SceneNarrator AI — Real-Time Scene Description for the Visually Impaired

Entreprise partenaire — révélée une fois votre stage confirmé

Compétences recherchées

Sujet du stage

Turning a camera feed into a clear, spoken description of what's ahead — a doorway, a person approaching, stairs — can make daily navigation meaningfully easier for a visually impaired user. What you'll work on : • Integrate an object detection pipeline processing a live camera feed • Use a language model to turn detected objects and scene context into a clear, spoken description • Build a simple, accessible mobile interface with audio-first interaction What we're looking for : • Solid working knowledge of React Native or Flutter expected. • Familiarity with Pretrained Object Detection is a plus. • Attention to detail and clear documentation habits. What you'll get : • Guidance from a mentor specialized in computer vision, through your progress report • A portfolio-ready project • Certificate tied to project completion • Best-performing candidates may be recommended for pre-hire or job opportunities