Image and Video Dataset for Visually Impaired using Intel Realsense Camera

Citation Author(s):
Pratham
Mehta
Ninad
Mehendale
K J Somaiya College of Engineering
Submitted by:
Ninad Mehendale
Last updated:
Wed, 04/19/2023 - 04:41
DOI:
10.21227/e875-6m37
Data Format:
Research Article Link:
License:
437 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

The Dataset consists of two videos, one recorded with blindfold on and the other without blindfold recorded using a 1080p Intel RealSense depth camera. It contains the videos, images extracted using ffmpeg and processed video which is made of a video with skipped frames created using ffmpeg. The scope of the dataset is for machine vision purposes to allow for tasks such as instance segmentation. A hat fixed on the head of a blindfolded person is used to record walking activities. For the generation of this dataset, we have recorded videos and extracted images with a blindfold to emulate the slower and more careful gait of a visually impaired person.

Instructions: 

·      Extract the zip file

·      It contains 3 folders, the source videos, the extracted images and the processed video with skipped frames.

·      You can keep the necessary folders and delete the unnecessary ones

·      Now the dataset can be utilized according to your purposes

Funding Agency: 
Somaiya Vidyavihar University
Grant Number: 
2021-22

Comments

We are working on a depth estimation project that may need to record a dataset using Intel Realsense. Therefore, we would like to access this dataset as we consider it would be a good reference for us to setup and record our own data.

Submitted by Thai Hoa Huynh on Sun, 07/09/2023 - 21:20