Efficient and robust crosswalk segmentation under adverse weather using convnext-enhanced DeepLabv3

Faqih, Muhammad ORCID: https://orcid.org/0009-0005-1755-2332, Rahman, Ridho Aulia ORCID: https://orcid.org/0009-0006-7656-3477 and Holle, Khadijah Fahmi Hayati ORCID: https://orcid.org/0000-0002-6991-1748 (2026) Efficient and robust crosswalk segmentation under adverse weather using convnext-enhanced DeepLabv3. Jurnal Ilmu Komputer dan Informasi, 19 (2). pp. 179-195. ISSN 2502-9274

Preview

Text 28524.pdf Download (5MB) | Preview

Abstract

Reliable crosswalk perception is crucial for first-person vision (FPV) navigation in assistive guidance and intelligent transportation, but segmentation accuracy often decreases under glare, rain reflections, nighttime illumination, and worn low-contrast markings. This study proposes ConvNeXt-Enhanced DeepLabv3 (CEDL), a pixel-level segmentation architecture that integrates DeepLabv3 atrous multi-scale encoding with the modern convolutional design of ConvNeXt-Tiny. Experiments were conducted on the FPVCrosswalk2025 dataset, containing synthetic and real FPV images captured under sunny, cloudy, rainy, and night conditions. The proposed model was compared with DeepLabv3 using ResNet-50 and MobileNetV3-L backbones under the same training and evaluation protocol. CEDL achieved the best overall performance, with 0.946 mean IoU and 0.972 Dice, while maintaining strong per-condition robustness and improved boundary preservation for thin crosswalk structures. It also achieved practical inference speed at 20.6 ms per frame, nearly five times faster than ResNet-50, despite having more parameters than MobileNetV3-L. Qualitative results show more continuous crosswalk stripes and fewer missed segments under adverse conditions. These findings indicate that CEDL provides a robust and computationally practical solution for FPV crosswalk segmentation on a mixed synthetic-real benchmark.

Item Type:	Journal Article
Keywords:	Crosswalk segmentation; semantic segmentation; adverse weather conditions; ConvNeXt backbone; DeepLabv3
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080104 Computer Vision 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Khadijah Fahmi Hayati Holle
Date Deposited:	27 Jul 2026 13:29

Downloads

Origin of downloads

Actions (login required)

View Item