(IRTSD-Datasetv1)-Indian Road Traffic Sign Detection dataset

Citation Author(s):
Jackulin Mahariba
A
SRM Institute of Science and Technology
Aryan
.
SRM Institute of Science and Technology
Submitted by:
Aryan Aryan
Last updated:
Mon, 07/08/2024 - 07:35
DOI:
10.21227/ap4b-c439
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The advancement of machine and deep learning methods in traffic sign detection is critical for improving road safety and developing intelligent transportation systems. However, the scarcity of a comprehensive and publicly available dataset on Indian traffic has been a significant challenge for researchers in this field. To reduce this gap, we introduced the Indian Road Traffic Sign Detection dataset (IRTSD-Datasetv1), which captures real-world images across diverse conditions. Our dataset consists of 5141 images spanning 37 traffic sign classes, collected from over 90 cities in India, with varying distances and lighting conditions, using mobile phones. To demonstrate the effectiveness of our dataset, we evaluated it using YOLOv8, YOLOv10, and RT-DETR algorithms, achieving a mean average precision (mAP) of up to 98.25%. We believe that our dataset provides a solid foundation for future research in traffic sign detection or any computer vision task, contributing to significant advancements in this field.

Instructions: 

Download the ITSB-Datasetv1 ZIP file, extract it, and note that the images are in PNG format and not pre-divided into training and testing sets, allowing users to split the data as per their requirements.