microYOLO: Towards Single-Shot Object Detection on Microcontrollers
This work addresses the challenge of deploying object detection on resource-constrained microcontrollers, though it is incremental as it adapts existing YOLO methods.
The paper tackles the problem of enabling single-shot object detection on microcontrollers, achieving about 3.5 FPS on a Cortex-M device with less than 800 KB Flash and 350 KB RAM for 128x128 RGB images.
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.