fairfolio
Saved Projects

Eye Track: An Indoor Navigation System for the Visually Impaired

CSEF · 2018 Computational Systems & Analysis

Saurav S. Gandhi · Cabrillo (Juan) Middle School, Santa Clara, Santa Clara County

Overview

Objectives/Goals Most individuals can't detect physical obstacles and avoid them. For example, if a table is blocking one's path, most people would walk around it to get to the other side. But unfortunately, visually impaired people don't have this ability. This project focuses on creating a wearable, assistive technology, for the visually impaired, that allows them to navigate their indoor surroundings. Methods/Materials There have been many attempts to solve this problem with the use of sensors, vibrotactile and voice feedback, computer vision cameras, and RFID technology. The Eye-Track was created using a cheap computer vision camera (cmuCam5 Pixy Cam), vibration motors for vibrotactile feedback, and a fanny pack. This camera is capable of recording color signatures of objects and detects pre-programmed obstacles, by its hue. The Eye-Track was programmed to vibrate left or right, depending on the placement of the obstacle in the camera's field of vision, to aid the user in avoiding the obstacle. Eye-Track also incorporates an emergency button connected to the user's phone via Bluetooth, to contact a family member via SMS in case of an emergency. Results This product was tested in an obstacle course for the blindfolded user to walk through. The test criteria were based off on whether the user was able to identify the obstacle, avoid the obstacle, reach the destination, and make it through the obstacle course without touching a single obstacle. The success (%) was calculated for one, two and three obstacles. In summary, the "Eye-Track" product was 87.5% successful with one obstacle, 85% successful with two obstacles, and 72.5% successful with three obstacles. Conclusions/Discussion In conclusion, the success percentage decreased as the number of obstacles increased. A more sophisticated computer vision camera, with the ability to store more signatures and calculate depth would further this product. Additionally, there were numerous qualitative learnings related to the pace of walking, the distance between objects, and external light conditions. Improving these components could make the Eye-Track safer, and more apt for mass production.

Summary statement

A wearable computer vision based indoor navigation system, for the visually impaired.

Help received

I received help from my teacher, Ms. Scilingo who was my advisor for this project and guided my thinking as I developed the initial design of the wearable. She provided feedback on the multiple options I was considering. I also received help from my parents in funding the project, and providing support as I

Competition history

  • CSEF 2018 Computational Systems & Analysis · Entry J0806

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google