Voice Navigator Project

Results:

Objects in increasing order of distance from user are cell phone, and person.

Pre-trained Models

• YoloV3 Object Detection (236.5 MB)
• NYU Depth V2 (164.9 MB)

Execution

• git clone https://github.com/anshuman03sinha/Voice-Navigator from a python enabled terminal/editor.
• pip install -r requirements txt to install all necessary packages.
• python app.py to run the final app.
• The basic Flask app will run on the users' localhost port (webcam access necessary).

On The Web

• Presentation
• Demo

Cited

@article{Alhashim2018,
  author    = {Ibraheem Alhashim and Peter Wonka},
  title     = {High Quality Monocular Depth Estimation via Transfer Learning},
  journal   = {arXiv e-prints},
  volume    = {abs/1812.11941},
  year      = {2018},
  url       = {https://arxiv.org/abs/1812.11941},
  eid       = {arXiv:1812.11941},
  eprint    = {1812.11941}
}