Pedestrian crossing guide based on Android-Cloud platform for blind people
Date
2014
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
BRAC University
Abstract
This paper presents an automatic system which can detect road traffic and let blind people know about that so that they can easily cross the road. In the recent years, Android-driven mobile phones have got popularity among users and developers as well. In the first place, we have selected Android-driven phone to get the desired output. We have used real time image processing system to detect traffic condition of a road. To implement this, at first we needed a camera with good resolutions, a methodology which will give the decisions and last but not the least Internet connection. The captured image will run through the application and then the application automatically sends this information to the cloud. The cloud will automatically send information to the blind by internet whether it is safe to cross the road or not. Later, it became so complex that we had to change our path and decided to make a custom application which will automatically decide whether it is safe to cross the road or not by capturing instant images and process using OpenCV.
Description
This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2014.
Cataloged from PDF version of thesis report.
Includes bibliographical references (page 34).
Cataloged from PDF version of thesis report.
Includes bibliographical references (page 34).
Keywords
Object recognition, Optical Flow, Object detection, Road sign identification,, Computer science and engineering
