Implementation of an Obstacle Recognition System for the Blind

Abstract

The blind encounter commuting risks, such as failing to recognize and avoid obstacles while walking, but protective support systems are lacking. Acoustic signals at crosswalk lights are activated by button or remote control; however, these signals are difficult to operate and not always available (i.e., broken). Bollards are posts installed for pedestrian safety, but they can create dangerous situations in that the blind cannot see them. Therefore, we proposed an obstacle recognition system to assist the blind in walking safely outdoors; this system can recognize and guide the blind through two obstacles (crosswalk lights and bollards) with image training from the Google Object Detection application program interface (API) based on TensorFlow. The recognized results notify the blind through voice guidance playback in real time. The single shot multibox detector (SSD) MobileNet and faster region-convolutional neural network (R-CNN) models were applied to evaluate the obstacle recognition system; the latter model demonstrated better performance. Crosswalk lights were evaluated and found to perform better during the day than night. They were also analyzed to determine if a client could cross at a crosswalk, while the locations of bollards were analyzed by algorithms to guide the client by voice guidance.

Dynamic Crosswalk Scene Understanding for the Visually Impaired

“…It exploits semantic segmentation technology to help visually impaired perceive traversable areas, stairs, etc. Similarly, some crosswalk guidance systems [5][6][7][8][9][15] [29] which consist of crosswalk detection and PTL status discrimination are presented to tackle the challenge of crossing the roads.…”

Deep Learning-Based Portable Device for Audio Distress Signal Recognition in Urban Areas

“…Finally, we deployed the trained neural network model on a Raspberry Pi and evaluated the computational performance of the real-time recognition system (Section 3.4). Currently, the Raspberry Pi represent a useful element to construct inexpensive portable devices that compute complex tasks in real time [13,14]. We end this paper with some conclusions and future work (Section 4).…”