Object Detection And Recognition For Blind Assistance.

EasyChair Preprint 1962

Abstract

The aim of this is to explore different methods for helping computers interpret the real world visually, investigate solutions to those methods offered by the open source computer vision library, OpenCV, and implement some of these in a Raspberry pi based application for detecting and keeping track of objects. The main focus rests on the practical side of the project.

The result of this thesis is a GNU/Linux based C/C++ application that is able to detect and keep track of object by reading the pixel value of frame captured by the Raspberry Pi camera module. The application also transmits some useful information, such as coordinates and size, to other computers on the network that send appropriate query.

Keyphrases: computer vision technique, object detection, object recognition

@booklet{EasyChair:1962,
  author    = {Akshay Shinde and Pratik Bhagat and Sairaj Dhobale},
  title     = {Object Detection And Recognition For Blind Assistance.},
  howpublished = {EasyChair Preprint 1962},
  year      = {EasyChair, 2019}}