A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology

One of the recent news headlines is that a pedestrian was killed by an autonomous vehicle because safety features in this vehicle did not detect an object on a road correctly. Due to this accident, some global automobile companies announced plans to postpone development of an autonomous vehicle. Fur...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2019-07, Vol.9 (14), p.2941
Main Authors: Kwon, Donghwoon, Malaiya, Ritesh, Yoon, Geumchae, Ryu, Jeong-Tak, Pi, Su-Young
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Automation
Automobiles
Autonomous vehicles
Blind spot area
blind spot detection
Cameras
Clustering
Data processing
Deep learning
Electric vehicles
embedded board
Embedded systems
Histograms
internet of things
Model accuracy
Pattern recognition
Sensors
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the recent news headlines is that a pedestrian was killed by an autonomous vehicle because safety features in this vehicle did not detect an object on a road correctly. Due to this accident, some global automobile companies announced plans to postpone development of an autonomous vehicle. Furthermore, there is no doubt about the importance of safety features for autonomous vehicles. For this reason, our research goal is the development of a very safe and lightweight camera-based blind spot detection system, which can be applied to future autonomous vehicles. The blind spot detection system was implemented in open source software. Approximately 2000 vehicle images and 9000 non-vehicle images were adopted for training the Fully Connected Network (FCN) model. Other data processing concepts such as the Histogram of Oriented Gradients (HOG), heat map, and thresholding were also employed. We achieved 99.43% training accuracy and 98.99% testing accuracy of the FCN model, respectively. Source codes with respect to all the methodologies were then deployed to an off-the-shelf embedded board for actual testing on a road. Actual testing was conducted with consideration of various factors, and we confirmed 93.75% average detection accuracy with three false positives.
ISSN:2076-3417
2076-3417
DOI:10.3390/app9142941