Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT

TL;DR

This paper develops and implements an energy-efficient real-time vision pipeline on ultra-low-power sensors for IoT, enabling effective detection and tracking with minimal power consumption.

Contribution

It introduces a novel embedded pipeline for real-time detection, classification, and tracking on smart vision sensors, optimizing energy efficiency for IoT applications.

Findings

Power consumption of 7.5 mW during inference

Inference time of 8 ms achieved

Effective background filtering for vision tasks

Abstract

The Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer vision applications, requiring the acquisition of images from specific devices. The need for high-end cameras often penalizes this process since they are power-hungry and ask for high computational resources to be processed. Thus, the availability of novel low-power vision sensors, implementing advanced features like in-hardware motion detection, is crucial for computer vision in the IoT domain. Unfortunately, to be highly energy-efficient, these sensors might worsen the perception performance (e.g., resolution, frame rate, color). Therefore, domain-specific pipelines are usually delivered in order to exploit the full potential of these cameras. This paper presents the development, analysis, and embedded implementation of a realtime detection, classification and tracking pipeline able to exploit the full potential of background filtering Smart Vision Sensors (SVS). The power consumption obtained for the inference - which requires 8ms - is 7.5 mW.