Technical Name 基於深度學習之視障人士的行走輔助系統
Project Operator National Central University
Project Host 王文俊
Summary
We provides a wearable device for the visually impaired to walk outdoors. By the deep learning network, the system can recognizeguide the visually impaired to walk on safe areas such as sidewalkscrosswalk. In addition, it can recognize the types of common obstaclesguide the visually impaired to avoid it in advance. Finally, we can convert the Google Maps route into easy-to-understand voice prompts instruction to guide the visually impaired to move in the right direction.
Scientific Breakthrough
We proposed a  wearable device that can recognizeguide the visually impaired to walk on the sidewalkcrosswalk. We proposed easily understanding instructions to guide the visually impaired to walk outdoors, avoid obstacles,go to the destination.  Combining sensor informationobject detection network, we provided a robust obstacle avoidance methoda convenient store sign-approaching method to guide the visually impaired to approach the convenience store to solve the problem of insufficient GPS location.
Industrial Applicability
This technology can help the visually impairedis a powerful product for the assistive device market for the visually impaired. Except for the white cane, this product is one of the most reliable assistive devices for the visually impaired congenitalacquired.
Matching Needs
天使投資人、策略合作夥伴
Keyword wearable device visually impaired deep learning semantic segmentation neural network object detection neural network obstacle avoidance depth estimate
other people also saw