Assisting the Visually Impaired: Obstacle Detection and Warning System by Acoustic Feedback

Abstract

The aim of this article is focused on the design of an obstacle detection system for assisting visually impaired people. A dense disparity map is computed from the images of a stereo camera carried by the user. By using the dense disparity map, potential obstacles can be detected in 3D in indoor and outdoor scenarios. A ground plane estimation algorithm based on RANSAC plus filtering techniques allows the robust detection of the ground in every frame. A polar grid representation is proposed to account for the potential obstacles in the scene. The design is completed with acoustic feedback to assist visually impaired users while approaching obstacles. Beep sounds with different frequencies and repetitions inform the user about the presence of obstacles. Audio bone conducting technology is employed to play these sounds without interrupting the visually impaired user from hearing other important sounds from its local environment. A user study participated by four visually impaired volunteers supports the proposed system.

Obstacle detection for pedestrians with a visual impairment based on 3D imaging

“…[7] make use of data obtained from a stereo pair. A polar grid that delimits the region in which ob stacles can occur was defined and estimated empirically to 4.5 meters.…”

Indoor assistance for visually impaired people using a RGB-D camera

“…The former methods mostly use the concept of an occupancy grid, which is a quantization of the space in front of the user into a number of bins. In [10], the authors define a polar grid in front of the user which is subsequently projected on the ground plane and the bins of the grid are filled with 3D points that are located within the bounds of each bin. Obstacles are then defined as cells containing more then a predefined number of points.…”

Smartphone-Based Obstacle Detection for the Visually Impaired

“…Leung and Medioni [9] propose an odometry system using stereo images and an inertial measurement unit (IMU) to reduce drift errors. Papers [11][12][13] describe methods focused on obstacle detection and safe path estimation, that employ a stereo pair to improve estimation accuracy. However, stereo cameras are currently quite expensive, bulky and showy, as compared to a standard mobile device.…”