In order to facilitate the visually impaired person in navigation, we have developed a prototype guidance system. The main assumption of this guidance system is that there are many straight paths in different real world scenarios. These straight paths have parallel edges, which when captured as an image seem to converge to a single point called the vanishing point. Proper feature extraction and mathematical modelling of the captured frame leads to the detection of these parallel edges. The vanishing point is then calculated and a decision system is formed which notifies the blind person about his/her deviation from a straight path. The scope of this system is limited to a straight path and has been tested in different lighting conditions and with different level of occlusion. A laptop mounted on a 2D robotic platform is used to develop and verify the robustness of the algorithm. Finally, a smartphone based real-time application has been implemented for this visual guidance system, in which the decision system returns an audio output to guide the visually impaired person. This application has an average execution rate of 20 frames per second, with each frame being of 320 by 240 pixel size. The system has an accuracy of 84.1% in a scenario with pedestrians and other objects, while without pedestrians it produces an accuracy of over 90%.
展开▼
