Indoor Navigation Assistant for Visually Impaired by Pedestrian Dead Reckoning and Position Estimative of Correction for Patterns Recognition

:This paper presents a guided audio Indoor navigation system built in a wearable device designed to work with a hybrid mapping. This mapping uses radio frequency tags (RF) and visual markers located within a known environment. The system allows visually impaired users to perform a guided navigation safe and fast, and has a low computational complexity. The methodological approach chosen divides the system into two phases: an offline and another online. In the offline phase, the interior mapping is done by building markers to generate a contextual database, which increases the quality of the location indication. The online phase, where the indoor navigation is performed, is based on a proximity method, recognition of visual pattern, odometry, and ultrasonic perception of obstacles. The results showed rates higher than 90.00% for the recognition of visual and RF markers with average computation time of 0.4 seconds, and more than 95.00% of positive ultrasonic perceived barriers.