102-106
ACOUSTIC VISION – ACOUSTIC PERCEPTION BASED ON REAL TIME VIDEO ACQUISITION FOR NAVIGATION ASSISTANCE
Authors: RAO S.K., PRASAD A.B., SHETTY A.R., CHINMAI, HEGDE R., BHAKTHAVATHSALAM R
Number of views: 517
A smart navigation system based on an object detection mechanism through real time video processing has been designed to detect the presence of obstacles that impede its movement. This paper is discussed keeping in mind the navigation of the visually impaired. A PAL video camera feeds image frames pertaining within its vicinity at a rate of 30 fps to a Da-Vinci Digital Media Processor, DM642. The processor carries out image processing techniques on every frame and the result contains information about the object in terms of image pixels. The algorithm aims to select that object, among others detected in the frame, which poses maximum threat to the navigation. The selected object then translates to one out of three sounds, whose pitch informs navigator about the obstacles’ relative threat. This paper implements a more efficient algorithm compared to its predecessors.