DELTA-SoyStage: A Lightweight Detection Architecture for Full-Cycle Soybean Growth Stage Monitoring
Sensors · 2025
DOI: 10.3390/s25237303 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Abdellah Lakhssassi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Southern Illinois University, Carbondale, IL 62901, USA. Hauptthemen laut MEDLINE: Glycine max. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Soybean Center at Southern Illinois University Carbondale, Soybean Center at the Southern Illinois University Carbondale.
Abstract (Originalsprache)
The accurate identification of soybean growth stages is critical for optimizing agricultural interventions, where mistimed treatments can result in yield losses ranging from 2.5% to 40%. Existing deep learning approaches remain limited in scope, targeting isolated developmental phases rather than providing comprehensive phenological coverage. This paper presents a novel object detection architecture DELTA-SoyStage, combining an EfficientNet backbone with a lightweight ChannelMapper neck and a newly proposed DELTA (Denoising Enhanced Lightweight Task Alignment) detection head for soybean growth stage classification. We introduce a dataset of 17,204 labeled RGB images spanning nine growth stages from emergence (VE) through full maturity (R8), collected under controlled greenhouse conditions with diverse imaging angles and lighting variations. DELTA-SoyStage achieves 73.9% average precision with only 24.4 GFLOPs computational cost, demonstrating 4.2× fewer FLOPs than the best-performing baseline (DINO-Swin: 74.7% AP, 102.5 GFLOPs) with only 0.8% accuracy difference. The lightweight DELTA head combined with the efficient ChannelMapper neck requires only 8.3 M parameters—a 43.5% reduction compared to standard architectures—while maintaining competitive accuracy. Extensive ablation studies validate key design choices including task alignment mechanisms, multi-scale feature extraction strategies, and encoder–decoder depth configurations. The proposed model’s computational efficiency makes it suitable for deployment on resource-constrained edge devices in precision agriculture applications, enabling timely decision-making without reliance on cloud infrastructure.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computing, Southern Illinois University, Carbondale, IL 62901, USA.
- Department of Plant, Soil, and Agricultural Systems, Southern Illinois University, Carbondale, IL 62901, USA.
- Department of Biological Sciences, School of Science, Hampton University, Hampton, VA 23668, USA.
ORCID-Profile: Abdellah Lakhssassi, Yasser Salhi, Naoufal Lakhssassi, Khalid Meksem, Khaled Ahmed
Förderung
- Soybean Center at Southern Illinois University Carbondale
- Soybean Center at the Southern Illinois University Carbondale
Zitieren
APA
Lakhssassi, A., Salhi, Y., Lakhssassi, N., Meksem, K., & Ahmed, K. (2025). DELTA-SoyStage: A Lightweight Detection Architecture for Full-Cycle Soybean Growth Stage Monitoring. Sensors. https://doi.org/10.3390/s25237303
Vancouver
Lakhssassi A, Salhi Y, Lakhssassi N, Meksem K, Ahmed K. DELTA-SoyStage: A Lightweight Detection Architecture for Full-Cycle Soybean Growth Stage Monitoring. Sensors. 2025. doi:10.3390/s25237303
BibTeX
@article{Lakhssassi2025,
author = {Lakhssassi, Abdellah and Salhi, Yasser and Lakhssassi, Naoufal and Meksem, Khalid and Ahmed, Khaled},
title = {DELTA-SoyStage: A Lightweight Detection Architecture for Full-Cycle Soybean Growth Stage Monitoring},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25237303}
}
EUVIMED