Vision-Language Based Real-Time Assistive System for Outdoor Navigation of the Visually Impaired in Indian Urban Environments

This paper presents a real-time assistive system for outdoor navigation of visually impaired users in complex Indian urban environments. A BLIP vision-language model is fine-tuned through a 3-stage LoRA training strategy on a custom 427-scene dataset built from Google Street View API imagery, yielding a +15.6% improvement across BLEU, METEOR, ROUGE and semantic similarity metrics. The system is deployed on a Raspberry Pi through an edge-cloud hybrid architecture, and covers the full research pipeline: dataset curation, model training, evaluation framework and edge deployment. The trained model is released on HuggingFace and the code is open-sourced.