Adaptive Shoe-Based Indoor Navigation with Audio-Augmented Guidance

Visually impaired individuals often face difficulties in navigating their surroundings safely and identifying people in their environment. Traditional mobility aids such as walking sticks provide limited assistance and cannot offer advanced environmental awareness. To address these limitations, this paper presents the design and implementation of a Smart Shoe with Human Identification and Obstacle Detection with Voice Output. The proposed system integrates ultrasonic sensors, a NodeMCU microcontroller, and a camera-based human identification module to assist visually impaired users in real-time navigation. The ultrasonic sensors continuously monitor the surroundings and detect obstacles from different directions. When an obstacle is detected within a predefined distance, the microcontroller processes the sensor data and generates a voice alert through a headset to inform the user about the obstacle direction. In addition to obstacle detection, the system incorporates a human identification module using a webcam and computer vision techniques. The captured images are processed using Python and OpenCV libraries to detect and recognize faces from a stored database. Once a person is identified, the system generates a corresponding voice message to notify the user about the detected individual. The proposed system focuses on simplicity, portability, and real-time operation, combining embedded sensing technology with computer vision and voice output mechanisms. The developed prototype demonstrates an effective assistive navigation solution that enhances safety, independence, and social interaction for visually impaired individuals.