To address these issues, this study proposes the Supervised Dynamic Kernel U-Net (SDKU-Net), a novel architecture designed to enhance shadow detection in complex remote sensing scenarios. SDKU-Net integrates dynamic kernel adjustment, a combined loss function incorporating Focal and Tversky Loss, and optimizer switching to effectively tackle class imbalance and improve segmentation quality. Using the AISD dataset, the proposed method achieved state-of-the-art performance with an Intersection over Union (IoU) of 0.8552, an F1-Score of 0.9219, an Overall Accuracy (OA) of 96.50%, and a Balanced Error Rate (BER) of 5.08%. Comparative analyses demonstrate SDKU-Net’s superior performance against established methods such as U-Net, U-Net++, MSASDNet, and CADDN. Additionally, the model’s efficient training process, requiring only 75 epochs, highlights its potential for resource-constrained applications. These results underscore the robustness and adaptability of SDKU-Net, paving the way for advancements in shadow detection and segmentation across diverse fields.
format Article
id doaj-art-6fba2fd8a1724638bb5274c62caa2269
institution OA Journals
issn 2073-431X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Computers
spelling doaj-art-6fba2fd8a1724638bb5274c62caa22692025-08-20T02:11:18ZengMDPI AGComputers2073-431X2025-02-011438010.3390/computers14030080SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote SensingGilberto Alvarado-Robles0Isac Andres Espinosa-Vizcaino1Carlos Gustavo Manriquez-Padilla2Juan Jose Saucedo-Dorantes3Engineering Faculty, San Juan del Rio Campus, Autonomous University of Queretaro, Rio Moctezuma 249, San Juan del Rio 76807, MexicoEngineering Faculty, San Juan del Rio Campus, Autonomous University of Queretaro, Rio Moctezuma 249, San Juan del Rio 76807, MexicoEngineering Faculty, San Juan del Rio Campus, Autonomous University of Queretaro, Rio Moctezuma 249, San Juan del Rio 76807, MexicoEngineering Faculty, San Juan del Rio Campus, Autonomous University of Queretaro, Rio Moctezuma 249, San Juan del Rio 76807, MexicoShadows in remote sensing images often introduce challenges in accurate segmentation due to their variability in shape, size, and texture. To address these issues, this study proposes the Supervised Dynamic Kernel U-Net (SDKU-Net), a novel architecture designed to enhance shadow detection in complex remote sensing scenarios. SDKU-Net integrates dynamic kernel adjustment, a combined loss function incorporating Focal and Tversky Loss, and optimizer switching to effectively tackle class imbalance and improve segmentation quality. Using the AISD dataset, the proposed method achieved state-of-the-art performance with an Intersection over Union (IoU) of 0.8552, an F1-Score of 0.9219, an Overall Accuracy (OA) of 96.50%, and a Balanced Error Rate (BER) of 5.08%. Comparative analyses demonstrate SDKU-Net’s superior performance against established methods such as U-Net, U-Net++, MSASDNet, and CADDN. Additionally, the model’s efficient training process, requiring only 75 epochs, highlights its potential for resource-constrained applications. These results underscore the robustness and adaptability of SDKU-Net, paving the way for advancements in shadow detection and segmentation across diverse fields.https://www.mdpi.com/2073-431X/14/3/80SDKU-Netdynamic kernelsremote sensingshadow detection
spellingShingle Gilberto Alvarado-Robles
Isac Andres Espinosa-Vizcaino
Carlos Gustavo Manriquez-Padilla
Juan Jose Saucedo-Dorantes
SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
Computers
SDKU-Net
dynamic kernels
remote sensing
shadow detection
title SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
title_full SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
title_fullStr SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
title_full_unstemmed SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
title_short SDKU-Net: A Novel Architecture with Dynamic Kernels and Optimizer Switching for Enhanced Shadow Detection in Remote Sensing
title_sort sdku net a novel architecture with dynamic kernels and optimizer switching for enhanced shadow detection in remote sensing
topic SDKU-Net
dynamic kernels
remote sensing
shadow detection
url https://www.mdpi.com/2073-431X/14/3/80
work_keys_str_mv AT gilbertoalvaradorobles sdkunetanovelarchitecturewithdynamickernelsandoptimizerswitchingforenhancedshadowdetectioninremotesensing
AT isacandresespinosavizcaino sdkunetanovelarchitecturewithdynamickernelsandoptimizerswitchingforenhancedshadowdetectioninremotesensing
AT carlosgustavomanriquezpadilla sdkunetanovelarchitecturewithdynamickernelsandoptimizerswitchingforenhancedshadowdetectioninremotesensing
AT juanjosesaucedodorantes sdkunetanovelarchitecturewithdynamickernelsandoptimizerswitchingforenhancedshadowdetectioninremotesensing