Sep 2026· 2026 IEEE International Conference on Advances in Computing Research On Science Engineering and Technology (ACROSET)· pp. 1-7· 0 citations· 15 references
TL;DR
This paper proposes a multimodal AI-based smart glasses framework for environmental awareness and predictive navigation, which integrates a camera, GPS, and 9-axis IMU with YOLOv8n and MobileNetV2-SSD models optimized via TensorFlow Lite.
Abstract
Navigational autonomy remains a critical challenge for the visually impaired (VI) population, with over 2.2 billion individuals globally affected by some form of vision impairment. Traditional assistive tools provide immediate obstacle detection but lack long-range predictive awareness. This paper proposes a multimodal AI-based smart glasses framework for environmental awareness and predictive navigation. The framework integrates a camera, GPS, and 9-axis IMU with YOLOv8n and MobileNetV2-SSD models optimized via TensorFlow Lite. An Extended Kalman Filter (EKF) fuses IMU and GPS data for robust localization in urban environments. Bone conduction transducers deliver auditory feedback while preserving ambient sound awareness. Simulation results show 92.4% mAP detection accuracy and approximately 180 ms end-to-end latency on a Raspberry Pi 4 edge node. This framework is a significant step toward a real-time, offline-capable wearable assistant for the visually impaired.
The proposed prototype validates the feasibility of deploying privacy-preserving, edge-native assistive intelligence for cost-sensitive mobility assistance on an ultra-low-power Raspberry Pi Zero 2W.
Ali Akarma, Adeel Ahmad, Toqeer Ali Syed· arXiv.org· 0 citations
Independent mobility is a foundational requirement for the autonomy of blind and low-vision (BLV) individuals, yet the assistive technologies that support it have historically evolved slowly. This survey systematically reviews 108 peer-reviewed studies published between 2008 and 2026, organizing the field into four tec...
Abtin Zandi, Arian Ashrafi, Sarvin Nami et al.· 0 citations
Vision impairment affects over 2.2 billion people worldwide and continues to impose severe barriers to independent daily life, from safe outdoor navigation to reading signage and recognising familiar faces. Conventional aids such as the white cane provide limited scene awareness and cannot describe objects, read text,...
Shibu Chacko, H. J, Arya B. Shetty et al.· Iconic research and engineer...· 0 citations
The design and implementation of a low-cost, wearable visual aid that improves navigation safety for visually impaired individuals through real-time object detection and intelligent audio feedback and the feasibility of an affordable, edge-deployed wearable visual aid suitable for daytime navigation assistance is prese...
A. Dauda, N. Bello· Nipes journal of Energy Tech...· 0 citations
The integration of Artificial Intelligence (AI) into wearable assistive technologies offers transformative potential for enhancing mobility, spatial awareness, and autonomy among Blind and Visually Impaired (BVI) individuals. This study introduces a real-time, AI-powered wearable system combining object detection, scen...
Yahia Said, M. Afif, Abdelnasser Saber Mohamed· International Journal of Adv...· 0 citations
Proximal Spatial Intelligence (PSI) is introduced as a conceptual framework for understanding how mobile assistance may coordinate environmental sensing, action responses, and user feedback within the user’s near-body space, and a mid-fidelity drone prototype designed to explore coherent, vision-based hazard perception...
