BED: A Real-Time Object Detection System for Edge Devices

TL;DR

BED is a real-time object detection system optimized for edge devices, combining a tiny DNN model with efficient inference on MAX78000 hardware, enabling accurate detection with low latency and energy consumption.

Contribution

This paper introduces BED, a complete, open-source object detection system for edge devices that integrates model training, quantization, and deployment on a specialized DNN accelerator.

Findings

Achieves 91.9 ms inference time with a 300-KB model

Consumes only 1.845 mJ of energy per inference

Provides accurate detection on resource-constrained hardware

Abstract

Deploying deep neural networks~(DNNs) on edge devices provides efficient and effective solutions for the real-world tasks. Edge devices have been used for collecting a large volume of data efficiently in different domains. DNNs have been an effective tool for data processing and analysis. However, designing DNNs on edge devices is challenging due to the limited computational resources and memory. To tackle this challenge, we demonstrate Object Detection System for Edge Devices~(BED) on the MAX78000 DNN accelerator. It integrates on-device DNN inference with a camera and an LCD display for image acquisition and detection exhibition, respectively. BED is a concise, effective and detailed solution, including model training, quantization, synthesis and deployment. The entire repository is open-sourced on Github, including a Graphical User Interface~(GUI) for on-chip debugging. Experiment results indicate that BED can produce accurate detection with a 300-KB tiny DNN model, which takes only 91.9 ms of inference time and 1.845 mJ of energy. The real-time detection is available at YouTube.