Enhanced speed bump detection system for driver assistance system (DAS) using Otsu’s threshold over adaptive Gaussian threshold for higher accuracy

The aim of this research is to detect speed bumps from a given image using Otsu’s threshold for better detection accuracy. The total sample size of 120 has been split into two different groups. The first group holds 60 samples and was tested on Adaptive Gaussian Threshold whereas the next group hold...

Full description

Saved in:
Bibliographic Details
Main Authors: Priyanka, R., Priya, W. D., Ramasenderan, N.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Adaptive sampling
Algorithms
Image enhancement
Road humps
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The aim of this research is to detect speed bumps from a given image using Otsu’s threshold for better detection accuracy. The total sample size of 120 has been split into two different groups. The first group holds 60 samples and was tested on Adaptive Gaussian Threshold whereas the next group holds 60 samples and was tested with Otsu’s Threshold. The sample size for each group is 10. The research’s dataset was downloaded from Kaggle.com and consists of 6000 photos, of which 4800 are utilised for training and the remaining ones for testing. The G power for this project is approximately around 80%. The resultant accuracy is higher for the Otsu’s Threshold (88.40%) than that of Adaptive Gaussian Threshold (85.60%). The achieved significance value is 0.002 (p
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0229211