Few shot clustering for indoor occupancy detection with extremely low-quality images from battery free cameras

TL;DR

This paper introduces a novel few shot clustering approach for indoor occupancy detection using extremely low-quality, privacy-preserving images from battery-free cameras, enabling low-cost, adaptive, and privacy-conscious occupancy monitoring.

Contribution

It presents a combined few shot learning and clustering algorithm tailored for ultra-low-quality images, with validation on benchmark datasets and real-world streaming data from innovative battery-free cameras.

Findings

Effective occupancy detection with minimal labeled data

Adaptive online clustering improves accuracy over time

Successful deployment on real battery-free camera data

Abstract

Reliable detection of human occupancy in indoor environments is critical for various energy efficiency, security, and safety applications. We consider this challenge of occupancy detection using extremely low-quality, privacy-preserving images from low power image sensors. We propose a combined few shot learning and clustering algorithm to address this challenge that has very low commissioning and maintenance cost. While the few shot learning concept enables us to commission our system with a few labeled examples, the clustering step serves the purpose of online adaptation to changing imaging environment over time. Apart from validating and comparing our algorithm on benchmark datasets, we also demonstrate performance of our algorithm on streaming images collected from real homes using our novel battery free camera hardware.