EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Design And Implementation Of An XNOR-Based Variable-Precision Object Detection Accelerator For Real-Time Edge AI Applications

Dr. Javeed MD, Dr. Srinivasa Reddy Dumpa, Kammampati Saisri, Varda Manasa

Adolescência e Saúde · 17.08.2026 · 21 (6s) · 347-355

DOI: 10.67440/ahj.v21i6s.1625 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Adolescência e Saúde, online erschienen am 17.08.2026. Verfasst von Dr. Javeed MD und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a hardware-efficient object detection accelerator based on XNOR-driven variable-precision computation for real-time edge artificial intelligence. The proposed network combines DenseToRes and transition layers to preserve feature information under aggressive quantization. Binary convolution is executed through XNOR and population-count operations, replacing most multiplier-based multiply-accumulate units. To maintain detection accuracy, the architecture supports 1-bit, 2-bit, and 8-bit modes so that sensitive layers can use higher precision while deeper layers operate at reduced precision. A parallel array of 64 processing elements performs multiple output-channel computations concurrently using an output-stationary dataflow. The accelerator integrates on-chip feature and weight memories, data-fetch units, batch normalization, RPReLU activation, quantization, pooling, and lightweight control logic. AXI-based interfacing enables integration with an embedded processing system and external memory. The resulting architecture reduces arithmetic complexity, memory bandwidth, and power consumption while supporting scalable real-time object detection on FPGA-based edge platforms.

Zitieren

APA

MD, D. J., Dumpa, D. S. R., Saisri, K., & Manasa, V. (2026). Design And Implementation Of An XNOR-Based Variable-Precision Object Detection Accelerator For Real-Time Edge AI Applications. Adolescência e Saúde, 21(6s), 347-355. https://doi.org/10.67440/ahj.v21i6s.1625

Vancouver

MD DJ, Dumpa DSR, Saisri K, Manasa V. Design And Implementation Of An XNOR-Based Variable-Precision Object Detection Accelerator For Real-Time Edge AI Applications. Adolescência e Saúde. 2026;21(6s):347-355. doi:10.67440/ahj.v21i6s.1625

BibTeX
@article{MD2026,
  author = {MD, Dr. Javeed and Dumpa, Dr. Srinivasa Reddy and Saisri, Kammampati and Manasa, Varda},
  title = {Design And Implementation Of An XNOR-Based Variable-Precision Object Detection Accelerator For Real-Time Edge AI Applications},
  journal = {Adolescência e Saúde},
  year = {2026},
  volume = {21},
  number = {6s},
  pages = {347--355},
  doi = {10.67440/ahj.v21i6s.1625}
}
Kostenlos starten →