Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2018-08-21 000000m 00:48:14 - Overview

ok109
Attribute Current Content New
Name (Institute + Shorttitle)Exclusively-Dark-Image-Dataset 
Description (include details on usage, files and paper references)In order to facilitate a new object detection and image enhancement research, we introduce the Exclusively Dark (ExDark) dataset (CVIU - under review). The Exclusively Dark (ExDARK) dataset is a collection of 7,363 low-light images from very low-light environments to twilight (i.e 10 different conditions) with 12 object classes (as to PASCAL VOC) annotated on both image class level and local object bounding boxes.

Paper (PDF):
https://arxiv.org/abs/1805.11227

Dataset Information (size = 1.5Gb):
The images are kept in individual class folders following the image class labels:

Bicycle - 652 images
Boat - 679 images
Bottle - 547 images
Bus - 527 images
Car - 638 images
Cat - 735 images
Chair - 648 images
Cup - 519 images
Dog - 801 images
Motorbike - 503 images
People - 609 images
Table - 505 images

(Total : 7,363 images)

If you find this dataset useful for your research, please cite:
@article{Exdark,
title={Getting to Know Low-light Images with The Exclusively Dark Dataset},
author={Loh, Yuen Peng and Chan, Chee Seng},
journal={arXiv preprint arXiv:1805.11227},
year={2018}
}
 
URL Linkhttps://github.com/cs-chan/Exclusively-Dark-Image-Dataset 
Files (#)7363 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)object detection, low light dark images, image enhancement 
Last Changed2018-08-21 
Turing (2.12+3.25=?) :-)