fairfolio
Saved Projects

AI Nightguard Vision+

CSEF · 2026 Electronics & Electromagnetics (Junior Division)

Abishrudha Sabari

Overview

Pedestrians face significantly increased risk at night and during rainy conditions due to poor visibility, reflective glare, water-filled potholes, sidewalk cracks, and hidden obstacles. These hazards are difficult to detect in low illumination and contribute to thousands of preventable injuries each year, particularly in areas with limited lighting or infrastructure. This project presents NightGuard Vision+, a smartphone-based electronic sensing system that combines computer vision and artificial intelligence to detect pedestrian hazards in real time. The system uses the smartphone camera as an optical electronic sensor to capture reflected electromagnetic light signals from the environment under low-light and wet conditions. These electronic image signals are processed using machine-learning models trained on a custom dataset of nighttime and rainy-weather scenes to identify dark zones, puddles, slippery surfaces, potholes, cracks, and obstacles before they reach the pedestrian’s path. NightGuard Vision+ converts the detected electronic signals into immediate visual, audio, or vibration alerts, enabling early hazard awareness. The research evaluates how low illumination, surface reflection, and glare affect electronic signal capture and detection accuracy, and measures the system’s response time and reliability across varying environmental conditions. By integrating electronic optical sensing with real-time AI processing, NightGuard Vision+ demonstrates a scalable and low-cost safety technology that enhances pedestrian awareness and accessibility especially for visually challenged individuals while advancing practical applications in electronics based environmental sensing and intelligent hazard detection systems.

Competition history

  • CSEF 2026 Electronics & Electromagnetics (Junior Division) · Entry J-10-02

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google