Scribd
Upload
12 views1 page

New Abstract CNN

.

Uploaded by

Rutuja Jadhav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views1 page

New Abstract CNN

.

Uploaded by

Rutuja Jadhav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

ABSTRACT

Priority No.1 13/09/2024

Traffic Sign Detection Under Adverse Environmental Conditions Based on CNN

A reliable Traffic Sign Detection and Recognition (TSDR) system is important for making
autonomous driving technology work well. Many researchers have studied this, but most of the
research focuses on perfect conditions and ignores challenges like rain, snow, and fog, which can
blur images and make detection harder. This paper looks at the problems TSDR faces in bad
weather conditions like rain, snow, fog, dirty lenses, and blurred lenses.

To solve this, a new method using a Convolutional Neural Network (CNN) is proposed. It has
three parts: a module to detect the type of bad weather using VGG19, an image enhancement
module called Enhance-Net to improve visibility in specific areas like traffic signs, and a traffic
sign detection module using YOLOv4 to make it faster. Tests with the CURE-TSD dataset
show that this system can reach an accuracy of 95.03 per and work at 12.79 frames per second,
making it both fast and reliable under tough conditions.

References
[1] QIANG GAO 1 , HUIPING HU2 , AND WEI LIU
Traffic Sign Detection Under Adverse Environmental Conditions Based on CNN

[2] H. H. Meng, H. B. Jiang, and T. B. Tang “Global development status and trends of au-
tonomous driving (Part 1),” East China Sci. Technol., vol. 23, no. 9, pp. 66–68, 2014.

[3] A. Mogelmose, M. M. Trivedi, and T. B. Moeslund “Vision-based traffic sign detection and
analysis for intelligent driver assistance systems: Perspectives and survey,” IEEE Trans.
Intell. Transp. Syst., vol. 13, no. 4, pp. 1484–1497, Dec. 2012.

[4] S. Chakraborty and K. Deb “Bangladeshi road sign detection based on YCbCr color model
and DtBs vector,” in Proc. Int. Conf. Comput. Inf. Eng. (ICCIE), Nov. 2015, pp. 158–161.
conference/jouranal name year

Guide, Student,
Dr.T.V.Bhandare Jadhav Rutuja Ramesh
Deptt. of IT. Engg. TE(IT. Engg.) Roll No. 243343

You might also like