An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection
Open Access
- 3 June 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (11) , 2442
Abstract
Real-time deployment of modern object-detection networks on edge devices is challenging because of limited compute resources, external-memory bandwidth, and strict power constraints. To address these issues, this paper presents a host–FPGA collaborative accelerator for quantized YOLOv5n on a Xilinx Zynq-7100 platform. The proposed design includes a modular multi-operator neural processing unit supporting seven atomic operators, a Dual-Multiply Packing (DMP) scheme to improve DSP48E1-based INT8 convolution density, a cache–compute–cache dataflow with global ping-pong buffering to overlap DMA transfers and computation, and a Multi-Quantization Domain Alignment (MQDA) pipeline to preserve accuracy at Add and Cat fusion nodes. Implemented at 200 MHz, the prototype achieves 24.617 ms FPGA-side forward-inference latency, 36.686 ms end-to-end single-frame latency, 27.2 FPS system-level performance, 182.8 GOPS equivalent throughput, and 8.536 W on-chip power consumption, corresponding to 21.42 GOPS/W. Experimental results also show that INT8 quantization causes only limited accuracy degradation, while MQDA improves quantized detection accuracy by reducing cross-domain fusion error. These results demonstrate that the proposed architecture provides an effective balance among throughput, energy efficiency, hardware cost, and quantized accuracy for real-time edge object detection.Keywords
This publication has 22 references indexed in Scilit:
- FPGA-based accelerator for YOLOv5 object detection with optimized computation and data access for edge deploymentParallel Computing, 2025
- An FPGA-Based Reconfigurable Convolutional Neural Network Accelerator for Tiny YOLO-V3Circuits, Systems, and Signal Processing, 2025
- End-to-end acceleration of the YOLO object detection framework on FPGA-only devicesNeural Computing and Applications, 2023
- High-speed YOLOv4-tiny hardware accelerator for self-driving automotiveThe Journal of Supercomputing, 2023
- An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design2021
- Activation Function Architectures for FPGAs2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- High Density and Performance Multiplication for FPGA2018
- SSD: Single Shot MultiBox Detector2016
- You Only Look Once: Unified, Real-Time Object Detection2016