ItemCompass helps find misplaced household objects with wearable AI
ItemCompass: Real-Time Edge-AI Wearable Vision for Tag-Free Domestic Object Retrieval
Human-Computer Interaction
Summary
Losing everyday things at home, especially for older people, is frustrating. The authors created ItemCompass, a smart pair of glasses that recognize and remember objects without needing tags. It listens to your voice and guides you to lost items using augmented reality. Their tests show the system is accurate and trusted by users while protecting privacy.
What this means in practice
- •For assistive technology developers: Create wearable devices that help elderly users locate household objects through voice commands and AR guidance without needing physical tags.$Commercial implications: Enables production of assistive smart glasses marketed to aging populations needing support with daily object retrieval.
- •For home automation integrators: Integrate edge-AI vision systems that build persistent spatial maps for seamless object tracking and retrieval in smart homes.
Authors
Tsz Lok Cheung, Jeff Kai-Tai Tang, Anthony Kong, Zackary P. T. Sin
Abstract
Misplacing household objects disrupts daily routines, especially for elderly users. ItemCompass addresses this with a real-time, tag-free wearable AR system that builds a persistent digital twin of the home for natural language object retrieval. A custom eyewear node streams visual and inertial data to an edge server, where YOLOv11n detection, Siamese re-identification, and a Pedestrian Dead Reckoning engine log object locations as Spatial Anchors in InfluxDB. Voice queries are resolved by a local Faster-Whisper and Qwen2 LLM pipeline, delivering concise spoken and AR guidance on a heads-up display. Evaluation shows 0.40 m localization drift, 97.5% step precision, and mAP@0.5 of 0.874, with users rating Accuracy and Trust at 4.6/5.0. The system highlights always-on sensing, conversational spatial memory, and privacy-by-design for wearable computing.