Mobility Assistant For Visually Impaired

MAVI is an ambitious project aimed at enabling mobility for visually impaired individuals, specially in India.
A major challenge in this regard is the wide range of complexities that arise in the Indian Scenario due to non-standard practices.

Know More

Overview

After grand success of SmartCane,we identified more serious problems which could be solved using the current technologies. The three major problems we want to tackle with MAVI are:

  • Safety
  • Social Inclusion
  • Navigation
  • A mix of computer vision, web based and cloud based techniques are being used in order to achieve the same. The idea is to have a system which could work both offline and online since the network conditions aren't very reliable for a huge majority. Here is a recent presentation about the challenges we are facing from a computer vision perspective.

    Computer Vision Components

    Texture Classification

    Texture Classification

    Texture Classification is used to guide the visually impaired about oncoming potholes or sidewalks which can be used.

    Signboard Detection

    SignBoard Detection

    Signboards make life simpler for all of us. Being able to process signboards while walking is a critical requirement for independent mobility.

    Face Detection

    Face Detection

    The delight of meeting a friend on the way is often missed by a visually impaired person. Face Detection/Recognition enables social inclusion for the visually impaired.

    Animal Detection

    Animal Detection

    When using the cane to guide oneself, it is important to be aware of any animals in the way. It is a scenario very common in the Indian environment.

    SO WHAT YOU THINK ?

    Please feel free to share your precious feedback/suggestions with us. We'd also like to hear about similar work you're working on.

    Contact Us