SemOD: Semantic-Enabled Object Detection Network Under Various Weather Conditions
Sensors · 13.03.2026 · 26 (6) · 1820
DOI: 10.3390/s26061820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.03.2026. Verfasst von Aiyinsi Zuo und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In the field of autonomous driving, camera-based perception models are mostly trained on clear weather data. Models designed to handle specific weather conditions often lack generalization to dynamically changing environments and primarily focus on weather removal rather than robust perception. This paper proposes a semantic-enabled network for object detection under diverse weather conditions. Semantic information enables the model to generate plausible content in missing regions and accurately delineate object boundaries. It also preserves visual coherence and realism across both restored and original image areas, thereby facilitating image transformation and object recognition. Specifically, our architecture consists of a Preprocessing Unit (PPU) and a Detection Unit (DTU), where the PPU utilizes a U-shaped network enriched with semantics to refine degraded images, and the DTU integrates this semantic information for object detection using a modified YOLO network. Extensive experiments demonstrate that the proposed method achieves mAP improvements ranging from 1.49% to 8.78% compared with existing approaches across multiple benchmark datasets under various weather conditions. These results demonstrate the effectiveness of semantic guidance in image enhancement and object detection, providing a comprehensive framework for improving detection performance. The source code will be made publicly available.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627, USA.
- Department of Electrical and Computer Engineering, University of California, Los Angeles, CA 90024, USA.
ORCID-Profile: Aiyinsi Zuo, Zhaoliang Zheng
Zitieren
APA
Zuo, A., & Zheng, Z. (2026). SemOD: Semantic-Enabled Object Detection Network Under Various Weather Conditions. Sensors, 26(6), 1820. https://doi.org/10.3390/s26061820
Vancouver
Zuo A, Zheng Z. SemOD: Semantic-Enabled Object Detection Network Under Various Weather Conditions. Sensors. 2026;26(6):1820. doi:10.3390/s26061820
BibTeX
@article{Zuo2026,
author = {Zuo, Aiyinsi and Zheng, Zhaoliang},
title = {SemOD: Semantic-Enabled Object Detection Network Under Various Weather Conditions},
journal = {Sensors},
year = {2026},
volume = {26},
number = {6},
pages = {1820},
doi = {10.3390/s26061820}
}
EUVIMED