# SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices

Source: [SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices](<https://www.sota2.com/research/paper/68fa70811e209131cea4b8e0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:44:00.333Z

Authors: Alexander Montgomerie-Corcoran, Petros Toupas, Zhewen Yu, Christos-Savvas Bouganis

Published: 2023-09-04T13:15:01.000Z

## Abstract

AI has led to significant advancements in computer vision and image processing tasks, enabling a wide range of applications in real-life scenarios, from autonomous vehicles to medical imaging. Many of those applications require efficient object detection algorithms and complementary real-time, low latency hardware to perform inference of these algorithms. The YOLO family of models is considered the most efficient for object detection, having only a single model pass. Despite this, the complexity and size of YOLO models can be too computationally demanding for current edge-based platforms. To address this, we present SATAY: a Streaming Architecture Toolflow for Accelerating YOLO. This work tackles the challenges of deploying stateof-the-art object detection models onto FPGA devices for ultralow latency applications, enabling real-time, edge-based object detection. We employ a streaming architecture design for our YOLO accelerators, implementing the complete model on-chip in a deeply pipelined fashion. These accelerators are generated using an automated toolflow, and can target a range of suitable FPGA devices. We introduce novel hardware components to support the operations of YOLO models in a dataflow manner, and off-chip memory buffering to address the limited on-chip memory resources. Our toolflow is able to generate accelerator designs which demonstrate competitive performance and energy characteristics to GPU devices, and which outperform current state-of-the-art FPGA accelerators.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.01587>)

[PDF](<https://arxiv.org/pdf/2309.01587.pdf>)
