microYOLO: Towards Single-Shot Object Detection on Microcontrollers

TL;DR

This paper explores the feasibility of deploying a simplified YOLO-based object detection model, microYOLO, on microcontrollers, demonstrating real-time performance and low resource usage for small images.

Contribution

It introduces microYOLO, a lightweight single-shot object detector capable of running on Cortex-M microcontrollers, enabling real-time detection with minimal resources.

Findings

Achieves 3.5 FPS on Cortex-M microcontrollers for 128x128 images.

Uses less than 800 KB Flash and 350 KB RAM.

Provides experimental accuracy results on three detection tasks.

Abstract

This work-in-progress paper presents results on the feasibility of single-shot object detection on microcontrollers using YOLO. Single-shot object detectors like YOLO are widely used, however due to their complexity mainly on larger GPU-based platforms. We present microYOLO, which can be used on Cortex-M based microcontrollers, such as the OpenMV H7 R2, achieving about 3.5 FPS when classifying 128x128 RGB images while using less than 800 KB Flash and less than 350 KB RAM. Furthermore, we share experimental results for three different object detection tasks, analyzing the accuracy of microYOLO on them.