EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FPGA-Based Low-Power High-Performance CNN Accelerator Integrating DIST for Rice Leaf Disease Classification

Jingwen Zheng, Zefei Lv, Dayang Li, Chengbo Lu, Yang Zhang, Liangzun Fu, Xiwei Huang, Jiye Huang, Dongmei Chen, Jingcheng Zhang

Electronics · 22.04.2025 · 14 (9) · 1704

DOI: 10.3390/electronics14091704 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 22.04.2025. Verfasst von Jingwen Zheng und 9 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Fundamental Research Funds for the Provincial Universities of Zhejiang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agricultural pest and disease monitoring has recently become a crucial aspect of modern agriculture. Toward this end, this study investigates methodologies for implementing low-power, high-performance convolutional neural networks (CNNs) on agricultural edge detection devices. Recognizing the potential of field-programmable gate arrays (FPGAs) to enhance inference parallelism, we leveraged their computational capabilities and intensive storage to propose an embedded FPGA-based CNN accelerator design aimed at optimizing rice leaf disease image classification. Additionally, we trained the MobileNetV2 network using multimodal image data and employed knowledge distillation from a stronger teacher (DIST) as the hardware benchmark. The solution was deployed on the ZYNQ-AC7Z020 hardware platform using High-Level Synthesis (HLS) design tools. Through a combination of fine-grained pipelining, matrix blocking, and linear buffering optimizations, the proposed system achieved a power consumption of 3.21 W, an accuracy of 97.41%, and an inference speed of 43 ms per frame, making it a practical solution for edge-based rice leaf disease classification.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Provincial Universities of Zhejiang
  • Zhejiang Provincial Natural Science Foundation of China

Zitieren

APA

Zheng, J., Lv, Z., Li, D., Lu, C., Zhang, Y., Fu, L., Huang, X., Huang, J., Chen, D., & Zhang, J. (2025). FPGA-Based Low-Power High-Performance CNN Accelerator Integrating DIST for Rice Leaf Disease Classification. Electronics, 14(9), 1704. https://doi.org/10.3390/electronics14091704

Vancouver

Zheng J, Lv Z, Li D, Lu C, Zhang Y, Fu L, et al. FPGA-Based Low-Power High-Performance CNN Accelerator Integrating DIST for Rice Leaf Disease Classification. Electronics. 2025;14(9):1704. doi:10.3390/electronics14091704

BibTeX
@article{Zheng2025,
  author = {Zheng, Jingwen and Lv, Zefei and Li, Dayang and Lu, Chengbo and Zhang, Yang and Fu, Liangzun and Huang, Xiwei and Huang, Jiye and Chen, Dongmei and Zhang, Jingcheng},
  title = {FPGA-Based Low-Power High-Performance CNN Accelerator Integrating DIST for Rice Leaf Disease Classification},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {9},
  pages = {1704},
  doi = {10.3390/electronics14091704}
}
Kostenlos starten →