Pre‐training Dataset Generation Using Visual Explanation for Classifying Beam of Vehicle Headlights from Nighttime Camera Image

For Automatic High Beam (AHB), the authors are working on a study to classify beam of car headlights as ‘High’ and ‘Low’ by realizing the presence of vehicle on road from nighttime in‐vehicle camera image using deep learning. In general, weights of deep learning model are pre‐trained on a large data...

Full description

Saved in:
Bibliographic Details
Published in:IEEJ transactions on electrical and electronic engineering 2021-12, Vol.16 (12), p.1603-1611
Main Authors: Oyabu, Tatsuya, Sultana, Rebeka, Sakagawa, Yuta, Ohashi, Gosuke
Format: Article
Language:English
Subjects:
Cameras
convolutional neural network
Datasets
Deep learning
Domains
Headlamps
Headlights
Image classification
intelligent transportation systems
Machine learning
Night
Object recognition
pre‐training
Training
visual explanation
Weights & measures
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For Automatic High Beam (AHB), the authors are working on a study to classify beam of car headlights as ‘High’ and ‘Low’ by realizing the presence of vehicle on road from nighttime in‐vehicle camera image using deep learning. In general, weights of deep learning model are pre‐trained on a large dataset which are then used as initial weights for other tasks such as image recognition. However, it has been reported that even if the pre‐trained weights are used as the initial weights, it is not a factor of accuracy improvement when domain differs. It is important to pre‐train a model on a dataset that is suitable for target domain. Therefore, we propose a method to generate a pre‐training dataset that can be easily created by using visual explanation which represents where a deep learning model is looking at when performs a task. Then, we applied the proposed pre‐training dataset on the headlight beam classification in the nighttime in‐vehicle camera image and verified the effectiveness of our method. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.
ISSN:1931-4973
1931-4981
DOI:10.1002/tee.23465